Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience

Makvandi, Mehdi; Khodabakhshi, Zeinab; Liu, Yige; Li, Wenjing; Yuan, Philip F.

doi:10.3390/su17156973

Open AccessArticle

Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience

by

Mehdi Makvandi

^1,2

,

Zeinab Khodabakhshi

²,

Yige Liu

¹,

Wenjing Li

¹

and

Philip F. Yuan

^1,*

¹

College of Architecture and Urban Planning, Tongji University, Shanghai 200092, China

²

College of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China

^*

Author to whom correspondence should be addressed.

Sustainability 2025, 17(15), 6973; https://doi.org/10.3390/su17156973

Submission received: 7 June 2025 / Revised: 9 July 2025 / Accepted: 16 July 2025 / Published: 31 July 2025

(This article belongs to the Section Sustainable Urban and Rural Development)

Download

Browse Figures

Versions Notes

Abstract

In rapidly urbanizing environments, environmental stressors—such as air pollution, noise, heat, and green space depletion—substantially exacerbate public health burdens, contributing to the global rise of non-communicable diseases, particularly hypertension, cardiovascular disorders, and mental health conditions. Despite expanding research on green spaces and health (+76.9%, 2019–2025) and optimization and algorithmic approaches (+63.7%), the compounded and synergistic impacts of these stressors remain inadequately explored or addressed within current urban planning frameworks. This study presents a Mixed Methods Systematic Review (MMSR) to investigate the potential of AI-driven urban design optimizations in mitigating these multi-scalar environmental health risks. Specifically, it explores the complex interactions between urbanization, traffic-related pollutants, green infrastructure, and architectural intelligence, identifying critical gaps in the integration of computational optimization with nature-based solutions (NBS). To empirically substantiate these theoretical insights, this study draws on longitudinal 24 h dynamic blood pressure (BP) monitoring (3–9 months), revealing that chronic exposure to environmental noise (mean 79.84 dB) increases cardiovascular risk by approximately 1.8-fold. BP data (average 132/76 mmHg), along with observed hypertensive spikes (systolic > 172 mmHg, diastolic ≤ 101 mmHg), underscore the inadequacy of current urban design strategies in mitigating health risks. Based on these findings, this paper advocates for the integration of AI-driven approaches to optimize urban environments, offering actionable recommendations for developing adaptive, human-centric, and health-responsive urban planning frameworks that enhance resilience and public health in the face of accelerating urbanization.

Keywords:

urbanization; environmental stressors; AI-based optimization; cardiovascular risks; urban health resilience

1. Introduction

Rapid urbanization intensifies environmental stressors that alter urban ecosystems, threaten public health, and jeopardize long-term sustainability [1,2,3,4]. Researchers categorize these stressors as physical (e.g., noise > 65 dB, thermal extremes) [1], chemical (e.g., air pollutants like PM_2.5 > 25 μg/m³) [2], biological (e.g., green space depletion < 9 m²/capita) [3], and psychosocial (e.g., traffic-induced stress and anxiety) [4]. These factors disrupt physiological homeostasis and increase disease susceptibility, thereby undermining environmental and public health outcomes. Many studies examine each stressor in isolation, yet growing evidence reveals their interactive and synergistic effects [5,6,7,8]. These interacting stressors contribute to the rising global burden of hypertension [9], cardiovascular diseases [10], and mental health disorders [11]. For instance, simultaneous exposure to noise and air pollution can increase the risk of hypertension by up to 1.7-fold [12]. Currently, 56% of the global population resides in urban areas—a number expected to rise by 2.8 billion by 2050 [13]. Urban centers thus become hotspots of compounded health vulnerabilities, particularly in rapidly developing nations, where the combined effects of environmental and social stressors on human health remain insufficiently addressed [14,15]. This situation underscores the urgent need to develop sustainable urban environments that prioritize public health.

Recent literature (Table 1) highlights key thematic intersections between urbanization and public health, particularly regarding cardiovascular risks. Studies conducted up to 2024 established a robust link between urban expansion and the prevalence of chronic conditions, such as hypertension and cardiovascular disease (see [15,16,17]). These findings are underpinned by research on environmental stressors, notably air pollution and traffic-related emissions, which have been identified as key contributors to the worsening of cardiovascular conditions (see studies [9,10,18]). Despite these advancements, few studies have adopted a comprehensive approach to integrate the multifactorial nature of urban stressors—such as noise, heat, and pollution—and their synergistic effects on public health.

To address this gap, the present study utilizes a Mixed Methods Systematic Review (MMSR) approach [19], synthesizing recent innovations in AI-powered urban design optimization. This review focuses on the interconnected dynamics of urbanization, traffic-related pollution, green infrastructure, and architectural intelligence, with particular attention to their combined effects on human health. It underscores how data-driven frameworks in urban planning can mitigate the harmful effects of environmental stressors and enhance urban health resilience. Additionally, this review emphasizes the pivotal role of green spaces in improving urban health outcomes (e.g., studies [20,21,22]); however, a notable gap persists in leveraging AI-driven models to systematically optimize these environments for maximal health benefit ([23,24,25]).

Building upon this review, this study also incorporates original experimental findings from a 24 h dynamic blood pressure (BP) study conducted over 3–9 months. This dual-pronged approach significantly enhances the empirical depth of the research, providing compelling evidence of a robust association between prolonged exposure to environmental stressors and the onset of hypertension, cardiovascular events, and stroke. These results underscore the critical role of environmental factors in exacerbating cardiovascular risks, further reinforcing the need for innovative urban design solutions.

Furthermore, studies exploring AI-based optimization (e.g., [7,26,27]) demonstrate promise in creating healthier urban spaces. However, the integration of AI with traditional urban planning practices remains underdeveloped ([20,28,29]). This study, therefore, critically evaluates the transformative potential of AI-driven optimization strategies in designing health-promoting urban environments, particularly in rapidly urbanizing regions. By synthesizing artificial intelligence (AI), nature-based solutions (NBS), and architectural intelligence, it offers a comprehensive review and proposes an evidence-based framework (detailed in Section 3.4) to address complex health risks stemming from environmental stressors. This framework emphasizes the integration of innovative, AI-driven solutions to optimize urban spaces, mitigate cardiovascular and other health risks, and support sustainable, adaptive urban development. By identifying existing research gaps and synthesizing interdisciplinary approaches, this study presents actionable strategies to mitigate urban health risks, fostering sustainable urban futures and advancing the design of more resilient, health-oriented cities.

Table 1. Representative reviews of existing research.

Literature	Year	Key Thematic Interconnections	Focus Area	Core Insights and Study Contributions	Gaps/Opportunities
[30] [31] [32] [33] [34] [35] [36] [37] [38] [39] [40]	2024 2024 2024 2024 2024 2024 2023 2023 2021 2024 2020	Urbanization ↔ Health	The interplay between urban growth and public health challenges.	Identifies the multifaceted impacts of urbanization on physical and mental health, particularly chronic diseases like hypertension.	Limited exploration of holistic frameworks to mitigate urban stressors at a population scale.
[41] [42] [43] [44] [45] [46] [47] [48] [49]	2024 2024 2024 2024 2024 2023 2021 2021 2020	Traffic ↔ Pollution	The health impacts of air pollution, traffic emissions, and exposure to pollutants.	Establishes a strong link between traffic-related pollution and respiratory/cardiovascular diseases.	Synergistic effects with other stressors like noise and heat remain underexplored.
[50] [10] [51] [52] [53] [54] [55] [56] [57]	2024 2024 2024 2024 2023 2022 2021 2021 2020	Environmental ↔ Stressors	Synergistic impacts of noise, air pollution, and urban heat islands (UHIs) on chronic health conditions.	Highlights cumulative stressor impacts on cardiovascular health, emphasizing environmental determinants of hypertension.	Lack of integrated studies combining multiple environmental stressors and their systemic effects.
[44] [18] [12] [58] [59] [60]	2024 2024 2023 2023 2021 2021	Stressors ↔ Hypertension	The mechanistic links between chronic stressors and hypertension-related health risks.	Highlights pathways such as oxidative stress and inflammation linking environmental factors to hypertension.	Few interdisciplinary studies bridging environmental, biological, and societal perspectives.
[61] [62] [63] [64] [65] [66]	2024 2024 2024 2024 2024 2024	Traffic ↔ Noise ↔ Stress	Psychological impacts of noise pollution and traffic-related stress on mental health.	Explores the rise in mental health disorders (e.g., anxiety, depression) caused by urban noise exposure.	Sparse data on population-level interventions to address traffic noise and associated stressors.
[20] [21] [22] [23] [24] [25] [28] [29]	2024 2024 2024 2024 2024 2024 2024 2021	Green Spaces ↔ Health	The role of green infrastructure (parks, roofs, walls) in mitigating urban stressors and promoting well-being.	Quantifies health benefits such as reduced urban heat, improved air quality, and enhanced physical and mental health.	Limited adoption of AI-driven models to optimize green space placement for maximum impact.
[67] [68] [69] [70] [71] [72] [73]	2024 2024 2024 2024 2024 2024 2024	Optimization ↔ Algorithmic Approaches	Use of AI, machine learning, and predictive modeling to design healthier urban environments.	Pioneers data-driven approaches to optimize urban layout, infrastructure placement, and green spaces to reduce health risks.	Underdeveloped integration of AI with traditional urban planning methodologies.
[74] [75] [76] [77] [78] [79] [79]	2024 2024 2024 2024 2023 2022 2021	Architectural (Arc) ↔ Intelligence (AI)	ArcAI plays an important role in improving the efficiency of and efficacy of urban design processes.	AI-based solutions optimize urban design to address chronic health risks through improved environmental planning.	Few real-world applications of ArcAI for urban health risks; further research is needed on long-term impacts.
[15] [80] [81] [82] [83] [84] [85]	2024 2024 2023 2023 2022 2021 2021	Environmental Performance ↔ Design	The integration of environmental performance metrics into urban and architectural design strategies.	Provides a bridge between health-conscious urban design and measurable sustainability outcomes.	Insufficient frameworks linking environmental performance with public health outcomes in urban contexts.

2. Methodology

2.1. Design and Framework

To address the complex health challenges driven by rapid urbanization—particularly the cardiovascular risks associated with environmental stressors—this study implements a sophisticated dual-phase methodological framework. Phase 1, the Mixed Methods Systematic Review (MMSR), synthesizes and distills critical insights from existing literature. Phase 2, Empirical Data Collection and Analysis (EDCA), substantiates these insights with real-world evidence, enhancing empirical robustness. Strategically integrated, these phases form a coherent and rigorous approach that fuses conceptual depth with applied relevance. Section 2.7 elaborates on this methodological trajectory—from systematic synthesis to data-driven validation—offering a comprehensive structure to assess urbanization’s impact on cardiovascular health.

2.2. Research Questions

This study tackles the following key research questions:

What are the primary environmental stressors linked to urbanization, and how do they fuel chronic illnesses, health disorders, and cardiovascular diseases?
Despite widespread acknowledgment in the literature of urbanization’s health impacts, systematic analyses remain scarce on how specific stressors—such as air pollution, noise, and extreme temperatures—translate into public health burdens.
How do urban stressors such as air pollution, noise, and climate-induced heat extremes drive hypertension and cardiovascular incidents?
A critical gap remains in understanding the mechanisms by which urban stressors contribute to pathogenesis and disease evolution, particularly through their interaction in complex urban environments.
To what extent can AI-driven design, optimization algorithms, and performance-based planning mitigate cardiovascular risks from urban environmental stressors?
Despite growing interest, the real-world efficacy and applicability of these advanced technologies in reducing urban health risks remain underexplored and poorly evidenced in the literature.
How do interdisciplinary approaches in urban design and public health converge to mitigate the adverse health effects of environmental stressors, and what scalability do these strategies possess in rapidly urbanizing regions?
A critical gap in the literature exists on the scalability and interdisciplinary integration of urban design, planning, and public health interventions. While studies have explored individual interventions, synergies, particularly in rapid urbanization, remain underexplored.

Together, these questions guide a comprehensive inquiry into how urban stressors, health outcomes, and technological innovations intersect, paving the way for actionable, resilient urban health strategies.

2.3. Search Strategy

A rigorous search was conducted across the Scopus database, covering peer-reviewed literature from 1942 to 2025 (Table 2), following the Mixed Methods Systematic Review (MMSR) approach outlined in Phase 1. Search terms, derived through bibliometric analysis (Figure 1; Table 3), highlighted emerging and high-impact themes in urban health research. For example, topics like ‘Green Spaces and Health’ and ‘Optimization and Algorithmic Approaches’ showed significant publication increases of 76.9% and 63.7%, respectively (2019–2025; Table 2).

These keywords, alongside Table 3 and Figure 1, further elucidate the selection logic and thematic connections, providing a clearer understanding of the rationale behind the chosen research directions. This review’s search strategy, aligned with emerging trends, facilitated an in-depth exploration of critical research trajectories, focusing on studies from 2019 to 2025. This approach particularly emphasized the complex interplay between urbanization, environmental stressors, and their impact on cardiovascular health, with a special focus on hypertension and related cardiovascular events.

2.4. Inclusion and Exclusion Criteria

Inclusion Criteria:
-
Peer-reviewed English publications (1942–2025).
-
Studies on environmental stressors (e.g., air pollution, noise, and climate change) and their impact on cardiovascular health, focusing on hypertension and stroke.
-
Research integrating AI-driven design, sustainable urban planning, and public health strategies to mitigate health risks.
-
Interdisciplinary studies bridging urban health, environmental science, and architectural design, emphasizing the health implications of urbanization.
Exclusion Criteria:
-
Non-urban studies or those lacking clear links between environmental stressors and health outcomes.
-
Publications without empirical data or failed causal/correlational evidence between stressors and cardiovascular health.

2.5. Data Extraction and Synthesis

Data extraction focused on key details, including author(s), publication title, journal, year, study objectives, methodology, and key findings, following Li et al.’s approach [19]. A qualitative thematic synthesis categorized findings of themes such as environmental stressors, cardiovascular health outcomes, and technological interventions. This was complemented by a quantitative analysis where applicable, particularly in relation to computational models. For example, in the thematic area of ‘Urbanization and Health’, 21,266 documents were found (1956–2025), with 10,843 between 2019 and 2025, and 7486 articles after applying the English-language filter. Similarly, ‘Traffic and Pollutants’ yielded 20,907 documents (1962–2025), with 8375 from 2019 to 2025, and 7118 articles meeting the language criteria. Table 2 presents a detailed overview of these findings, illustrating research growth and article numbers across each theme.

2.6. Visualizing Network and Bibliometric Trends with VOSviewer and VS Code

Bibliometric analysis was performed using VOSviewer (version 1.6.19) to generate co-authorship, citation, and keyword co-occurrence networks (Table 3), providing deep insights into the intellectual structure of the field and highlighting key clusters and emerging trends in urban health, environmental stressors, and cardiovascular outcomes. The visualizations enabled the identification of research gaps and supported hypothesis development for further investigation. To further refine the analysis, AI-powered features through VS Code were integrated, enhancing the visual outputs and emphasizing underlying relationships among key variables. This combined approach enabled a more comprehensive and nuanced interpretation of the data, unveiling deeper connections within the research domain. Figure 2 illustrates an example of these refined relationships.

2.7. Rigorous Overview of the Two-Phase Methodology

To address the multifaceted health challenges of urbanization, particularly cardiovascular risks from environmental stressors, this study employs a dual-phased research design, with the interconnected phases of MMSR and EDCA working synergistically to provide both theoretical depth and empirical precision.

2.7.1. Phase 1: Mixed Methods Systematic Review (MMSR)

As illustrated in Figure 3, this foundational review phase employed an MMSR, following the methodology outlined by Li et al. [19], to rigorously synthesize and critically examine the existing literature on the impacts of urbanization and environmental stressors on cardiovascular health. This study selected MMSR for its ability to integrate quantitative meta-analyses with qualitative thematic synthesis, enabling the precise identification of complex, non-linear interactions between environmental variables and public health outcomes. MMSR provided a clear, interdisciplinary lens, bridging urban design, environmental science, and public health. It proved especially effective in analyzing complex urban systems, where statistical data alone often fail to capture deeper contextual nuances [19]. Through the synthesis of diverse data types, MMSR revealed key research gaps, exposing both statistical trends and contextual factors, such as the urgent need for green infrastructure implementation. This flexibility enables it to address multidimensional interactions, e.g., the combined effects of air pollution and noise on cardiovascular health [12], which are often overlooked in conventional reviews. In addition to analyzing the effects of urbanization and environmental stressors on cardiovascular health, this phase also investigates the potential of emerging technologies—particularly AI-driven design solutions—to optimize environmental performance and urban form. Specifically, it explores how such technologies can mitigate urbanization-driven environmental stressors and reduce cardiovascular health risks. MMSR enables the creation of actionable frameworks (see Figure 4) by integrating empirical evidence with strategic design solutions, such as AI-driven urban optimization for cardiovascular protection. This integration bridges evidence and actionable intervention, culminating in a computational framework for optimizing urban health performance (Figure 4). The key thematic interconnections explored in this phase include the following:

Urbanization ↔ Health: Uncovering how urbanization alters environmental conditions and impacts public health, particularly cardiovascular health risks (↔ denotes an interconnected relationship).
Traffic ↔ Pollution: Investigating the role of traffic-related pollutants (e.g., particulate matter, nitrogen oxides, carbon monoxide, and noise) in increasing long-term cardiovascular health risks.
Environmental Stressors ↔ Hypertension: Analyzing the contribution of environmental stressors (air pollution, noise, and urban heat islands) to the onset and progression of hypertension.
Traffic Noise ↔ Chronic Stress ↔ Cardiovascular Disease: Exploring the pathways through which traffic noise leads to chronic stress, which in turn contributes to cardiovascular diseases.
Green Spaces ↔ Health: Assessing the potential of green spaces (e.g., parks, urban forests) in mitigating the adverse health effects of environmental stressors.
Optimization ↔ Algorithmic Approaches: Reviewing AI-driven approaches that optimize urban design for health, with a focus on improving air quality, noise reduction, and the availability of green spaces.
Architectural Intelligence ↔ Public Health: Exploring how AI-augmented architectural intelligence can integrate into urban planning to reduce environmental stressors and enhance public health.
Environmental Performance ↔ Sustainable Design: Exploring the role of sustainable building techniques, smart city technologies, and resilient design principles in mitigating cardiovascular health risks.

By synthesizing literature, case evidence, and computational strategies, Phase 1 develops a multidisciplinary framework for guiding Phase 2’s empirical inquiry into cardiovascular outcomes under real-world urban stressor exposure.

Figure 3. A visual synthesis summarizing the review’s objectives, methods, key contributions, and insights.

Figure 4. Proposed framework for mitigating urban health risks and enhancing resilience.

2.7.2. Phase 2: Empirical Data Collection and Analysis (EDCA)

Building upon the conceptual insights established in Phase 1, Phase 2 advances a rigorous empirical investigation to quantify the relationship between environmental stressors and cardiovascular health outcomes. In particular, this phase strategically prioritizes chronic urban noise exposure—identified in the preceding multi-stressor synthesis as one of the most significant environmental determinants of health in densely populated settings (Figure 2). Chronic exposure to traffic-related noise directly contributes to adverse mental health outcomes and triggers autonomic dysregulation, elevates cortisol levels, impairs endothelial function, and initiates the onset of hypertension. By isolating noise within a multi-exposure context, this phase investigates its specific mechanistic contribution to cardiovascular risk, thereby offering deeper insights into the pathophysiological pathways through which persistent urban stimuli contribute to the development of hypertension. To capture these disruptions in real time, continuous ambulatory blood pressure (BP) monitoring was employed, enabling the detection of physiological responses to prolonged environmental stressor exposure in an individual at risk for hypertension. This phase employs the following methodology:

(1): Data Collection Tools: A 24 h Ambulatory BP Monitoring (ABPM) study was conducted over a 3–9-month period (December 2023–August 2024) using an IEEE/ESH-validated ABPM50 device (Contec Medical Systems Co., Ltd., Qinhuangdao, China) [86], which recorded systolic (SBP) and diastolic (DBP) pressures at 30 min intervals. The study also included additional cardiovascular metrics—including pulse rate (PR), pulse pressure difference (PPD), mean arterial pressure (MAP), and double product (DP)—to support a more comprehensive cardiovascular assessment (see Figure 5). Simultaneously, the research team placed a Type 2250-S (Brüel & Kjær Sound & Vibration Measurement A/S, Copenhagen, Denmark) Class 1 Sound Analyzer (illustrated in Figure 2) at both the subject’s residential and occupational sites (Figure 6b) to collect environmental data. This setup allowed precise temporal alignment between physiological responses and environmental noise exposure—specifically hypertensive episodes (defined as SBP > 140 mmHg) and noise spikes (>85 dB [87]). BP variability was analyzed using linear mixed-effects models [88], adjusted for confounding variables such as circadian rhythms and physical activity levels. The standard deviation across 48 daily readings was used to measure pressure instability (Figure 5). This integrated dataset yielded robust mechanistic evidence of noise-induced vascular dysfunction (Figure 6c), reinforcing the prioritization of chronic noise exposure as a key urban health stressor, as originally identified in the MMSR (Phase 1). It also highlighted the relevance of AI-driven urban optimization strategies—emphasized in Phase 1—as promising tools for mitigating such stressors. By grounding conceptual hypotheses in high-resolution biometric and environmental data, Phase 2 established a methodological bridge between theoretical synthesis and physiological assessment. The analysis further examined the temporal concurrence of hypertensive episodes with high-intensity construction events, underscoring the rationale for implementing real-time adaptive interventions such as sound barriers and vegetative buffers.
(2): Participant Selection: The study subject—a 40-year-old male (height: 1.75 m; weight: 85 kg; BMI: 27.8; see Appendix A) without prior hypertension or stroke history—was selected due to prolonged exposure (3 ≤ t ≤ 9 months), investigating correlations with environmental stressors, to one of Shanghai’s known high-risk zones: Yangpu District. As depicted in Figure 6b, this area, where the participant resided and worked for over a year, is subject to chronic noise exposure, a well-documented environmental pollutant [61,62,63,64,65,66]. Located near key transportation corridors and railways (shown in Figure 6b and Figure 7d), noise levels in the area typically range from 60 to 90 dB. However, active road construction and heavy truck traffic frequently push these levels above 100 dB (range: 60–105 dB, from moderate to extreme noise), creating an environment with intense exposure to both vehicular and railway noise. This chronic noise exposure, compounded by additional pollutant levels, significantly exacerbates health risks, contributing to the broader environmental burden faced by residents of the area. To contextualize this selection, Phase 1’s MMSR established the synergistic impacts of multiple urban stressors—particularly air pollution and urban heat—on cardiovascular health. Phase 2, however, strategically narrows its empirical scope to isolate the mechanistic role of chronic noise exposure—a decision not only shaped by methodological and logistical constraints, but also driven by the need for a deeper, high-resolution understanding of its specific cardiovascular impacts. The MMSR thus provides a robust conceptual foundation for future investigations that aim to integrate multiple co-occurring stressors. While this cohort does not constitute a formal control group, it serves as a reference population that underscores the representativeness and ecological relevance of the selected case. The selection reflects a broader local burden, with approximately 85% of long-term residents (N = 20) presenting with hypertension and 15% with stroke history (Appendix B); comparative data from this cohort further support the ecological validity of the single-case design (Appendix C).

Figure 5. The 24 h BP monitoring and its association with hypertensive episodes and stroke.

Figure 6. (a) Proof of concept from the authors’ human case study: left image shows hypertension, middle image indicates the observed cerebrovascular accident (CVA) point, and right image presents MRI Scan Outcomes 1 and 2. (b) Study area and experimental analysis following the identification of urban traffic hotspots: conjunction of transportation corridors and railways with roads under construction. Subsections include (A) intense vehicular noise and pollutant exposure, (B) intense railway-associated noise, and (C) residential areas subjected to chronic environmental stressors, with the subject exposed to 24 h noise and air pollutant levels. (c) Impact of transportation-related noise and air pollution on cardiovascular disease, marked by exposure points.

Figure 7. (a) The progression of human development and its environmental impact, (b) major environmental stressors influencing health, (c) elevated cardiovascular risk and morbidity associated with environmental factors, (d) comprehensive analysis of noise as a critical environmental stressor, (e) the Traffic Noise-Induced Stress Concept (TNISC) and its physiological implications, and (f) temporal monitoring of BP with emphasis on hypertension trends.

The experimental location, illustrated in Figure 7d, lies adjacent to active railway lines and roadways undergoing frequent construction. The cumulative exposure to multiple environmental stressors presents an acute case of urban-induced health risk, serving as a critical testbed for the overarching framework developed in Phase 1. Together, these two phases form a robust transdisciplinary methodology that bridges urban health research, environmental monitoring, and computational design. The MMSR phase establishes a theoretical foundation by mapping the systemic complexity of urban cardiovascular health, while the EDCA phase offers real-world validation at a human scale. This two-pronged approach not only aligns with WHO recommendations for hotspot-focused investigations [55,89] but also serves as a methodological prototype for next-generation urban planning—where architectural intelligence, AI-driven tools, and environmental sensing technologies converge to proactively safeguard public health in rapidly urbanizing environments.

3. Classification, Analysis, and Outcomes

3.1. Systematic Analysis of Urbanization and Health Interactions: A Data-Driven Perspective

As shown in Table 2, scholarly engagement with the intersection of urbanization and health resilience has intensified markedly, yielding 21,266 publications between 1956 and 2025. Strikingly, 10,843 of these appeared between 2019 and 2025 alone, reflecting a +50.9% surge and underscoring a rapid acceleration in research activity. This pronounced expansion signals an urgent scholarly focus on urban health resilience, particularly in response to mounting environmental stressors. To systematically investigate the complex interrelations among urbanization, environmental variables, and public health risks, occurrence network analysis was conducted using multidimensional scaling (MDS) visual network maps across co-examined research domains. Table 3 synthesizes this analysis across nine thematic categories, revealing critical interconnections that delineate emergent research trajectories. The structured analytical framework highlights key relational patterns driving the evolving discourse on urban sustainability and health resilience.

3.1.1. Thematic Convergence and Research Density Trends

The first analytical layer examines the structural relationships among the core research themes identified, emphasizing their co-occurrence dynamics and research intensity. The following insights emerge:

Urbanization and Health: A foundational category, comprising 21,266 publications, exhibiting strong associations with environmental and physiological risk factors.
Traffic and Pollutants: With 20,907 studies, this category signifies an intensifying focus on air quality deterioration, respiratory complications, and cardiovascular diseases.
Environmental Stressors and Health Risks: The 20,895 documented studies highlight the compounding effects of multiple urban stressors—pollution, heat islands, and socio-environmental disparities—on mental and physical health.
Stressors and Hypertension: A specific pathway connecting environmental determinants to cardiovascular outcomes, evidenced by 1321 studies, reveals the physiological toll of chronic urban stressor exposure.
Traffic, Noise, and Stress: A highly interconnected domain (997 studies) identifies the psychological strain associated with urban noise pollution, a rising concern in densely populated regions.
Green Spaces and Health: Represented by 3578 studies, confirming the restorative potential of green spaces in mitigating urban stressors and enhancing well-being. Table 4 underscores the importance of optimizing urban green spaces (UGSs) to improve public health, environmental quality, and urban resilience, as strongly supported by Athokpam et al.’s study [23].
Optimization and Algorithmic Approaches: With 10,124 studies, this category explores computational techniques to enhance urban resilience via predictive modeling and decision support systems.
Architectural Intelligence: Housing 5105 studies, this domain investigates how intelligent design and urban morphology influence environmental sustainability and occupant health.
Environmental Performance and Design: The most extensive research theme (69,591 studies) reflects the growing emphasis on design-based interventions to mitigate environmental risks in urban planning.

3.1.2. Research Growth Trajectories and Emerging Convergences

An analysis of research growth rates across the domains (Figure 1) unveiled distinct and pronounced acceleration trends:

Green spaces and health research exhibited the highest growth rate (+76.9%, 2019–2025), signaling rising recognition of nature-based solutions (NBS) in urban resilience and public health.
Optimization and algorithmic approaches showed a +63.7% increase, indicating an increasing reliance on computational intelligence for urban and environmental management strategies.
Architectural intelligence and environmental performance and design both demonstrated sustained growth (+53.6% and +53.4%, respectively), highlighting the integration of AI-driven and sustainable architectural strategies in urban health research.

The trends in Figure 1 (left: research growth rates across domains, right: trends from 2019 to 2025) underscore significant acceleration in research fields such as green spaces and health, optimization and algorithmic approaches, and architectural intelligence—areas that have rapidly expanded and gained interdisciplinary momentum.

3.1.3. Multivariate Linkages and Network Dependencies

A refined analysis of keyword co-occurrence mapping and modularity clustering uncovered three dominant interaction clusters, spotlighting critical intersections between urban health research domains:

Pollution–Stress–Health Nexus: The interdependencies between traffic, pollutants, and stressors formed a distinct cluster, reinforcing the established link between urban environmental degradation and the prevalence of chronic health conditions, such as hypertension and respiratory diseases.
Green Space as a Mitigating Variable: A notably strong positive correlation was observed between urban green spaces (UGSs) and the reduction in stress-related health conditions, further validating the role of green spaces as key urban interventions for mitigating environmental stressors.
AI and Design-Driven Urban Health Solutions: The rapid convergence of optimization algorithms, architectural intelligence, and environmental performance metrics highlighted a paradigm shift toward AI-assisted health-centric urban design strategies, signaling an emerging model for future urban health interventions.

These findings underscore the urgent need for evidence-based urban health policies, focusing on key areas for future development: (1) the strategic integration of urban green spaces as proactive resilience measures, promoting both ecological sustainability and public health outcomes. (2) The implementation of regulatory measures to mitigate traffic-induced pollution and noise stressors, addressing their impact on urban health. (3) The expansion of AI-driven health analytics to predict urban health risks more accurately and optimize environmental interventions accordingly. (4) The promotion of multidisciplinary collaboration among urban planners, environmental scientists, and healthcare professionals to address urban health risks in a holistic manner.

Table 2 and Table 3 present a structured analysis of the evolving urban health landscape, offering a comprehensive narrative of its transformation. At the nexus of environmental stressors, urban policy initiatives, and algorithmic innovations was a clear call for strategic interventions that align environmental sustainability with public health objectives. Moreover, the surge in research on green infrastructure, computational modeling, and smart urban design signaled a transformative shift toward resilient ecosystems. These ecosystems were increasingly capable of addressing and mitigating health risks in the face of growing urbanization.

3.1.4. Hierarchical Interactions of Environmental Stressors

Table 5 categorizes primary urban stressors most disruptive to human physiology, with noise as the leading disruptor, activating the hypothalamic–pituitary–adrenal/HPA axis, while PM_2.5 triggers systemic inflammation [5,53]. Together, they raise hypertension risk by 1.13-fold [90]. Additionally, green space loss (<9 m²/capita) is a key biological stressor, mitigated by nature-based solutions (NBS) like urban greenery, which cuts traffic noise by 5–10 dB and reduces heat and pollution in high-risk areas [3,91].

3.2. From Comprehensive MMSR to Empirical Evidence: Establishing Noise as a Critical Environmental Stressor

Growing evidence linking environmental stressors to human health highlighted the urgent need to examine noise as a critical environmental determinant. However, despite some focus, noise exposure remains insufficiently emphasized compared to other stressors, leaving a substantial gap in understanding its profound impact on cardiovascular and metabolic disorders, as shown in Figure 1. This gap was further reinforced by the comprehensive review presented in this study (MMSR), which identified noise (Figure 2) as one of the most prominent environmental stressors contributing to a range of cardiovascular and metabolic disorders. The review underscored the growing recognition of chronic noise exposure, not only for its detrimental effects on sleep disturbances and vascular dysfunction but also for its potential to amplify traditional cardiovascular risk factors, such as hypertension and diabetes. These effects are further visualized in Figure 6c, highlighting the physiological impacts of noise exposure.

These findings demand immediate attention, emphasizing the urgent need for empirical studies to examine the physiological consequences of noise in greater depth. To address this, a proof-of-concept experimental case study was conducted (Figure 6) to validate correlations observed in the review and assess the physiological impact of chronic noise exposure with real-world data. The subject, a 40-year-old male (175 cm, 85 kg, BMI: 27.8, Appendix A), was a newcomer to a local community building where chronic noise constituted a significant and sustained environmental stressor. This location was not randomly chosen: approximately 85% of long-term residents (N = 20) in the area were affected by hypertension, as confirmed by both survey results and medical records (Appendix B, Table A2), suggesting a potent link between environmental conditions and cardiovascular health. The subject’s profile closely mirrored that of long-term residents exposed to chronic noise (see Figure 6b), as detailed in Appendix C, Table A3, making him a prime candidate to investigate the early physiological shifts triggered by prolonged environmental stressors, particularly their direct effects on cardiovascular health. The residential zone was subject to persistent 24 h environmental stressors, including vehicular and railway noise combined with ambient air pollution. These conditions formed a potent mix of physical and chemical stressors known to exacerbate cardiovascular risks (Table 5).

To enhance analytical precision, this study sought to determine whether 3–9 months of chronic noise exposure could measurably contribute to the development of hypertension—mirroring the health status of a comparative group (N = 20; aged 40–60), which revealed alarming rates of hypertension (≈85%) and stroke incidence (15%) (Appendix B, Table A2). The results demonstrated sustained elevations in the subject’s blood pressure/BP (Figure 6a), validating previous findings by Jacob et al. [10]. The data further revealed significant impairments in vascular reactivity and endothelium-dependent relaxation, providing robust empirical evidence that noise exposure activates stress responses capable of disrupting critical physiological processes. These disruptions initiate a cascade of biological stress responses, corroborating extensive evidence that noise impairs sleep, disrupts redox homeostasis, compromises vascular integrity, and dysregulates autonomic and metabolic systems (see Table 6). If sustained over time, these mechanisms may precipitate severe conditions such as hypertension and stroke, as demonstrated by the subject’s MRI and cerebrovascular findings (Figure 6).

To further substantiate these effects, 24 h dynamic BP monitoring over the observation period identified circadian disruptions associated with chronic noise exposure (Figure 5), supporting its contribution to cardiovascular and systemic decline (Table 6). The results indicated an average BP of 132/76 mmHg, which slightly exceeded the reference value of 130/80 mmHg. Notably, the subject experienced hypertensive spikes, with a maximum systolic BP reaching 167 mmHg and exceeding 172 mmHg at times (Figure 6a), while diastolic pressure reached 101 mmHg, significantly surpassing clinical thresholds. These hypertensive episodes occurred during the same period as an MRI-confirmed stroke, suggesting a potential association between elevated BP and cerebrovascular events. During the monitoring period, the subject’s BP was notably higher during the daytime, with systolic pressure exceeding 135 mmHg for 49.02% of the day and diastolic pressure surpassing 85 mmHg for 29.41% of the time. Though the subject’s night-time BP was closer to normal levels, reductions of 10.90% in both systolic and diastolic pressures were consistent with the expected circadian rhythm. These findings, highlighted in Figure 5, provided compelling evidence of significant BP instability, particularly during the daytime, which may have elevated the risk of cardiovascular damage. A systolic variation coefficient of 16.09% over 24 h—rising to 18.24% at night—indicated substantial BP fluctuations, which were thought to contribute to overall cardiovascular risk. Given the strong temporal association between hypertensive spikes and the stroke event, this case underscores the urgent need for clinical intervention to address such fluctuations and mitigate the risk of recurrent strokes.

The Cardiovascular Toll of Chronic Noise: Mechanisms and Urban Solutions

Empirical findings from the case study data (Figure 5 and Figure 6), and a comparative cohort (N = 20; Appendix B and Appendix C), confirmed that chronic noise exposure significantly impaired cardiovascular health. Prolonged exposure to noise, particularly from traffic sources, resulted in sustained elevations in blood pressure (BP) and compromised vascular function, thereby exacerbating cardiovascular risks—most notably hypertension. Figure 6c illustrates the pathological trajectory and underlying mechanisms by which noise and air pollutants contribute to cardiovascular disease. The schematic clearly delineated how exposure to defined pollutant sources (A and B) initiates a cascade of adverse health effects, including sleep disruption, cognitive dysfunction, auditory system damage, and emotional stress. These physiological and psychological disturbances activate multiple pathogenic pathways, including autonomic dysfunction, hypothalamic–pituitary–adrenal (HPA) axis activation, systemic inflammation, and thrombosis. Synthesizing these findings, the cascade depicted in Figure 6c highlighted the biological disruptions triggered by chronic stress, which led to heightened circulating levels of stress hormones such as epinephrine, dopamine, norepinephrine, angiotensin II, and cortisol. These hormonal alterations further exacerbated cardiovascular and cardiometabolic risks, with hypertension emerging as a central clinical concern in environments dominated by chronic noise and air pollution.

In turn, these environmental stressors catalyzed hormonal dysregulation, amplified vascular resistance, disrupted metabolic function, and accelerated the onset of hypertension and related disturbances, including hyperglycemia and obesity, as supported by previous studies [95,96]. Figure 7 provides a comprehensive synthesis of the outcomes, offering an integrated perspective on how rapid urbanization and intensified human-driven development shaped health outcomes across the lifespan. Figure 7a,b emphasized the critical need to assess the cumulative and interactive effects of multiple environmental stressors on biological responses, particularly in the context of rapidly urbanizing regions. Building upon the initial categorization of stressors (Table 5), we identified several dominant contributors: traffic-related noise, air pollution, climate change (including thermal extremes and green space loss), light pollution, and poor urban planning (Figure 7b). These stressors, acting synergistically, disrupted physiological homeostasis and intensified chronic health burdens. The cardiovascular implications of these stressors (Figure 7c) were classified into four primary categories: (1) cerebrovascular events, such as ischemic strokes and vascular dementia; (2) vascular disorders, including hypertension, carotid atherosclerosis, and microvascular dysfunction; (3) cardiac disorders, such as coronary artery disease, myocardial infarction, arrhythmias, and heart failure; and (4) metabolic disorders, encompassing hypercholesterolemia, hyperglycemia, and obesity. Notably, among the identified stressors, noise exposure emerged as a particularly potent environmental health risk, with extensive research [61,62,63,64,65,66] corroborating its significant cardiovascular impact.

This study provided a comprehensive examination of various sources of chronic noise exposure, emphasizing the noise levels generated by small vehicles (60–75 dB), trucks (70–90 dB), and trains (70–100 dB). In areas with active road construction, noise levels frequently exceeded typical ranges, particularly due to heavy truck traffic, with measurements surpassing 100 dB and peaking at 105 dB in our study. Remarkably, the average chronic noise exposure level in the study area was 79.84 dB (Figure 7d), a level that correlated with a 1.8-fold increased risk of hypertension. This finding is especially notable when compared to previous studies, which reported a 1.7-fold increase in hypertension risk due to the combined exposure to noise and air pollution [12], yet did not explicitly account for the effects of prolonged or chronic noise exposure. The near-identical magnitude of risk in our study underscored that chronic noise exposure alone could independently rival the cardiovascular burden associated with multiple environmental stressors, reinforcing its critical impact as a standalone health risk. Residents exposed to persistent traffic noise, railway noise, and elevated pollutant levels faced compounded environmental stressors that significantly increased cardiovascular health risks in urban settings. In response to this, we proposed the Traffic Noise-Induced Stress Concept (TNISC), a conceptual framework that examined the physiological and psychological responses triggered by prolonged exposure to urban noise environments. Figure 7d–f illustrate the gradient of noise exposure levels—from roadway (60–90 dB) to railway noise (70–100 dB)—and emphasize both direct effects (e.g., hearing loss, sleep disturbances) and indirect effects (e.g., annoyance and emotional stress such as depression). This model also captured how sustained stress exposure activated the autonomic nervous system and endocrine responses, particularly the sympathetic nervous system and pituitary–adrenal glands. The introduction of TNISC provided a conceptual framework for understanding the physiological and psychological mechanisms elicited by chronic noise exposure.

Figure 7e underscores that noise-induced chronic stress was associated with key cardiovascular risk factors, particularly elevated BP, which significantly contributed to cardiovascular disorders, particularly hypertension. This schematic depiction of noise perception and stress response mechanisms offered a comprehensive understanding of the intricate relationship between environmental noise exposure, stress mechanisms, and cardiovascular health outcomes. By mapping these stress-induced pathways, we emphasized the urgent need for interventions to mitigate the long-term cardiovascular risks associated with chronic environmental noise exposure. This calls for immediate action and a holistic approach to urban health management. One such promising intervention, as highlighted by the findings of an MMSR, is the integration of urban green spaces (UGSs) as a nature-based solution. UGSs have consistently been shown to reduce noise pollution by 5–10 dB [91] while also enhancing cognitive function, reducing emotional stress, and contributing to improved cardiovascular health. By providing a natural buffer against environmental pollutants, UGSs not only mitigate the harmful effects of noise but also foster better physiological and psychological well-being, offering a holistic strategy for cardiovascular disease prevention in urban settings. Furthermore, to optimize the effectiveness of UGSs, it is essential to apply AI-driven urban design strategies, such as evolutionary algorithms (EA) [7], which could optimize the placement and design of green spaces to maximize their environmental performance. These strategies could help tailor green spaces to specific urban contexts, enhancing their capacity to mitigate pollution and maximize health benefits. Through the integration of AI, cities could create more sustainable and health-oriented urban environments that effectively address the environmental health challenges posed by rapid urbanization.

3.3. Optimizing Urban Green Spaces for Health and Sustainability: The Role of AI and Nature-Based Solutions (NBS) in Mitigating Environmental Stress

A growing body of evidence confirms the adverse effects of prolonged exposure to environmental stressors on cardiovascular function and overall public health [10,50,53,54,55,56,57]. In response, nature-based solutions (NBS), especially urban green spaces (UGSs), have emerged as effective and evidence-backed interventions. Their multi-dimensional benefits were well documented across disciplines [20,21,22,23,24,25,28,29], as illustrated in Figure 1. Table 4 classifies the solution-driven benefits of UGSs, underscoring their strategic role in mitigating urban stress. From 2019 to 2025, the number of studies addressing the health benefits of green spaces increased by 76.9%, paralleled by a 63.7% rise in research on optimization strategies. This trend reflected a clear shift toward recognizing the dual potential of UGSs in enhancing urban health and advancing environmental sustainability. As illustrated in Figure 7a, the intensification of urbanization, particularly in high-risk areas, amplified the need to optimize UGSs as protective infrastructure against environmental stressors. While UGSs’ health benefits were well established (Table 1 and Table 4), their environmental potential can be maximized through the integration of artificial intelligence (AI), which is key to optimizing their performance and scalability. AI offers a scientifically rigorous, data-driven, and efficient approach to refining UGSs, addressing urban health and environmental challenges. In this context, the application of AI relied on advanced computational optimization algorithms, most notably evolutionary algorithms (EAs) and Artificial Neural Networks (ANNs), to model complex, non-linear relationships within urban systems. This approach is further strengthened by ArcAI (architectural intelligence), which enhances and enables the efficacy of design and environmental planning processes through AI-driven insights. As detailed in Table 7 and Table 8, these approaches enable refined and more precise urban design strategies that reduce environmental stressors and boost system performance. The synergy of AI and architectural intelligence enhances green space design, making it more functional, accessible, and aesthetically pleasing, thus promoting the well-being of urban populations.

These technologies synergistically optimize the spatial configuration, design quality, functional performance, and strategic placement of urban green spaces, reinforcing their role as resilient and health-promoting green infrastructure. Building on this, recent research [7], illustrated in Figure 8, demonstrates this optimization through the application of evolutionary principles and heuristic search algorithms (as detailed in Table 7). These algorithms analyze spatial efficiency, vegetation selection, accessibility, and pollution exposure, enabling cities to design green spaces that maximize health benefits and serve as strategic buffers against urban stressors in vulnerable areas.

Figure 8. Synergistic integration of technologies for optimizing the design, functionality, and placement of green spaces, utilizing evolutionary principles and heuristic search algorithms, as demonstrated in recent research [7].

To further advance this optimization, architectural intelligence can operationalize these AI-driven insights by integrating them into the morphological and contextual aspects of UGS design (see Table 8 for detailed examples of these applications). This ensured that UGSs were not only functionally effective but also aesthetically integrated, contextually adaptive, and resilient within the broader urban system. Green spaces thus evolved from isolated interventions into core components of holistic urban resilience frameworks. The convergence of AI, optimization algorithms, and architectural intelligence marked a significant advancement in urban planning methodologies. By incorporating AI throughout the lifecycle of UGS development—from spatial analysis to dynamic management—cities were equipped to tackle sustainability and public health imperatives simultaneously. AI’s predictive capabilities also supported biodiversity enhancement, carbon sequestration, and energy efficiency, aligning UGS strategies with broader climate and urban development objectives.

As AI-driven urban design research grows, particularly at the intersection of urbanization, pollution, and green infrastructure, a clear shift is occurring in how cities address public health. The increasing focus on optimization algorithms, architectural intelligence, and environmental performance highlights AI as a central force in urban health and sustainability. This technological convergence enables cities to adopt data-driven, adaptive strategies, paving the way for more integrated approaches to green space management that optimize health outcomes. Integrating AI in the design and management of UGSs offers a transformative path to healthier, more resilient cities. These spaces are better equipped to tackle the challenges of rapid urban growth and environmental stress. The synergy between AI and nature-based solutions (NBSs) forms a scalable, sustainable framework for urban health, ensuring long-term benefits for both populations and ecosystems. Overall, embedding AI in UGS planning presents a powerful, future-proof model for enhancing urban resilience and heal.

3.4. Proposed Framework for Mitigating Urban Health Risks and Enhancing Resilience

The escalating public health challenges driven by rapid urbanization necessitate innovative, multi-faceted approaches to enhance urban health resilience. Addressing these complex challenges requires an integrated, evidence-based framework that combines technological advances with ecologically grounded strategies. To this end, this study proposes a multi-stage, evidence-driven framework integrating AI-driven optimization, nature-based solutions (NBSs), and health-centered architectural intelligence.

This framework is rigorously grounded in a two-phase investigative process: (i) a Mixed Methods Systematic Review (MMSR) to identify critical gaps and technological opportunities (Phase 1), and (ii) Empirical Data Collection and Analysis (EDCA) to validate physiological impacts of environmental stressors (Phase 2). Insights from Phases 1 and 2 collectively underpin the framework’s design and structure, forming the basis for the final integrative phase that synthesizes evidence to inform actionable, AI-driven urban design interventions (Phase 3; Figure 4). Thus, the MMSR (Phase 1) established the foundational evidence layer through a comprehensive thematic synthesis (Table 1), identifying noise exposure as the most prominent yet insufficiently addressed environmental stressor contributing to cardiovascular morbidity. It further highlighted the growing relevance of technological innovations such as AI and algorithmic design in urban health research, with notable growth in key domains: green spaces and health (+76.9%), optimization and algorithmic approaches (+63.7%), and architectural intelligence (+53.6%). These trends highlight the growing imperative to integrate technological innovations with ecological strategies in advancing urban resilience frameworks. However, despite these advances, the MMSR revealed a critical gap: AI-based models remain underutilized in systematically optimizing urban environments to enhance health outcomes, particularly regarding the integration of computational strategies with nature-based interventions. Complementing these theoretical insights, the EDCA (Phase 2) provided empirical validation through high-resolution environmental and biometric monitoring, including continuous blood pressure (BP) tracking. Key findings highlighted the severity of chronic noise exposure: an average ambient noise level of 79.84 dB was associated with a 1.8-fold increase in hypertension risk, which is comparable to the synergistic effects of noise and PM_2.5 (1.7-fold [12]). Acute hypertensive events (systolic spikes >172 mmHg) temporally aligned with peak noise incidents reaching 105 dB, revealing the immediate physiological impact of unmitigated environmental stressors. This robust empirical evidence both substantiated and extended Phase 1 findings by elucidating the physiological mechanisms linking chronic noise exposure to cardiovascular risk.

Collectively, evidence from the MMSR and EDCA unequivocally establishes chronic noise as a pivotal environmental stressor and cardiovascular risk factor, highlighting a pressing need for advanced, data-driven solutions. To address this imperative, the framework is structured around three core pillars delineated in Phase 3 (Figure 4)—AI-driven urban design optimization, the strategic deployment of nature-based solutions (NBSs), and health-centered architectural intelligence. These pillars are integrated within a cross-cutting foundation of interdisciplinary collaboration to ensure systemic resilience, thereby translating theoretical and empirical insights into practical, data-driven urban health interventions.

The framework’s first pillar, AI-driven urban design optimization, leverages advanced computational tools to enable dynamic adjustments to evolving environmental and health stressors. These include evolutionary algorithms (EAs), such as Genetic Algorithms (GAs) [7] for spatial optimization, Artificial Neural Networks (ANNs) for modeling stressor–health dynamics, and decision support systems (DSS) for delivering real-time, actionable urban interventions. Table 7 presents the models supporting the AI-driven optimization. For instance, based on empirical findings of average chronic noise exposure of 79.84 dB—linked to a 1.8-fold increased hypertension risk—Genetic Algorithms (GAs) [7] can optimize the spatial distribution and design of urban green spaces (UGSs) to mitigate noise exposure. These algorithms aim to maximize noise attenuation, targeting 5–10 dB reductions, as documented empirically [91], by optimally positioning UGSs within high-exposure areas identified through continuous noise monitoring. Similarly, ANNs can predict synergistic health risks by training on EDCA-derived datasets, such as the observed 16.09% 24 h BP variability, which rose to 18.24% at night, enabling non-linear modeling of environmental-health interactions.

A second crucial pillar involves the strategic deployment of nature-based solutions (NBSs). Grounded in MMSR-validated benefits, NBS are deployed using spatial analytics to buffer stressors and deliver therapeutic effects, such as cardiovascular risk reduction and air quality improvement. The MMSR study, aligned with EDCA, indicates that green spaces can function not only as buffers for environmental stressors but also as therapeutic urban elements with cascading benefits, including mental health support. This is particularly critical in rapidly urbanizing regions like the Yangpu District, where long-term exposure to noise and infrastructural disruptions correlated with hypertension rates above 85% and stroke histories in 15% of residents (Appendix B and Appendix C). In such high-risk areas, targeted green infrastructure can mitigate exposure while enhancing ecological connectivity.

The third core pillar is health-centered architectural intelligence (ArcAI; Table 1 and Table 8). ArcAI introduces a layer of smart design into the built environment, informed by AI and focused on mitigating micro-scale environmental threats such as poor ventilation, acoustic overload, and inadequate daylight. It supports the integration of responsive design elements, like noise-dampening façades, passive cooling mechanisms, and intelligent materials, that dynamically regulate internal conditions to reduce chronic exposure to health-deteriorating stimuli. Furthermore, ArcAI bridges built and ecological systems, facilitating the spatial merging of architectural forms with surrounding NBSs, thereby ensuring continuity between buildings and ecological infrastructures. Lastly, systemic implementation of this framework necessitates a transdisciplinary approach underpinned by a cross-cutting foundation of interdisciplinary integration for systemic resilience. The success of AI models, green infrastructure, and ArcAI systems can be predicated on cohesive collaboration among urban planners, public health specialists, environmental scientists, data analysts, and policymakers. Without such integrative governance structures, the siloed deployment of tools and strategies risks inefficiency, poor scalability, and diminished impact on urban health outcomes.

Overall, to facilitate the transition from theoretical constructs to practical application, the framework follows a tripartite implementation pathway (Figure 4). Stage 1, Data-Driven Diagnosis, initiates the process through high-resolution environmental surveillance and biometric health monitoring, akin to the methods employed in the EDCA. This includes dynamic noise mapping, BP monitoring, and spatial pollutant profiling. Stage 2, AI-Enhanced Planning, mobilizes algorithmic modeling—using GA for spatial optimization of NBS deployment, Neural Networks for predicting risk intensification, and DSS for prioritizing high-risk intervention zones. Stage 3, Context-Aware Intervention, finalizes the transition to implementation by tailoring urban form modifications and green infrastructure deployments to socio-environmental realities, ensuring interventions are locally optimized and health-oriented. By synthesizing insights from the MMSR and empirical evidence from the EDCA, the proposed framework offers a potential pathway for advancing urban health planning through evidence-based, technologically driven interventions. This multi-layered approach addresses persistent gaps in current urban health planning by leveraging compounded and synergistic insights, thereby laying a foundation for future development and context-responsive implementation in rapidly urbanizing environments.

4. Conclusions

In response to the escalating public health challenges posed by urbanization, this study highlights the compounded effects of environmental stressors—such as air pollution, noise, heat, and the depletion of green spaces—on urban populations, particularly concerning cardiovascular health. The pervasive nature of these stressors significantly contributes to the rising prevalence of hypertension and cardiovascular diseases, emphasizing the urgent need for innovative, multifaceted approaches to urban health resilience. This research underscores the critical role of integrating advanced artificial intelligence (AI) algorithms with nature-based solutions (NBSs) to mitigate the adverse impacts of urban environmental stressors. Specifically, AI-driven optimization of urban green spaces (UGSs) provides a powerful tool for enhancing their environmental functionality while improving health outcomes. The fusion of AI with NBSs enables the design of adaptive, context-sensitive interventions that transform urban green spaces from passive aesthetic features to active components of urban health resilience. These green spaces become dynamic buffers, counteracting urban heat islands, improving air quality, and providing essential mental and physical health benefits to city dwellers.

By leveraging real-time data, predictive analytics, and optimization algorithms, this study underscores the potential of AI to optimize urban design with a focus on human health. Through continuous monitoring and data-driven decision making, AI offers the capacity to tailor interventions that directly address the cardiovascular risks exacerbated by urbanization. These predictive capabilities allow for more targeted and efficient allocation of resources, ensuring that interventions are both timely and effective.

Moreover, the integration of AI-powered architectural intelligence and NBSs marks a paradigm shift in urban planning. This synergy facilitates the creation of resilient, scalable, and adaptive urban environments that prioritize the health and well-being of residents while advancing environmental sustainability. The dynamic and responsive nature of AI-driven optimization ensures that urban spaces are not only optimized for environmental performance but are also designed with human health at the forefront.

Ultimately, this study presents a robust, scientifically grounded, evidence-based framework for mitigating the health risks posed by urbanization through the strategic integration of AI, NBSs, and architectural intelligence. It affirms the transformative potential of AI-enhanced urban design, offering a comprehensive approach that enables cities to proactively address cardiovascular health risks, foster environmental sustainability, and build urban spaces that are more resilient to the challenges of rapid urban growth and climate change.

Limitations and Future Work

This study acknowledges two limitations, neither of which compromises the primary conclusions. (1) Building upon Phase 1’s identification of chronic noise as a key environmental stressor, Phase 2 deliberately focused on elucidating its mechanistic impact on cardiovascular outcomes. This targeted scope allowed for detailed empirical validation, while the investigation of additional co-stressors will be pursued in future studies guided by the comprehensive MMSR framework. (2) Although the single-case design did not include a formal control group, cohort data from long-term residents provided a scientifically robust reference population, thereby enhancing ecological validity in accordance with established environmental health research practices. To improve generalizability and further characterize synergistic effects, future research should incorporate multi-site comparisons and expand environmental metrics. Beyond these limitations, the conceptual AI-based urban optimization framework lays a strategic foundation for future research. While this study does not develop or validate AI models—or provide detailed parameters, training protocols, or implementation code—it outlines a direction for integrating AI into health-responsive urban planning. Continued advancement in AI-driven models and robust data integration is essential to enable scalable multi-stressor analyses and to design interventions that mitigate environmental risks, enhance resilience, and promote sustainability. As such, AI offers a transformative pathway toward these objectives. Future studies should rigorously assess its practical effectiveness, scalability, and adaptability across diverse urban contexts.

Author Contributions

Conceptualization, M.M. and Z.K.; methodology, M.M.; software, M.M.; validation, M.M., Z.K. and Y.L.; formal analysis, M.M.; investigation, W.L.; resources, P.F.Y., M.M. and W.L.; data curation, M.M.; writing—original draft preparation, M.M.; writing—review and editing, M.M.; visualization, M.M.; supervision, P.F.Y. and M.M.; project administration, P.F.Y. and M.M.; funding acquisition, P.F.Y., M.M. and W.L. All authors have read and agreed to the published version of the manuscript.

Funding

This article is supported by the National Key R&D Program of China (2023YFC3806900), the National Key R&D Program of China (2022YFE0141400), the National Natural Science Foundation of China (grant No. U1913603), and the Fundamental Research Funds for the Central Universities. Additionally, this work was supported by the Distinguished Funding Project of the China Postdoctoral Science Foundation (2024T170669), the Ministry of Human Resources and Social Security, National Foreign Expert Individual Project (grant No. Y20240087), and the Shanghai Municipal Science and Technology Major Project.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

The data supporting the findings of this study are available upon reasonable request.

Acknowledgments

The authors are grateful for the support from the DigitalFUTURE Lab at Tongji University.

Conflicts of Interest

The authors declare no conflicts of interest.

Abbreviations

The following abbreviations are used in this manuscript:

MMSR	Mixed methods systematic review.
EDCA	Empirical data collection and analysis.
NBSs	Nature-based solutions.
BMI	Body mass index.
TNISC	Traffic noise-induced stress concept.
UGSs	Urban green spaces.
BP	Blood pressure.
AI	Artificial intelligence.
EA	Evolutionary algorithms.
ML	Machine learning
PM	Predictive modeling
UHIs	Urban heat islands
CVD	Cardiovascular disease
DBP	Diastolic blood pressure
MAP	Mean arterial pressure
DP	Double product
PR	Pulse rate
PPD	Pulse pressure difference
CAD	Coronary artery disease
SBP	Systolic blood pressure
GA	Genetic algorithm
PSO	Particle swarm optimization
HA	Heuristic algorithm
OAs	Optimization algorithms
RF	Random forest
PM	Particulate matter
PM_2.5	Fine particulate matter, <2.5 µm
OS	Oxidative stress
CO₂	Carbon dioxide
USR	Urban soundscape recorder
ABPM	Ambulatory blood pressure monitoring
dB	Decibels
MDS	Multidimensional scaling
HPA	Hypothalamic-pituitary-adrenal
AIS	Artificial immune systems
AAs	Annealing algorithms
NDS	Non-dominated sorting
PLM	Piecewise linear model
ANN	Artificial neural network
LR	Linear regression
SVM	Support vector machine

Appendix A

Standard Body Mass Index (BMI) Classification

The Body Mass Index (BMI) is a standardized anthropometric indicator calculated as weight (kg) divided by height squared (m²). It classifies individuals into underweight, normal weight, overweight, or obese categories. In this study, the participant’s BMI was 27.8, placing them in the ‘overweight’ category based on standard criteria.

Table A1. BMI classification and study participant categorization.

BMI Range	Category	BMI: 27.8
<18.5	Underweight	-
18.5–24.9	Normal weight	-
25.0–29.9	Overweight	✓
≥30.0	Obese	-

✓ Indicates the BMI category corresponding to the subject’s BMI (27.8).

Appendix B

Community Health Data from the Study Area

To calculate the total hypertension prevalence across different groups (in this case, men and women), the weighted average method is employed. This method accounts for the varying sample sizes of the groups, which can influence the overall prevalence rate. Rather than simply averaging the percentages, the formula incorporates the number of individuals in each group to provide a more accurate representation of the overall prevalence.

T o t a l P r e v a l e n c e = \frac{(P_{m e n} \times N_{m e n}) + (P_{w o m e n} \times N_{w o m e n})}{N_{m e n} + N_{w o m e n}}

where P_men is the hypertension prevalence in men, P_women refers to the hypertension prevalence in women, N_men is the sample size of men, and N_women is the sample size of women.

Table A2. Hypertension and stroke prevalence among long-term residents (≥5 years) exposed to chronic environmental stressors in Yangpu district, Shanghai.

Study Group	Sample Size	Hypertension Prevalence (%)	Stroke History (%)	Avg. Noise Exposure (dB)	Data Source
Men (40–60 years)	12	87.5	16.7	± 79.8	Local clinic medical records
Women (40–60 years)	8	83.3	12.5	± 79.8	Local clinic medical records
Total	20	≈85	15.0	± 79.8

Note: Data collected from long-term residents (≥5 years) in the same building/complex as the case study subject. Hypertension defined as systolic BP ≥140 mmHg or diastolic BP ≥90 mmHg (per WHO guidelines). Stroke history confirmed via medical imaging/records.
Metric	Study Community/ N = 20	National Avg.	Absolute Difference	Relative Difference	Interpretation
Hypertension (40–60 years)	≈85% (17/20)	32%	+53.8%	+168.1%	Substantially Higher
Stroke Incidence	15% (2/13)	5.2%	+9.8%	+188.4%	Higher

Appendix C

Comparative Health and Exposure Metrics: Case Subject vs. Long-Term Urban Residents

To enhance the transparency and ecological validity of the study, Table A3 presents a comparative health profile between the case subject and a representative sample of long-term residents in the Yangpu cohort (Table A2). The case subject’s lifestyle (non-smoker, sedentary) and socioeconomic status (SES; middle-income) were broadly representative of the cohort. The calculation of the subject’s BMI resulted in a value of 27.8, classified as overweight in the study. For details on BMI classification, see Appendix A. The subject’s absence of stroke history was contextualized against local community health indicators, where approximately 85% of residents have diagnosed hypertension, and 15% have a history of stroke. Noise exposure levels were also comparable, with the subject experiencing sustained environmental noise ranging from 60 to 105 dB (mean: 79.84 dB), consistent with the broader urban hotspot population. This comparative analysis supports the representativeness of the single-case study design and strengthens the generalizability of the findings.

Table A3. Comparative health metrics between case subjects and long-term residents.

Parameter	Case Subject (During Study)		Long-Term Residents (N = 20)
	Before Exposure	After Exposure
Age (years)	40	40	40–60
Hypertension (%)	0 (no prior history)	100 (diagnosed)	≈85
Stroke History (%)	0 (no prior history)	100 (diagnosed)	15
Noise Exposure (dB)	60–105 (mean: 79.84)	60–105 (mean: 79.84)	Similar

References

Münzel, T.; Steven, S.; Frenis, K.; Lelieveld, J.; Hahad, O.; Daiber, A. Environmental Factors Such as Noise and Air Pollution and Vascular Disease. Antioxid. Redox Signal. 2020, 33, 581–601. [Google Scholar] [CrossRef] [PubMed]
Henning, R.J. Particulate Matter Air Pollution is a Significant Risk Factor for Cardiovascular Disease. Curr. Probl. Cardiol. 2023, 49, 102094. [Google Scholar] [CrossRef] [PubMed]
Russo, A.; Cirella, G.T. Modern Compact Cities: How Much Greenery Do We Need? Int. J. Environ. Res. Public Health 2018, 15, 2180. [Google Scholar] [CrossRef] [PubMed]
Kumar, R.; Varma, B. Mushrooming traffic congestion and its psychological implications among drivers. Int. J. Creat. Res. Thoughts 2020, 8, 295–301. [Google Scholar]
Roche, I.V.; Ubalde-López, M.; Daher, C.; Nieuwenhuijsen, M.; Gascón, M. The Health-Related and Learning Performance Effects of Air Pollution and Other Urban-Related Environmental Factors on School-Age Children and Adolescents—A Scoping Review of Systematic Reviews. Curr. Environ. Health Rep. 2024, 11, 300–316. [Google Scholar] [CrossRef]
Makvandi, M.; Yuan, P.F.; Ji, Q.; Li, C.; Elsadek, M.; Li, W.; Hassan, A.; Li, Y. Resilience to Climate Change by Improving Air Circulation Efficiency and Pollutant Dispersion in Cities: A 3D-UFO Approach to Urban Block Design. Heliyon 2024, 10, e36904. [Google Scholar] [CrossRef]
Makvandi, M.; Li, W.; Li, Y.; Wu, H.; Khodabakhshi, Z.; Xu, X.; Yuan, P.F. Advancing Urban Resilience Amid Rapid Urbanization: An Integrated Interdisciplinary Approach for Tomorrow’s Climate-Adaptive Smart Cities—A Case Study of Wuhan, China. Smart Cities 2024, 7, 2110–2130. [Google Scholar] [CrossRef]
Makvandi, M.; Li, W.; Ou, X.; Chai, H.; Khodabakhshi, Z.; Fu, J.; Yuan, P.F.; Horimbere, E.D. Urban Heat Mitigation towards Climate Change Adaptation: An Eco-Sustainable Design Strategy to Improve Environmental Performance under Rapid Urbanization. Atmosphere 2023, 14, 638. [Google Scholar] [CrossRef]
Hahad, O.; Rajagopalan, S.; Lelieveld, J.; Sørensen, M.; Kuntić, M.; Daiber, A.; Basner, M.; Nieuwenhuijsen, M.; Brook, R.D.; Münzel, T. Noise and Air Pollution as Risk Factors for Hypertension: Part II-Pathophysiologic Insight. Hypertension 2023, 80, 1384–1392. [Google Scholar] [CrossRef]
Blaustein, J.R.; Quisel, M.J.; Hamburg, N.M.; Wittkopp, S. Environmental Impacts on Cardiovascular Health and Biology: An Overview. Circ. Res. 2024, 134, 1048–1060. [Google Scholar] [CrossRef]
Cuijpers, P.; Miguel, C.; Ciharova, M.; Kumar, M.; Brander, L.; Kumar, P.; Karyotaki, E. Impact of climate events, pollution, and green spaces on mental health: An umbrella review of meta-analyses. Psychol. Med. 2023, 53, 638–653. [Google Scholar] [CrossRef] [PubMed]
Hahad, O.; Rajagopalan, S.; Lelieveld, J.; Sørensen, M.; Frenis, K.; Daiber, A.; Basner, M.; Nieuwenhuijsen, M.; Brook, R.D.; Münzel, T. Noise and Air Pollution as Risk Factors for Hypertension: Part I-Epidemiology. Hypertension 2023, 80, 1375–1383. [Google Scholar] [CrossRef] [PubMed]
Badaloni, C.; De Sario, M.; Caranci, N.; de’ Donato, F.K.; Bolignano, A.; Davoli, M.; Leccese, L.; Michelozzi, P.; Leone, M. A spatial indicator of environmental and climatic vulnerability in Rome. Environ. Int. 2023, 176, 107970. [Google Scholar] [CrossRef] [PubMed]
Saraswati, C.M.; Judge, M.A.; Weeda, L.J.Z.; Bassat, Q.; Prata, N.; Le Souëf, P.N.; Bradshaw, C.J.A. Net benefit of smaller human populations to environmental integrity and individual health and wellbeing. Front. Public Health 2024, 12, 1339933. [Google Scholar] [CrossRef]
Rajagopalan, S.; Vergara-Martel, A.; Zhong, J.; Khraishah, H.; Kosiborod, M.N.; Neeland, I.J.; Dazard, J.-E.J.; Chen, Z.; Munzel, T.; Brook, R.D.; et al. The Urban Environment and Cardiometabolic Health. Circulation 2024, 149, 1298–1314. [Google Scholar] [CrossRef]
Zhang, K.; Brook, R.D.; Li, Y.; Rajagopalan, S.; Kim, J.B. Air Pollution, Built Environment, and Early Cardiovascular Disease. Circ. Res. 2023, 132, 1707–1724. [Google Scholar] [CrossRef]
Kaczyńska, M. Urban Green Spaces’ Influence on Civilization Diseases—Meta-Analysis and Critical Review. Sustainability 2024, 16, 3925. [Google Scholar] [CrossRef]
Kuntić, M.; Hahad, O.; Al-Kindi, S.; Oelze, M.; Lelieveld, J.; Daiber, A.; Münzel, T. Pathomechanistic synergy between particulate matter and traffic noise induced cardiovascular damage and the classical risk factor hypertension. Antioxid. Redox Signal. 2024, 42, 827–847. [Google Scholar] [CrossRef]
Li, W.; Hong, W.; Xu, X.; Makvandi, M.; Zhang, B.; Chen, Q.; Yuan, P.F. A radical shift to probabilistic thinking: Integrating energy analysis in performance-driven building morphology generation. Build. Environ. 2025, 269, 112443. [Google Scholar] [CrossRef]
Zheng, Y.; Cheng, B.; Dong, L.; Zheng, T.; Wu, R. The Moderating Effect of Social Participation on the Relationship between Urban Green Space and the Mental Health of Older Adults: A Case Study in China. Land 2024, 13, 317. [Google Scholar] [CrossRef]
Fu, J.; Fu, H.; Zhu, C.; Sun, Y.; Cao, H. Assessing the health risk impacts of urban green spaces on air pollution—Evidence from 31 China’s provinces. Ecol. Indic. 2024, 159, 111725. [Google Scholar] [CrossRef]
Zhang, F.; Qian, H. A comprehensive review of the environmental benefits of urban green spaces. Environ. Res. 2024, 252, 118837. [Google Scholar] [CrossRef] [PubMed]
Athokpam, V.; Chamroy, T.; Ngairangbam, H. The Role of Urban Green Spaces in Mitigating Climate Change: An Integrative Review of Ecological, Social, and Health Benefits. Environ. Rep. 2024, 6, 10–14. [Google Scholar] [CrossRef]
Tate, C.; Wang, R.; Akaraci, S.; Burns, C.; Garcia, L.; Clarke, M.; Hunter, R. The contribution of urban green and blue spaces to the United Nation’s Sustainable Development Goals: An evidence gap map. Cities 2024, 145, 104706. [Google Scholar] [CrossRef]
Nieuwenhuijsen, M.; de Nazelle, A.; Pradas, M.C.; Daher, C.; Dzhambov, A.M.; Echave, C.; Gössling, S.; Iungman, T.; Khreis, H.; Kirby, N.; et al. The superblock model: A review of an innovative URBAN model for sustainability, liveability, health and well-being. Environ. Res. 2024, 251, 118550. [Google Scholar] [CrossRef]
Peng, Z.-r.; Lu, K.-F.; Liu, Y.; Zhai, W. The Pathway of Urban Planning AI: From Planning Support to Plan-Making. J. Plan. Educ. Res. 2023, 44. [Google Scholar] [CrossRef]
Mashhood, M.; Salman, H.; Amjad, R.; Nisar, H. The Advantages of Using Artificial Intelligence in Urban Planning—A Review of Literature. Stat. Comput. Interdiscip. Res. 2023, 5, 1–12. [Google Scholar] [CrossRef]
Egerer, M.; Annighöfer, P.; Arzberger, S.; Burger, S.; Hecher, Y.; Knill, V.; Probst, B.M.; Suda, M. Urban oases: The social-ecological importance of small urban green spaces. Ecosyst. People 2024, 20, 2315991. [Google Scholar] [CrossRef]
Rahimi-Ardabili, H.; Astell--Burt, T.; Nguyen, P.Y.; Zhang, J.; Jiang, Y.; Dong, G.-h.; Feng, X. Green Space and Health in Mainland China: A Systematic Review. Int. J. Environ. Res. Public Health 2021, 18, 9937. [Google Scholar] [CrossRef]
Hepat, A.; Khode, D.; Chakole, S.V. A Narrative Review of Urbanization and Mental Health: An Indian Perspective. Cureus 2024, 16, e55381. [Google Scholar] [CrossRef]
Kunno, J.; Luangwilai, T.; Manomaipiboon, B.; Onklin, I.; Ong-artborirak, P.; Krainara, P.; Chaichana, T.; Gregory Robson, M. The Urban Health Themes and Urban Factors Associated with Health: A Brief Review. Vajira Med. J. 2024, 68, e269743. [Google Scholar] [CrossRef]
Lin, K.; Ramos, S.; Sun, J. Urbanization, self-harm, and suicidal ideation in left-behind children and adolescents in China: A systematic review and meta-analysis. Curr. Opin. Psychiatry 2024, 37, 225–236. [Google Scholar] [CrossRef]
Mugisha, E.K. Hypertension and Its Correlation with Socioeconomic Status in East African Urban and Rural Populations: A Scientific Review. Newport Int. J. Public Health Pharm. 2024, 5, 62–66. [Google Scholar]
Ikiriko, T.D.; Johnbull, S.W.; Brown, I. Understanding the Nexus Between Urban Planning and Public Health Challenges in Selected Informal Settlements in Port Harcourt Municipal. Glob. Res. Environ. Sustain. 2024, 2, 9–28. [Google Scholar] [CrossRef]
Gu, K.; Jing, Y.; Tang, J.; Jia, X.; Zhang, X.; Wang, B. Hypertension risk pathways in urban built environment: The case of Yuhui District, Bengbu City, China. Front. Public Health 2024, 12, 1443416. [Google Scholar] [CrossRef] [PubMed]
Mendoza-Quispe, D.; Chambergo-Michilot, D.; Moscoso-Porras, M.G.; Bernabé-Ortiz, A. Hypertension prevalence by degrees of urbanization and altitude in Peru: Pooled analysis of 186 906 participants. J. Hypertens. 2023, 41, 1142–1151. [Google Scholar] [CrossRef] [PubMed]
Tyagi, S.K.; Kumar, P.V.; Kumar, K.; Kumar, D. Environmental health quality and the consequences of urbanization: A review. Int. J. Adv. Agric. Sci. Technol. 2023, 10, 13–23. [Google Scholar] [CrossRef]
Corburn, J. Urbanization and health. In Oxford Textbook of Global Public Health; Detels, R., Karim, Q.A., Baum, F., Li, L., Leyland, A.H., Eds.; Oxford University Press: Mumbai, India, 2021. [Google Scholar]
Elsadek, M.; Li, Y.; Makvandi, M.; Zhang, D. Seasonal Influence of Sakura Trees on Human Health: Evidence From Physiological and Psycho-logical Responses. Environ. Behav. 2024, 56, 614–648. [Google Scholar] [CrossRef]
Sampson, L.A.; Ettman, C.K.; Galea, S. Urbanization, urbanicity, and depression: A review of the recent g lobal literature. Curr. Opin. Psychiatry 2020, 33, 233–244. [Google Scholar] [CrossRef]
Akomolafe, O.O.; Olorunsogo, T.; Anyanwu, E.C.; Osasona, F.; Ogugua, J.O.; Daraojimba, O.H. Air Quality and Public Health: A Review of Urban Pollution Sources and Mitigation Measures. Eng. Sci. Technol. J. 2024, 5, 259–271. [Google Scholar] [CrossRef]
Debelu, D.; Mengistu, D.A.; Aschalew, A.; Mengistie, B.; Deriba, W. Global Public Health Implications of Traffic Related Air Pollution: Systematic Review. Environ. Health Insights 2024, 18, 11786302241272403. [Google Scholar] [CrossRef]
Sagheer, U.; Al-Kindi, S.G.; Abohashem, S.; Phillips, C.T.; Rana, J.S.; Bhatnagar, A.; Gulati, M.; Rajagopalan, S.; Kalra, D.K. Environmental Pollution and Cardiovascular Disease. JACC 2024, 3, 100805. [Google Scholar]
Münzel, T.; Molitor, M.; Kuntić, M.; Hahad, O.; Röösli, M.; Engelmann, N.; Basner, M.; Daiber, A.; Sørensen, M. Transportation Noise Pollution and Cardiovascular Health. Circ. Res. 2024, 134, 1113–1135. [Google Scholar] [CrossRef] [PubMed]
Zhang, S.; Qian, Z.M.; Chen, L.; Zhao, X.; Cai, M.; Wang, C.; Zou, H.; Wu, Y.; Zhang, Z.; Li, H.; et al. Exposure to Air Pollution during Pre-Hypertension and Subsequent Hypertension, Cardiovascular Disease, and Death: A Trajectory Analysis of the UK Biobank Cohort. Environ. Health Perspect. 2023, 131, 17008. [Google Scholar] [CrossRef] [PubMed]
Shetty, S.S.; Deepthi, D.; Harshitha, S.; Sonkusare, S.; Naik, P.B.; Kumari, N.S.; Madhyastha, H. Environmental pollutants and their effects on human health. Heliyon 2023, 9, e19496. [Google Scholar] [CrossRef] [PubMed]
Khan, M.; Well, K. A Review of Traffic-related Air Pollution. Int. J. Eng. Work. 2021, 8, 175–179. [Google Scholar] [CrossRef]
Saremi, P. A Review of Role of Traffic Culture in Air Pollution Reduction in Metropolis of Developing Countries. J. Adv. Res. Altern. Energy Environ. Ecol. 2020, 7, 19–27. [Google Scholar] [CrossRef]
Sarla, G.S. Air pollution: Health effects Contaminación del aire. Ef. Sobre La Salud 2020, 37, 33–38. [Google Scholar]
Heidari, H.; Lawrence, D.A. An integrative exploration of environmental stressors on the microbiome-gut-brain axis and immune mechanisms promoting neurological disorders. J. Toxicol. Environ. Health Part B Crit. Rev. 2024, 27, 233–263. [Google Scholar] [CrossRef]
Sliwa, K.; Viljoen, C.A.; Stewart, S.; Miller, M.R.; Prabhakaran, D.; Kumar, K.; Thienemann, F.; Piniero, D.; Prabhakaran, P.; Narula, J.; et al. Cardiovascular Disease in Low-and Middle-Income Countries Associated with Environmental Factors. Eur. J. Prev. Cardiol. 2024, 31, 688–697. [Google Scholar] [CrossRef]
Wicki, B.; Vienneau, D.; Schwendinger, F.; Schmidt-Trucksäss, A.; Wunderli, J.-M.; Schalcher, S.; Röösli, M. Associations of exposure to transportation noise with sleep and cardiometabolic health: Exploration of pathways. Environ. Res. 2025, 279, 121805. [Google Scholar] [CrossRef]
Heidari, H.; Lawrence, D.A. Climate Stressors and Physiological Dysregulations: Mechanistic Connections to Pathologies. Int. J. Environ. Res. Public Health 2023, 21, 28. [Google Scholar] [CrossRef]
Awada, M.; Becerik-Gerber, B.; Liu, R.; Seyedrezaei, M.; Lu, Z.; Xenakis, M.; Lucas, G.M.; Roll, S.C.; Narayanan, S.S. Ten questions concerning the impact of environmental stress on office workers. Build. Environ. 2022, 229, 109964. [Google Scholar] [CrossRef]
Münzel, T.; Hahad, O.; Sørensen, M.; Lelieveld, J.; Duerr, G.D.; Nieuwenhuijsen, M.; Daiber, A. Environmental risk factors and cardiovascular diseases: A comprehensive expert review. Cardiovasc. Res. 2021, 118, 2880–2902. [Google Scholar] [CrossRef] [PubMed]
Sineva, I.M.; Khafizova, A.A.; Permyakov, I.A. Environmental Determinants of Urban Mental Health: A Literature Review. Public Health Life Environ. 2021, 29, 67–75. [Google Scholar] [CrossRef]
Ulpiani, G. On the linkage between urban heat island and urban pollution island: Three-decade literature review towards a conceptual framework. Sci. Total Environ. 2020, 751, 141727. [Google Scholar] [CrossRef]
Fontes, M.A.P.; Marins, F.R.; Patel, D.T.A.; de Paula, C.A.; Dos Santos Machado, L.R.; de Sousa Lima, É.B.; Ventris-Godoy, A.C.; Viana, A.C.R.; Linhares, I.C.S.; Xavier, C.H.; et al. Neurogenic Background for Emotional Stress-Associated Hypertension. Curr. Hypertens. Rep. 2023, 25, 107–116. [Google Scholar] [CrossRef]
Elsaid, N.; Saied, A.; Kandil, H.; Soliman, A.; Taher, F.; Hadi, M.; Giridharan, G.A.; Jennings, R.; Casanova, M.; Keynton, R.S.; et al. Impact of stress and hypertension on the cerebrovasculature. Front. Biosci. 2021, 26, 1643–1652. [Google Scholar] [CrossRef]
Cicalese, S.; da Silva, J.F.; Priviero, F.B.M.; Webb, R.C.; Eguchi, S.; Tostes, R.d.C. Vascular Stress Signaling in Hypertension. Circ. Res. 2021, 128, 969–992. [Google Scholar] [CrossRef]
Arregi, A.; Vegas, O.; Lertxundi, A.; Silva, A.; Ferreira, I.; Bereziartua, A.; Cruz, M.T.; Lertxundi, N. Road traffic noise exposure and its impact on health: Evidence from animal and human studies—Chronic stress, inflammation, and oxidative stress as key components of the complex downstream pathway underlying noise-induced non-auditory health effects. Environ. Sci. Pollut. Res. Int. 2024, 31, 46820–46839. [Google Scholar] [CrossRef]
Hahad, O.; Kuntić, M.; Al-Kindi, S.; Kuntić, I.; Gilan, D.; Petrowski, K.; Daiber, A.; Münzel, T. Noise and mental health: Evidence, mechanisms, and consequences. J. Expo. Sci. Environ. Epidemiol. 2025, 35, 16–23. [Google Scholar] [CrossRef]
Hassan, N.E. Noise Pollution and Its Effects on Human Health: A Review. EPRA Int. J. Multidiscip. Res. (IJMR) 2024, 10, 24–37. [Google Scholar] [CrossRef]
Mehrotra, A.; Shukla, S.P.; Shukla, A.K.; Manar, M.; Singh, S.K.; Mehrotra, M. A Comprehensive Review of Auditory and Non-Auditory Effects of Noise on Human Health. Noise Health 2024, 26, 59–69. [Google Scholar] [CrossRef] [PubMed]
Karki, T.B.; Manandhar, R.B.; Neupane, D.; Mahat, D.; Ban, P. Critical Analysis of Noise Pollution and Its Effect on Human Health. Int. J. Educ. Life Sci. 2024, 2, 161–176. [Google Scholar] [CrossRef]
Kuntić, M.; Hahad, O.; Münzel, T.; Daiber, A. Crosstalk between Oxidative Stress and Inflammation Caused by Noise and Air Pollution—Implications for Neurodegenerative Diseases. Antioxidants 2024, 13, 266. [Google Scholar] [CrossRef]
He, W.; Chen, M. Advancing Urban Life: A Systematic Review of Emerging Technologies and Artificial Intelligence in Urban Design and Planning. Buildings 2024, 14, 835. [Google Scholar] [CrossRef]
Xu, H.; Omitaomu, F.; Sabri, S.; Zlatanova, S.; Li, X.; Song, Y. Leveraging generative AI for urban digital twins: A scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement. Urban Inform. 2024, 3, 29. [Google Scholar] [CrossRef]
Bolón-Canedo, V.; Morán-Fernández, L.; Cancela, B.; Alonso-Betanzos, A. A review of green artificial intelligence: Towards a more sustainable future. Neurocomputing 2024, 599, 128096. [Google Scholar] [CrossRef]
Zhang, X.; Wang, X.; Du, S.; Tian, S.; Jia, A.; Ye, Y.; Gao, N.; Kuang, X.; Shi, X. A systematic review of urban form generation and optimization for performance-driven urban design. Build. Environ. 2024, 253, 111269. [Google Scholar] [CrossRef]
Tay, J.Z.; Ortner, F.P.; Wortmann, T.; Aydin, E.E. Computational Optimisation of Urban Design Models: A Systematic Literature Review. Urban Sci. 2024, 8, 93. [Google Scholar] [CrossRef]
Xiong, Y.; Liu, T.; Qin, Y.; Chen, H. A Scientometric Examination on Performance-Driven Optimization in Urban Block Design Research: State of the Art and Future Perspectives. Buildings 2024, 14, 403. [Google Scholar] [CrossRef]
Kidari, R.; Tilioua, A. Improving Health Through Indoor Environmental Quality Monitoring: A Review of Data-Driven Models and Smart Sensor Innovations. ITM Web Conf. 2024, 69, 02007. [Google Scholar] [CrossRef]
Bittencourt, J.C.N.; Costa, D.G.; Portugal, P.; Vasques, F. A Survey on Adaptive Smart Urban Systems. IEEE Access 2024, 12, 102826–102850. [Google Scholar] [CrossRef]
Aziz, S.; Sharun, S.M.; Wagiman, K.R.; Moorapun, C. Architectural Intelligence (ArcAI) Evolution and Progress on Sustainable Smartscapes Planning for the Cities of Tomorrow. Environ.-Behav. Proc. J. 2024, 9, 107–114. [Google Scholar] [CrossRef]
Kommineni, M.; Baseer, K.K. An Architecture and Review of Intelligence Based Traffic Control System for Smart Cities. EAI Endorsed Trans. Energy Web 2024, 11. [Google Scholar] [CrossRef]
Caetano, I.; Leitão, A. Connecting design and fabrication through algorithms: Current and future prospects for AEC. Autom. Constr. 2024, 164, 105445. [Google Scholar] [CrossRef]
Živković, M.; Žujović, M.; Milošević, J. Architectural 3D-Printed Structures Created Using Artificial Intelligence: A Review of Techniques and Applications. Appl. Sci. 2023, 13, 10671. [Google Scholar] [CrossRef]
Snooks, R. Behavioral tectonics: AgentBody prototypes and the compression of tectonics. Archit. Intell. 2022, 1, 9. [Google Scholar] [CrossRef]
Thijssens, T. The Relation Between Environmental Performance and Environmental Disclosure: A Critical Review of the Performance Measures Used. SSRN Electron. J. 2024, 24, 1140–1157. [Google Scholar] [CrossRef]
Zhou, Y.; Ma, M.; Tam, V.W.Y.; Le, K.N. Design variables affecting the environmental impacts of buildings: A critical review. J. Clean. Prod. 2023, 387, 135921. [Google Scholar] [CrossRef]
Attaianese, E.; Barilà, M. Inclusive mental well-being through environmental design. E3S Web Conf. 2023, 436, 06005. [Google Scholar] [CrossRef]
Faedda, S.; Plaisant, A.; Talu, V.; Tola, G. The Role of Urban Environment Design on Health During the COVID-19 Pandemic: A Scoping Review. Front. Public Health 2022, 10, 791656. [Google Scholar] [CrossRef] [PubMed]
Mansour Salamé, J.; Leroy, Y.; Saidani, M.; Nicolai, I. Understanding and Monitoring Environmental Performance of Infrastructure Design Projects. Proc. Des. Soc. 2021, 1, 3269–3278. [Google Scholar] [CrossRef]
Jassem, S.; Zakaria, Z.A.; Azmi, A.A.C. Sustainability balanced scorecard architecture and environmental performance outcomes: A systematic review. Int. J. Product. Perform. Manag. 2021, 71, 1728–1760. [Google Scholar] [CrossRef]
Hermányi, Z.; Pokoly, B.; Visolyi, G.Á.; Barna, I. Evaluation of Meditech ABPM-06 ambulatory blood pressure measuring device, according to the European Society of Hypertension, the British Hypertension Society and the International Organization for Standardization Protocol. Blood Press. Monit. 2019, 24, 208–211. [Google Scholar] [CrossRef]
Vienneau, D.; Saucy, A.; Schäffer, B.; Flückiger, B.; Tangermann, L.; Stafoggia, M.; Wunderli, J.M.; Röösli, M. Transportation noise exposure and cardiovascular mortality: 15-years of follow-up in a nationwide prospective cohort in Switzerland. Environ. Int. 2021, 158, 106974. [Google Scholar] [CrossRef]
Hernandez, M.F.; Chang, T.I. The Need to Reduce Variability in the Study of Blood Pressure Variability. Am. J. Kidney Dis. 2023, 81, 379–381. [Google Scholar] [CrossRef]
Teixeira, L.R.; Pega, F.; de Abreu, W.; de Almeida, M.S.; de Andrade, C.A.F.; Azevedo, T.M.; Dzhambov, A.M.; Hu, W.; Macedo, M.R.V.; Martinez-Silveira, M.S.; et al. The prevalence of occupational exposure to noise: A systematic review and meta-analysis from the WHO/ILO Joint Estimates of the Work-related Burden of Disease and Injury. Environ. Int. 2021, 154, 106380. [Google Scholar] [CrossRef]
Chen, J.; Hart, J.E.; Fisher, N.D.L.; Yanosky, J.D.; Roscoe, C.; James, P.; Laden, F. Multiple Environmental Exposures and the Development of Hypertension in a Prospective US-Based Cohort of Female Nurses: A Mixture Analysis. Environ. Sci. Technol. 2024, 58, 14146–14157. [Google Scholar] [CrossRef]
Wickramathilaka, N.; Ujang, U.; Azri, S.; Choon, T.L. Influence of Urban Green Spaces on Road Traffic Noise Levels:-A Review. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 2022, XLVIII-4/W3-2022, 195–201. [Google Scholar] [CrossRef]
Makvandi, M.; Li, B.; Elsadek, M.; Khodabakhshi, Z.; Ahmadi, M. The Interactive Impact of Building Diversity on the Thermal Balance and Micro-Climate Change under the Influence of Rapid Urbanization. Sustainability 2019, 11, 1662. [Google Scholar] [CrossRef]
Chen, J.; Hoek, G. Long-term exposure to PM and all-cause and cause-specific mortality: A systematic review and meta-analysis. Environ. Int. 2020, 143, 105974. [Google Scholar] [CrossRef]
Tota, M.; Karska, J.; Kowalski, S.; Piątek, N.; Pszczołowska, M.; Mazur, K.; Piotrowski, P. Environmental pollution and extreme weather conditions: Insights into the effect on mental health. Front. Psychiatry 2024, 15, 1389051. [Google Scholar] [CrossRef]
Sunena; Mishra, D.N. Stress Etiology of Type 2 Diabetes. Curr. Diabetes Rev. 2022, 18, e240222201413. [Google Scholar] [CrossRef]
Cozma, D.; Siatra, P.; Bornstein, S.R.; Steenblock, C. Sensitivity of the Neuroendocrine Stress Axis in Metabolic Diseases. Horm. Metab. Res. 2023, 56, 65–77. [Google Scholar] [CrossRef]
Stojanovski, T.; Zhang, H.; Frid, E.; Chhatre, K.; Peters, C.; Samuels, I.; Sanders, P.; Partanen, J.; Lefosse, D. Rethinking Computer-Aided Architectural Design (CAAD)—From Generative Algorithms and Architectural Intelligence to Environmental Design and Ambient Intelligence. In Proceedings of the Computer-Aided Architectural Design Futures, Los Angeles, CA, USA, 16–18 July 2021. [Google Scholar]
Newton, D.W. Fostering Augmented Intelligence in Architectural Education to Address Complexity. In Proceedings of the 2021 AIA/ACSA Intersections Research Conference: Communities, Washington, DC, USA, 29 September–1 October 2021. [Google Scholar] [CrossRef]
Li, J. Transforming architecture: The synergy of digital fabrication and parametric design. Appl. Comput. Eng. 2024, 66, 243–248. [Google Scholar] [CrossRef]
Yu, H.; Wen, B.; Zahidi, I.; Fai, C.M.; Madsen, D.Ø. Constructing the future: Policy-driven digital fabrication in China’s urban development. Results Eng. 2024, 22, 102096. [Google Scholar] [CrossRef]

Figure 1. Research growth rates across domains (left) and trends from 2019 to 2025 (right) highlighted significant acceleration in green spaces and health, optimization and algorithmic approaches, and architectural intelligence as rapidly advancing research fields.

Figure 2. A major urban health stressor: noise. The figure justifies the selection of a 40-year-old male for long-term monitoring. Right: ABPM50 tracks 24 h BP over 3–9 months. Top: Class-1 2250-S analyzer captures noise exposure.

Table 2. Research growth analysis: total documents (1942–2025) with focus on increment in research activity (2019–2025).

No.	Search Query	Total Documents Found	Documents Found Between 2019 and 2025	Study Growth Pattern: Increment in Research Activity Over the Last 5 Years	Identified Article Documents (n=)	Language Filter: English Only?
1	Urbanization and Health	21,266 (1956–2025)	10,843	Research growth: 50.9%	7486	Yes
2	Traffic and Pollutant	20,907 (1962–2025)	8375	Research growth: 40.0%	7118	Yes
3	Environmental and Stressors	20,895 (1961–2025)	10,011	Research growth: 47.9%	4172	Yes
4	Stressors and Hypertension	1321 (1951–2025)	431	Research growth: 32.6%	318	Yes
5	Traffic, Noise, and Stress	997 (1969–2025)	392	Research growth: 39.3%	236	Yes
6	Green Spaces and Health	3578 (1975–2025)	2754	Research growth: 76.9%	982	Yes
7	Optimization and Algorithmic Approaches	10,124 (1970–2025)	6449	Research growth: 63.7%	4272	Yes
8	Architectural and Intelligence	5105 (1942–2025)	738	Research growth: `5`3.6%	1090	Yes
9	Environmental Performance and Design	69,591 (1942–2025)	37,211	Research growth: 53.4%	4335	Yes
Total		153,784	78,194	50.8 %	30,009

Table 3. Synthesis of occurrence analysis and interdisciplinary interactions between urbanization, environmental stressors, health risks, and development-related domains.

No.	‘Urbanization’ and ‘Health’ occurrence analysis	Examination of Significant Interactions between Urbanization and Health Risk factors
1
No.	‘Traffic’ and ‘Pollutant’ occurrence analysis	Examination of Significant Interactions between Traffic and Pollutant
2
No.	‘Environmental’ and ‘Stressors’ occurrence analysis	Examination of Significant Interactions between Environmental and Stressors Risks
3
No.	‘Stressors’ and ‘Hypertension’ occurrence analysis	Examination of Significant Interactions between Stressors and Hypertension
4
No.	‘Traffic’ and ‘Noise’ and ‘Stress’ occurrence analysis	Examination of Significant Interactions between Traffic, Noise, and Stress
5
No.	‘Green Spaces’ and ‘Health’ occurrence analysis	Examination of Significant Interactions between Green Spaces and Public Health
6
No.	‘Optimization’ and ‘Algorithmic Approaches’ occurrence analysis	Examination of Significant Interactions between Optimization and Algorithmic Approaches
7
No.	‘Architectural’ and ‘Intelligence’ occurrence analysis	Examination of Significant Interactions between Architectural and Intelligence
8
No.	‘Environmental Performance’ and ‘Design’ occurrence analysis	Examination of Significant Interactions between Environment Performance and Design
9

Table 4. Why optimizing urban green spaces (UGSs) matters: unlocking benefits for public health, environmental quality, and urban resilience [23].

No.	Benefit Classification	Identifiable Impacts and Tangible Advantages	Specifics
1	Ecological benefits	Carbon sequestration	UGSs function as carbon sinks, sequestering atmospheric CO₂, thereby contributing to the mitigation of climate change.
		Biodiversity support	UGSs serve as habitats for diverse species, fostering biodiversity and bolstering ecosystem resilience.
		UHIs mitigation	Vegetation mitigates the UHIs effect by providing shade and facilitating evapotranspiration, thereby reducing ambient temperatures and lowering energy consumption for cooling.
2	Social benefits	Community integration and solidarity	UGSs serve as gathering spots for social interactions, fostering community ties and reducing isolation.
		Economic rejuvenation	Proximity to UGSs has been shown to enhance property values, attract business investment and tourism, thereby contributing to local economic growth.
		Recreation and leisure opportunities	Parks and UGSs facilitate recreational activities, thereby improving residents’ overall quality of life.
3	Health benefits	Physical health improvement	Access to UGSs promotes physical activity, thereby reducing the incidence of chronic conditions such as obesity, diabetes, and cardiovascular diseases.
		Mental health improvement	Exposure to natural environments and UGSs effectively reduces stress, anxiety, and depression, fostering psychological resilience and enhancing residents’ mental health.
		Air quality improvement	UGSs, through vegetation, filter pollutants, improving air quality and mitigating respiratory illnesses.

Table 5. Urban stressors most disruptive to human physiology.

Stress Class	Subtype	Sources	Health Impact	Thresholds	Interactions
Physical	Noise Pollution	Traffic, construction	HPA axis activation; elevated cortisol; hypertension	>65 dB (daytime) [1]	Amplifies air pollution effects
Physical	Urban Heat Islands	Heat emissions	Stress, CVD mortality, heat stroke	ΔT ≥2 °C [92] (urban vs. rural)	Increases PM_2.5 toxicity
Chemical	PM_2.5, NO₂	Vehicular emissions	Atherosclerosis, lung disease, systemic inflammation	WHO: PM_2.5 < 10 μg/m³ [93]	Synergistic with noise
Biological	Green Space Loss	Urban densification	Higher cortisol levels (stress hormone), anxiety	<9 m²/capita (WHO) [3]	Increases heat, pollution, and noise

Table 6. The impact of key environmental stressors on urban health.

		Urban Health Under Siege: The Role of Key Environmental Stressors
Ref.	Year	The noise/stress concept and the associated adverse mental health consequences	The effects of noise on different organ systems and on mental health
[62]	2024
		Molecular pathways of traffic noise-induced stress and inflammation	Environmental pollution in the pathogenesis of mental disorders
[94]	2024		ICAM-1, intercellular cell adhesion molecule-1; VCAM-1, vascular cell adhesion molecule-1; DCF, density compensation function; CBF, cerebrospinal fluid; ROS, reactive oxygen species.
		Major environmental exposures and cardiovascular health	The exposome concept of Noise-stress
[10] [55]	2024 2024
		Interplay between neuroinflammation and oxidative stress in neurodegeneration	Mechanisms of air pollution-induced neuroinflammation and oxidative stress
[66]	2024

Table 7. Computational optimization algorithms and modeling techniques for optimizing UGSs.

	Models	Objectives	Infrastructure Type	Scale
Evolutionary Algorithms (EA)	Genetic algorithm (GA)	Urban health and design: optimizing urban green spaces (UGSs), enhance biodiversity and ecological balance, reduce UHI effects, ensure equitable green space access, minimize noise, improve air quality, and promote public health and well-being.	Urban green spaces (UGSs)	Urban spatial structure
Evolutionary Algorithms (EA)	Artificial Immune Systems (AIS)	Public health: optimize UGSs, reducing environmental impact, enhancing accessibility, and preserving biodiversity within constraints. AIS effectively handles complex, multi-dimensional UGSs optimization, particularly in large, dynamic search spaces.	Urban green spaces (UGSs)	Urban spatial structure
	Annealing algorithms (AAs)	Urban health and design: AAs, especially simulated annealing (SA), optimize urban green spaces by improving layout, accessibility, and connectivity, enhancing air quality and biodiversity.	Urban green spaces (UGSs)	Urban spatial structure
	Non- Dominated Sorting (NDS)	Public health and design: given conflicting objectives like green space coverage, environmental impact reduction (e.g., noise, pollution), accessibility, biodiversity preservation, and space utilization, NDS efficiently addresses multi-objective optimization. It identifies Pareto optimal solutions, balancing these factors for effective UGSs design.	Urban green spaces (UGSs)	Urban spatial structure
	Particle Swarm-based Optimization (PSO) Algorithm	Urban health and design: a solution for urban green space placement that maximizes noise attenuation in high-traffic zones, optimizes land use within zoning constraints, enhances biodiversity, ecosystem services (e.g., air purification, carbon sequestration, water management), improves energy efficiency, and mitigates urban heat islands (UHIs).	Urban green spaces (UGSs)	Urban spatial structure
Heuristic algorithm (HA)	HA	Urban health: enhancing biodiversity, ecosystem security, and access to green spaces to improve mental and physical health. Strategically placing green spaces near high-risk areas (e.g., pollution, noise) to buffer noise, improve air quality, regulate temperature (urban heat island effect), and promote sustainability. Ensuring aesthetic quality, livability, and social equity by providing green spaces to underserved communities.	Urban green spaces (UGSs)	Urban spatial structure
Machine learning (ML)	Artificial Neural Network (ANN)	Urban health: optimizing urban green spaces (UGS) to mitigate environmental stressors like noise, air pollution, and heat. ANNs can model complex, non-linear relationships between urban factors (e.g., noise levels, population density) and desired outcomes (e.g., health improvements, pollution reduction).	Urban green spaces (UGSs)	Urban spatial structure
	Linear Regression (LR)	Urban and public health: improving urban health by addressing environmental stressors such as noise, air pollution, and heat.	Urban green spaces (UGSs)	Urban spatial structure
	Random Forest (RF)	Urban design and health: optimizing urban green spaces (UGS) by analyzing factors like green space size, vegetation, noise, and air pollution.	Urban green spaces (UGSs)	Urban spatial structure
	Support Vector Machine (SVM)	Urban health: SVM optimizes urban green spaces by classifying regions based on health outcomes and environmental stressors. It handles complex, non-linear relationships but faces challenges in scalability and interpretability. With proper tuning, it is a valuable tool for urban health optimization.	Urban green spaces (UGSs)	Urban spatial structure
Optimization Algorithms (OAs)	OAs	Urban health and design: OAs help urban planners design green space layouts, considering factors like size, distribution, accessibility, environmental stressors (e.g., noise, pollution), and their impact on urban health, energy efficiency, heat islands, air quality, biodiversity, and urban cooling.	Urban green spaces (UGSs)	Urban spatial structure
Other optimization methods	Piecewise Linear Model (PLM)	PLM optimizes UGSs by capturing non-linear relationships between green space size and urban health factors. Its segmented approach enhances decision-making, allowing planners to design effective, context-specific green spaces that adapt to varying urban conditions and stages of development.	Urban green spaces (UGSs)	Urban spatial structure
	Taguchi Method	The Taguchi Method optimizes UGSs by identifying optimal design parameters (e.g., size, plant species, accessibility) to enhance health outcomes, reduce environmental stressors (e.g., noise, pollution), and improve energy efficiency and heat island mitigation. It defines an objective function to balance these factors, ensuring effective, long-term UGSs design.	Urban green spaces (UGSs)	Urban spatial structure
	3D Spatial Optimization Model 3D-SOM	3D-SOM optimizes UGSs by considering spatial arrangements, accessibility, and environmental impacts like noise, air pollution, and heat islands. It enables multi-objective optimization, balancing noise reduction, air quality, health benefits, and heat mitigation. The model adapts to urban constraints and scales for dynamic, sustainable green space design, despite challenges in computational complexity and data requirements.	Urban green spaces (UGSs)	Urban spatial structure

Table 8. The role of architectural intelligence and AI integration in UGSs optimization for health and environmental sustainability.

Ref.	Year	Exploration	Summary	Can It Influence Environmental Performance?	Can It Impact Health Outcomes?	Can It Reduce Environmental Stressors?
[97]	2021	Rethinking Computer-Aided Architectural Design (CAAD)—From Generative Algorithms and Architectural Intelligence to Environmental Design and Ambient Intelligence	Architectural intelligence augmented by AI can refine urban design strategies to enhance environmental performance and foster healthier urban environments.	YES. AI-driven design leads to more efficient and sustainable urban spaces, improving air quality, biodiversity, and energy use.	YES. Enhances mental and physical health through better-designed spaces that reduce stressors.	YES. Reduces urban heat islands, pollution, and noise.
[75]	2024	Architectural Intelligence (ArcAI) Evolution and Progress on Sustainable Smartscapes Planning for the Cities of Tomorrow	Architectural intelligence and AI can integrate eco-friendly practices and smart technologies to create sustainable smart urban environments.	YES. Promotes eco-friendly practices, energy efficiency, and reduced carbon footprints.	YES. Improved health outcomes through smarter urban planning and better access to green spaces.	YES. Addresses air pollution, reduces heat effects, and promotes efficient use of space.
[98]	2021	Fostering Augmented Intelligence in Architectural Education to Address Complexity	Augmented intelligence combining human and AI can help architectural education address complex design problems for sustainable urban environments.	YES. Improves sustainable building designs, optimizing material usage and energy consumption.	YES. Supports mental health by creating environments that address the psychological impact of urban living.	YES. Reduces resource waste and environmental degradation.
[99]	2024	Transforming architecture: The synergy of digital fabrication and parametric design	The integration of digital fabrication and parametric design enables more sustainable, efficient, and innovative architectural solutions.	YES. Enhances energy efficiency, reduces waste, and supports sustainability in urban environments.	YES. Contributes to healthier urban areas by creating environments that support social well-being.	YES. Reduces construction waste, pollution, and resource consumption.
[100]	2024	Constructing the future: Policy-driven digital fabrication in urban development	Digital fabrication technologies (e.g., 3D printing and CNC machining) are revolutionizing architectural design, improving construction efficiency, enabling smart city innovations, and promoting sustainability.	YES. Improves the sustainability of urban infrastructure, reducing carbon emissions and material waste.	YES. Provides access to health-optimizing green spaces and reduces urban heat islands.	YES. Helps reduce environmental stressors such as noise, pollution, and energy consumption.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

Share and Cite

MDPI and ACS Style

Makvandi, M.; Khodabakhshi, Z.; Liu, Y.; Li, W.; Yuan, P.F. Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience. Sustainability 2025, 17, 6973. https://doi.org/10.3390/su17156973

AMA Style

Makvandi M, Khodabakhshi Z, Liu Y, Li W, Yuan PF. Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience. Sustainability. 2025; 17(15):6973. https://doi.org/10.3390/su17156973

Chicago/Turabian Style

Makvandi, Mehdi, Zeinab Khodabakhshi, Yige Liu, Wenjing Li, and Philip F. Yuan. 2025. "Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience" Sustainability 17, no. 15: 6973. https://doi.org/10.3390/su17156973

APA Style

Makvandi, M., Khodabakhshi, Z., Liu, Y., Li, W., & Yuan, P. F. (2025). Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience. Sustainability, 17(15), 6973. https://doi.org/10.3390/su17156973

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Can AI and Urban Design Optimization Mitigate Cardiovascular Risks Amid Rapid Urbanization? Unveiling the Impact of Environmental Stressors on Health Resilience

Abstract

1. Introduction

2. Methodology

2.1. Design and Framework

2.2. Research Questions

2.3. Search Strategy

2.4. Inclusion and Exclusion Criteria

2.5. Data Extraction and Synthesis

2.6. Visualizing Network and Bibliometric Trends with VOSviewer and VS Code

2.7. Rigorous Overview of the Two-Phase Methodology

2.7.1. Phase 1: Mixed Methods Systematic Review (MMSR)

2.7.2. Phase 2: Empirical Data Collection and Analysis (EDCA)

3. Classification, Analysis, and Outcomes

3.1. Systematic Analysis of Urbanization and Health Interactions: A Data-Driven Perspective

3.1.1. Thematic Convergence and Research Density Trends

3.1.2. Research Growth Trajectories and Emerging Convergences

3.1.3. Multivariate Linkages and Network Dependencies

3.1.4. Hierarchical Interactions of Environmental Stressors

3.2. From Comprehensive MMSR to Empirical Evidence: Establishing Noise as a Critical Environmental Stressor

The Cardiovascular Toll of Chronic Noise: Mechanisms and Urban Solutions

3.3. Optimizing Urban Green Spaces for Health and Sustainability: The Role of AI and Nature-Based Solutions (NBS) in Mitigating Environmental Stress

3.4. Proposed Framework for Mitigating Urban Health Risks and Enhancing Resilience

4. Conclusions

Limitations and Future Work

Author Contributions

Funding

Institutional Review Board Statement

Informed Consent Statement

Data Availability Statement

Acknowledgments

Conflicts of Interest

Abbreviations

Appendix A

Standard Body Mass Index (BMI) Classification

Appendix B

Community Health Data from the Study Area

Appendix C

Comparative Health and Exposure Metrics: Case Subject vs. Long-Term Urban Residents

References

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI