Search Results (20)

Artificial intelligence (AI) is increasingly influencing healthcare administration and clinical informatics by supporting disease diagnosis, clinical decision-making, treatment personalization, drug discovery, remote monitoring, public health surveillance, and hospital operations. However, the successful adoption of AI in healthcare depends not only on algorithmic performance, but also on its safe integration into clinical information systems, organizational workflows, and governance structures. This article presents a narrative critical review of recent advances in AI-driven healthcare, with a focus on four major domains: AI-enabled disease diagnosis, treatment personalization and clinical decision support, drug discovery and biomedical knowledge generation, and healthcare administration. Evidence from radiology, pathology, ophthalmology, dermatology, and cardiology shows that AI systems can achieve strong diagnostic performance in selected settings, while applications in electronic health records, natural language processing, telemedicine, and predictive analytics are increasingly used to support healthcare delivery and operational decision-making. At the same time, important barriers continue to limit real-world implementation, including fragmented data infrastructures, limited interoperability, poor data quality, algorithmic bias, lack of explainability, privacy and cybersecurity risks, unclear accountability, and insufficient external validation. This review critically examines these challenges and proposes a governance-oriented roadmap for responsible AI integration in healthcare administration and clinical informatics. The proposed roadmap emphasizes data readiness, model validation, workflow integration, institutional accountability, post-deployment monitoring, and workforce readiness. The findings suggest that AI can contribute to more efficient, accessible, and patient-centered healthcare only when it is implemented within trustworthy medical informatics ecosystems supported by ethical governance, human oversight, and continuous evaluation. Full article

This study investigates how AI-driven personalization shapes traveler satisfaction in a post-adoption tourism context, with particular attention to the mechanisms and boundary conditions through which personalization is associated with experiential outcomes. Using an integrated post-adoption framework, the study conceptualizes AI-driven personalization as an experiential input influencing satisfaction through trust formation, perceived value, and individual readiness to engage with technology. Survey data were collected from 347 tourists with direct experience of AI-enabled tourism services in Kosovo. The relationships were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results show that AI-driven personalization is positively associated with traveler satisfaction. It enhances trust in AI-powered systems, and trust is positively associated with perceived value. Perceived value mediates the relationship between trust in AI-powered systems and traveler satisfaction, highlighting value appraisal as a central post-adoption mechanism. AI-driven personalization is also indirectly associated with traveler satisfaction through a sequential mechanism, in which trust precedes perceived value in the experiential evaluation process. Technology readiness moderates the relationship between perceived value and traveler satisfaction, indicating heterogeneous experiential responses to AI-enabled tourism services. The study contributes to tourism and hospitality research by demonstrating a sequential relational–evaluative mechanism through which AI-driven personalization is associated with traveler satisfaction, shifting the focus from adoption-based explanations toward post-adoption experiential pathways. It further clarifies the role of trust as a relational mechanism preceding value formation and identifies technology readiness as a boundary condition shaping satisfaction outcomes in an emerging destination context. The findings also offer practical guidance for designing AI-enabled services that strengthen trust, enhance value perceptions, and align personalization strategies with varying levels of traveler technology readiness. Full article

Background: Esophageal squamous cell carcinoma (ESCC) is the predominant subtype of esophageal cancer, with poor outcomes following neoadjuvant chemoradiotherapy (NCRT). Neoadjuvant chemoimmunotherapy (NCIT) has emerged as a promising strategy, but reliable predictive biomarkers remain lacking. This study aimed to develop an AI-driven pathomic model for NCIT response prediction and explore its biological mechanisms. Methods: We analyzed 269 H&E-stained whole-slide images (WSIs) from 198 ESCC patients (104 from Tongji Hospital, 94 from TCGA). Using ResNet152, we segmented WSIs into four tissue categories (tumor cells, stroma, lymphocytes, and necrosis), extracted spatially weighted pathomic features, and constructed the ECiT score via logistic regression. An integrated model combining the ECiT score with clinical variables (T stage, P53 status) was developed. Mechanistic analyses were performed using TCGA-ESCA and GSE160269 datasets. Results: The integrated model achieved AUCs of 0.897 (training) and 0.809 (temporal validation), outperforming clinical (AUC = 0.624) and pathomic-only (AUC = 0.751) models. Mechanistically, a high ECiT score correlated with enhanced immune activation (elevated CD4⁺ memory T cell infiltration), while low scores were linked to endoplasmic reticulum (ER) stress-unfolded protein response (UPR) activation. EIF2S3 was identified as a key molecular mediator, correlating with three pathomic features, UPR activation, and poor prognosis. Conclusions: This study may offer a preliminary indicator that could assist in personalized clinical decision-making. Correlative evidence suggests that the EIF2S3-mediated ER stress–UPR axis represents a potential candidate therapeutic target to overcome NCIT resistance, generating testable hypotheses to advance precision oncology for resectable locally advanced ESCC. Full article

This study examines sector-specific patterns of remarketing implementation in manufacturing and service industries and evaluates their effectiveness during digital transformation from a sustainability perspective. Using a mixed-method approach, the research combines descriptive analysis of enterprises’ digital maturity with Monte Carlo simulation modeling of remarketing campaign performance based on key parameters such as budget allocation, conversion efficiency, customer lifetime value, personalization intensity, and investment in AI-driven analytics. The results demonstrate that remarketing enhances traffic, user engagement, and return on investment; however, its sustainability depends on sectoral characteristics and behavioral responsiveness. AI-powered personalization is identified as a critical factor in reducing ad fatigue and improving conversion stability. While manufacturing firms tend to achieve higher but more volatile returns, service-sector companies demonstrate more stable outcomes due to greater digital adaptability and more intensive use of dynamic advertising tools. The findings highlight that sustainable remarketing strategies require sector-specific adaptation to balance economic efficiency, technological investment, and long-term consumer engagement, thereby supporting resilient and sustainable business development in the digital economy. Full article

Boron neutron capture therapy (BNCT) is experiencing a global resurgence driven by advances in boron pharmacology, accelerator-based neutron sources, and molecular imaging-guided theranostics. BNCT produces high linear energy transfer particles with micrometer-range energy deposition, enabling cell-selective irradiation confined to boron-enriched tumor cells in a geometrically targeted region by the neutron beam. This mechanism offers the potential for exceptionally high therapeutic ratios, provided two core requirements are met: sufficient differential tumor uptake of ¹⁰B and a neutron beam with appropriate energy and penetration. After early clinical attempts in the mid-20th century were hindered by inadequate boron agents and reactor-based neutron beams, recent technological breakthroughs have made BNCT clinically viable. The development of hospital-compatible accelerator neutron sources, next-generation boron delivery systems (such as receptor-targeted compounds and nanoparticles), advanced theranostic approaches (such as ¹⁸F-BPA positron emission tomography and boron-sensitive magnetic resonance imaging), and AI-driven biodistribution modeling now support personalized treatment planning and patient selection. These innovations have catalyzed modern clinical implementation, exemplified by Japan’s regulatory approval of BNCT for recurrent head and neck cancer and the rapid expansion of clinical programs across Asia, Europe, and South America. Building on these foundations, BNCT has transitioned from a predominantly academic experimental modality into an increasingly commercialized and industrially supported therapeutic platform. The emergence of dedicated BNCT companies, international collaborations between accelerator manufacturers and hospitals, and pharmaceutical development pipelines for next-generation boron carriers has accelerated clinical translation. Moreover, BNCT now occupies a unique position among radiation modalities due to its hybrid nature, namely combining the biological targeting of radiopharmaceutical therapy with the external-beam controllability of radiotherapy, thereby offering new therapeutic opportunities where competitive approaches fall short. Emerging evidence suggests therapeutic promise in glioblastoma, recurrent head and neck cancers, melanoma, meningioma, lung cancer, sarcomas, and other difficult-to-treat malignancies. Looking ahead, continued innovation in compact neutron source engineering, boron nanocarriers, multimodal theranostics, microdosimetry-guided treatment planning, and combination strategies with systemic therapies such as immunotherapy will be essential for optimizing outcomes. Together, these converging developments position BNCT as a biologically targeted and potentially transformative modality in the era of precision oncology. Full article

This study investigates how next-generation digital infrastructures—terahertz (THz) communication and AI-driven network orchestration—shape perceived service quality, luxury perception, and loyalty within the context of luxury hospitality. An empirical survey was conducted among 693 guests at Torre Melina Gran Meliá (Barcelona) between June 2024 and June 2025. Using a refined 38-item Likert-scale instrument, a three-factor structure was validated: (F1) Network Performance (speed, stability, coverage, seamless roaming, and multi-device reliability), (F2) Luxury Perception (modernity, innovation, and brand image), and (F3) Service Loyalty (satisfaction, return intentions, recommendations, and willingness to pay a premium). The results reveal that superior network performance functions both practically and symbolically. Functionally, it enables uninterrupted video calls, smooth streaming, low-latency gaming, and reliable multi-device usage—now considered essential utilities for contemporary travelers. Symbolically, high-performing and intelligently managed connectivity conveys technological leadership and exclusivity, thereby enhancing the hotel’s luxury image. Collectively, these effects create a “virtuous cycle” in which technical excellence reinforces perceptions of luxury, which in turn amplifies satisfaction and loyalty behaviors. From a managerial perspective, advanced connectivity should be viewed as a strategic investment and brand differentiator rather than a cost center. THz-ready, AI-orchestrated networks support personalization, dynamic bandwidth allocation (i.e., real-time adjustment of network capacity in response to fluctuating user demand), and monetizable premium service tiers, directly strengthening guest retention and brand equity. Ultimately, next-generation connectivity emerges not as an ancillary amenity but as a defining pillar of luxury hospitality in the emerging 6G era. Full article

Wearable devices are becoming widely applied in healthcare to enable continuous, noninvasive monitoring, but their use in pediatric populations remains relatively underexplored. This review synthesizes 36 clinical studies focused on pediatric hospital and outpatient wearables published between 2014 and 2025. Devices included wrist-worn trackers, adhesive biosensors, and more, capturing electrocardiography, photoplethysmography, accelerometry, and other signals. Clinical applications spanned a variety of care settings. Artificial intelligence (AI) partially enhanced interpretation for the early detection of conditions such as postoperative complications and sepsis. Despite their promising accuracy, most studies remain small, single-center pilots focused on feasibility and signal validity rather than outcomes such as mortality, readmission, or long-term recovery. Key barriers include pediatric-specific device design, motion-robust signal quality, regulatory clearance, workflow integration, and equitable adoption in low-resource settings. Ethical concerns such as privacy, consent, and incidental findings and regulatory constraints, particularly the lack of pediatric labeling and approval for consumer and AI-driven devices, further limit translation into practice. Future work should prioritize multi-center studies, multimodal analytics, explainable AI, and seamless integration into clinical pathways. With these advances, wearables can move beyond feasibility to become reliable, personalized tools that improve pediatric monitoring and care. Full article

Background/Objectives: Efficient and personalized task allocation in hospital emergency departments (EDs) is critical for operational efficiency and patient-centered care. However, the complexity of staff coordination and the variability among patients and healthcare professionals pose significant challenges. This study proposes a simulation-based framework for modeling doctors and nurses as intelligent agents guided by computational trust mechanisms. The objective is to explore how trust-informed coordination can support AI-driven and personalized decision-making in ED management. Methods: The framework was implemented in Unity, a 3D graphics platform, where agents assess their competence and patient-specific needs before undertaking tasks and adaptively coordinate with colleagues. The simulation environment enables real-time observation of workflow dynamics, resource utilization, and patient outcomes. We examined three scenarios—Baseline, Replacement, and Training—reflecting alternative staff management strategies. Results: Trust-informed task allocation balanced patient safety and efficiency by adaptively responding to nurse performance and patient acuity levels. In the Baseline scenario, prioritizing safety reduced errors but increased patient delays compared to a FIFO policy. The Replacement scenario improved throughput and reduced delays, though at additional staffing costs. The training scenario fostered long-term skill development among low-performing nurses, despite short-term delays and risks, supporting sustainable and personalized capacity building in ED teams. Conclusions: The proposed framework demonstrates the potential of computational trust for personalized and evidence-based decision support in emergency medicine. By linking staff coordination with adaptive and AI-informed decision-making, hospital managers are provided with a tool to evaluate alternative staffing and treatment policies under controlled and repeatable conditions. This work thus contributes to the broader vision of precision and personalized medicine, where operational decisions dynamically adapt to both patient needs and staff capabilities. Full article

Background: Older adults are highly vulnerable to infectious diseases due to immunosenescence, multimorbidity, and atypical presentations. Artificial intelligence (AI) offers promising opportunities to improve diagnosis, prognosis, treatment, and continuity of care in this population. This review summarizes current applications of AI in the management of infections in older adults across diagnostic, prognostic, therapeutic, and preventive domains. Methods: We conducted a narrative review of peer-reviewed studies retrieved from PubMed, Scopus, and Web of Science, focusing on AI-based tools for infection diagnosis, risk prediction, antimicrobial stewardship, prevention of healthcare-associated infections, and post-discharge care in individuals aged ≥65 years. Results: AI models, including machine learning, deep learning, and natural language processing techniques, have demonstrated high performance in detecting infections such as sepsis, pneumonia, and healthcare-associated infections (Area Under the Curve AUC up to 0.98). Prognostic algorithms integrating frailty and functional status enhance the prediction of mortality, complications, and readmission. AI-driven clinical decision support systems contribute to optimized antimicrobial therapy and timely interventions, while remote monitoring and telemedicine applications support safer hospital-to-home transitions and reduced 30-day readmissions. However, the implementation of these technologies is limited by the underrepresentation of frail older adults in training datasets, lack of real-world validation in geriatric settings, and the insufficient explainability of many models. Additional barriers include system interoperability issues and variable digital infrastructure, particularly in long-term care and community settings. Conclusions: AI has strong potential to support predictive and personalized infection management in older adults. Future research should focus on developing geriatric-specific, interpretable models, improving system integration, and fostering interdisciplinary collaboration to ensure safe and equitable implementation. Full article

The hospitality industry’s rapid adoption of AI service robots has revealed significant variability in consumer acceptance, highlighting the need for personality-based implementation strategies rather than one-size-fits-all approaches. This study extended the AIDUA (Artificial Intelligence Device Use Acceptance) model by integrating Big Five personality traits and robot design characteristics to understand AI service robot acceptance among South African hospitality consumers. A convergent mixed-methods design combined structural equation modeling of survey data (n = 301) with natural language processing analysis of qualitative responses to examine personality-acceptance pathways and consumer concern themes. Results demonstrated that neuroticism negatively influenced performance expectancy (β = −0.284, p < 0.001), while openness enhanced hedonic motivation and preference for humanoid robots (β = 0.347, p < 0.001). Privacy concerns partially mediated the neuroticism-rejection relationship, while transparency interventions significantly improved acceptance among high-neuroticism consumers (effect size d = 0.98). Four distinct consumer segments emerged: Tech Innovators (23.1%), Pragmatic Adopters (31.7%), Cautious Sceptics (28.4%), and Social Moderates (16.8%), each requiring tailored robot deployment strategies. The extended AIDUA framework explained 68.4% of variance in acceptance intentions, providing hospitality operators with empirically validated guidelines for matching robot types to guest personality profiles, optimizing guest satisfaction while minimizing resistance through culturally sensitive implementation strategies. Full article

This study investigates hotel employees’ perceptions of AI-driven human resource (HR) management systems within the Accor Group’s properties across three major European cities: Paris, Berlin, and Amsterdam. These diverse urban contexts, spanning a broad portfolio of hotel brands from luxury to economy, provide a rich setting for exploring how AI integration affects employee attitudes and work–life balance. A total of 437 employees participated in the survey, offering a robust dataset for structural equation modeling (SEM) analysis. Exploratory factor analysis identified two primary factors shaping perceptions: AI Perceptions, which encompasses employee views on AI’s impact on job performance, communication, recognition, and retention, and balanced management, reflecting attitudes toward fairness, personal consideration, productivity, and skill development in AI-managed environments. The results reveal a complex but optimistic view, where employees acknowledge AI’s potential to enhance operational efficiency and career optimism but also express concerns about flexibility loss and the need for human oversight. The findings underscore the importance of transparent communication, contextual sensitivity, and continuous training in implementing AI systems that support both organizational goals and employee well-being. This study contributes valuable insights to hospitality management by highlighting the relational and ethical dimensions of algorithmic HR systems across varied organizational and cultural settings. Full article

Artificial intelligence (AI) is transforming organizational functions across sectors; however, its application to human resource management (HRM) within healthcare remains underexplored. This study aims to unpack the black-box nature of AI capability’s impact on HR functions within China’s healthcare sector, a domain undergoing rapid digital transformation, driven by national innovation policies. Grounded in resource-based theory, the study conceptualizes AI capability as a multidimensional construct encompassing tangible resources, human resources, and organizational intangibles. Using a structural equation modeling approach (PLS-SEM), the analysis draws on survey data from 331 professionals across five hospitals in three Chinese cities. The results demonstrate a strong, positive, and statistically significant relationship between AI capability and HR functions, accounting for 75.2% of the explained variance. These findings indicate that AI capability enhances HR performance through smarter recruitment, personalized training, and data-driven talent management. By empirically illuminating the mechanisms linking AI capability to HR outcomes, the study contributes to theoretical development and offers actionable insights for healthcare administrators and policymakers. It positions AI not merely as a technological tool but as a strategic resource to address talent shortages and improve equity in workforce distribution. This work helps to clarify a previously opaque area of AI application in healthcare HRM. Full article

Background/Objectives: Recent advances in artificial intelligence (AI) and machine learning (ML) enable targeted optimization of emergency department (ED) operations. We examine how reworking an ED’s vertical processing pathway (VPP) using AI- and ML-driven recommendations affected patient throughput. Methods: We trained a non-linear ML model using triage data from 49,350 ED encounters to generate a personalized risk score that predicted whether an incoming patient is suitable for vertical processing. This model was integrated into a stochastic patient flow framework using queueing theory to derive an optimized VPP design. The resulting protocol prioritized a vertical assessment for patients with Emergency Severity Index (ESI) scores of 4 and 5, as well as 3 when the chief complaints involved skin, urinary, or eye issues. In periods of ED saturation, our data-driven protocol suggested that any waiting room patient should become VPP eligible. We implemented this protocol during a 13-week prospective trial and evaluated its effect on ED performance using before-and-after data. Results: Implementation of the optimized VPP protocol reduced the average ED length of stay (LOS) by 10.75 min (4.15%). Adjusted analyses controlling for potential confounders during the study period estimated a LOS reduction between 7.5 and 11.9 min (2.89% and 4.60%, respectively). No adverse effects were observed in the quality metrics, including 72 h ED revisit or hospitalization rates. Conclusions: A personalized, data-driven VPP protocol, enabled by ML predictions, significantly improved the ED throughput while preserving care quality. Unlike standard fast-track systems, this approach adapts to ED saturation and patient acuity. The methodology is customizable to patient populations and ED operational characteristics, supporting personalized patient flow optimization across diverse emergency care settings. Full article

Background/Objectives: Lumbar spine surgery has undergone significant technological transformation in recent years, driven by the goals of minimizing invasiveness, improving precision, and enhancing clinical outcomes. Emerging tools—including robotics, augmented reality, computer-assisted navigation, and artificial intelligence—have complemented the evolution of minimally invasive surgical (MIS) approaches, such as endoscopic and lateral interbody fusions. Methods: This systematic review evaluates the literature from February 2020 to February 2025 on technological and procedural innovations in LSS. Eligible studies focused on degenerative lumbar pathologies, advanced surgical technologies, and reported clinical or perioperative outcomes. Randomized controlled trials, comparative studies, meta-analyses, and large case series were included. Results: A total of 32 studies met the inclusion criteria. Robotic-assisted surgery demonstrated high accuracy in pedicle screw placement (~92–94%) and reduced intraoperative blood loss and radiation exposure, although long-term clinical outcomes were comparable to conventional techniques. Intraoperative navigation improved instrumentation precision, while AR enhanced ergonomic workflow and reduced surgeon distraction. AI tools showed promise in surgical planning, guidance, and outcome prediction but lacked definitive evidence of clinical superiority. MIS techniques—including endoscopic discectomy and MIS-TLIF—offered reduced blood loss, shorter hospital stays, and faster recovery, with equivalent pain relief, fusion rates, and complication profiles compared to open procedures. Lateral and oblique approaches (XLIF/OLIF) further optimized alignment and indirect decompression, with favorable perioperative metrics. Conclusions: Recent innovations in lumbar spine surgery have enhanced technical precision and perioperative efficiency without compromising patient outcomes. While short-term benefits are clear, long-term clinical advantages and cost-effectiveness require further investigation. Integration of robotics, navigation, AI, and MIS into spine surgery reflects an ongoing shift toward personalized, data-driven, and less invasive care. Full article

Artificial intelligence (AI) is playing a dominant role in advancing heart failure detection and diagnosis, significantly furthering personalized healthcare. This review synthesizes AI-driven innovations by examining methodologies, applications, and outcomes. We investigate the integration of machine learning algorithms, diverse datasets including electronic health records (EHRs), medical records, imaging data, and clinical notes, deep learning models, and neural networks to enhance diagnostic accuracy. Key advancements include prediction models that leverage real-time data from wearable devices alongside state-of-the-art AI systems trained on patient data from hospitals and clinics. Notably, recent studies have reported diagnostic accuracies ranging from 86.7% to as high as 99.9%, with sensitivity and specificity values often exceeding 97%, underscoring the potential of these AI systems to improve early detection and clinical decision-making substantially. Our review further explores the impact of symmetry and asymmetry in model design, highlighting that symmetric architectures like U-Net offer computational efficiency and structured feature extraction. In contrast, asymmetric models improve the sensitivity to rare conditions and subtle clinical patterns. Incorporating these deep learning (DL) methods in anomaly detection and disease progression modeling further reinforces their positive impact on diagnostic accuracy and patient outcomes. Furthermore, this review identifies challenges in current AI applications, such as data quality, algorithmic transparency, model bias, and evaluation metrics, while outlining future research directions, including integrating generative models, hybrid architectures, and explainable AI techniques to optimize clinical practice. Full article