The Role of Evidence-Based Management in Driving Sustainable Innovation in Saudi Arabian Healthcare Systems

Abstract

Nowadays, evidence-based management (EBM) plays an important role in bringing sustainability into the decision-making process in the healthcare industry. The present study examines how evidence-based management affects the strategic decision criteria for the cost efficiency, equity, and accessibility of medical services in Saudi Arabia. A mixed-methods approach used hybrid surveys, interactive focus groups, digital ethnography, and experience sampling methods to collect data from healthcare managers, policymakers, and stakeholders. Structural equation modeling (SEM), latent semantic analysis (LSA), XGBoost models, and dynamic network analysis (DNA), among others, were used to provide robust insights about the system. The results showed a 25 percent increase in cost efficiency, a 20 percent improvement in inequitable resource allocation, and a 15 percent improvement in accessibility with evidence-based management adoption. According to the XGBoost models, streamlined resource management explains 30% of the variation in cost efficiency, and data-driven decision-making practices explain 35% of the variance in equity performance. After EBM implementation, collaborative efforts among stakeholders increased by 40%, as determined by DNA analysis. In addition, time-series analysis revealed a 22% reduction in operational delays, improving service delivery. These results suggest that evidence-based management is an important opportunity to ‘bend the curve’ of patient care, driving healthcare sustainability by optimizing resource use, equity, and accessibility. The contributions of this research to the broader discourse on sustainable healthcare management lie in its proven actionable insights and scalable framework for evidence-based management practices. The integration of advanced analytics underlines its relevance for global healthcare systems to attain long-term efficiency and sustainability.

1. Introduction

1.1. Background

Evidence-based management (EBM) has become a transformative paradigm in healthcare organizations, where significant changes in strategic thinking and healthcare delivery have occurred. It holds significant potential to improve strategic decision-making and healthcare outcomes in Saudi Arabia. In times of significant technological and demographic shifts in the contemporary healthcare systems, applying systematic, research-based strategies is now more critical than ever [1].

The sustainable model of the healthcare ecosystem demands an equilibrium between economic factors and the quality of healthcare services. However, classical decision-making models are no longer popular, and more contemporary models based on data and insights are being built. Applying these analytical frameworks in healthcare organizations allows for the efficient utilization of resources, maximization of patient care, and better service delivery. Contrary to traditional managerial techniques based on assessment, learning, and evidence-based action, this approach is considered far superior. EBM and strategic decision-making are useful in tackling real healthcare issues. They create a continuous enhancement, creativity, and adaptive management culture, prompting us to accept change and seek improvements [2].

The healthcare system in Saudi Arabia operates through a combination of public and private sectors. The Ministry of Health (MoH) serves as the primary provider, financer, and regulator of healthcare services, offering free care to citizens and residents in public facilities. In contrast, the private sector complements public services by offering specialized and premium care, typically on a fee-for-service basis or through private insurance. Healthcare financing is predominantly government-funded, though recent reforms under Vision 2030 aim to enhance private-sector participation and promote sustainability through public–private partnerships. Vision 2030 is a transformative initiative that emphasizes healthcare privatization, quality improvement, and accessibility, thus reshaping the healthcare landscape across the Kingdom.

Evidence-based management (EBM) serves as a strategic method to unite research findings with managerial know-how and organizational factors for enhancing healthcare choices. In healthcare organizations, Evidence-based management (EBM) is described as a systematic method of interpretation of evidence from systematic research, critical assessment, and data analysis to support management decision-making [3]. This approach introduces a new approach to how healthcare organizations navigate and design their management plans, shifting from an ad hoc basis to a systematic and research-based approach [4].

1.2. Significance of the Study

This paper underscores the importance of EBM in healthcare management. It makes efficiency, service quality, and sustainability easier. EBM is compelling because a wealth of literature describes its potential to transform healthcare and foster new practices that make organizations more flexible and adaptable [5]. This is particularly helpful in emerging healthcare systems with limited resources and innovative care [2].

Encouraging critical thinking and evidence-based practice enhances management approaches in the healthcare sector. This approach enables leadership to depart from normal decision-making frameworks and rely on science-based evidence and analysis. Amid today’s complex healthcare systems, organizations need to be structured to understand and effectively maneuver the environment and create better options for healthcare [6].

Medical service decision-making occurs at strategic levels and depends on many interdependent factors, including economic factors. It entails overcoming challenges that call for conceptual tools to knit practical data with strategic business objectives. In the modern world, numerous tight fiscal situations exist in health institutions. Using sophisticated operational research methods, decision-makers should design strategies to estimate a middle ground between the distribution of resources and the provision of high-quality services [7].

Equity and accessibility are two vital strategic measures ensuring healthcare services for various population groups, guaranteeing equity and accessibility in healthcare services. This is even more important when the populace of the society is characterized by many demographic and socioeconomic differences, as in Saudi Arabia. Decision-making should be included so that gaps are addressed and healthcare delivery systems are established to meet the population’s diverse needs. One of the key strategic choices, technological adoption, occurs through the adoption of such technologies as AI, telemedicine, and precision medicine, which revolutionize care delivery [8].

1.3. Literature Review

The existing literature suggests theoretical frameworks for integrating evidence-based management with strategic management. These frameworks encompass stakeholder needs and cover the long-term goals of healthcare organizations and management systems that address the challenges in healthcare environments. Incorporating EBM principles into healthcare organizations and developing an effective, adaptable, patient-centered management system will tackle current and future healthcare challenges more sustainably and creatively [9].

The study of the future of healthcare economics and management is defined as a research area that integrates evidence-based management, strategic decision-making, and sustainable innovation. This intersection is a unique opportunity for innovative means of healthcare provision applicable in the rapidly developing healthcare systems of countries like Saudi Arabia. In this context, public–private partnerships have become the main mechanism to support the implementation of sustainable health management practices, exchange experiences, and develop new approaches and services for the public and private sectors [10].

Sustainable innovations in healthcare are not limited to technological solutions but include an overall organization, management, and resource utilization model. These innovations focus on important areas of society, including healthcare affordability and quality. New technologies such as telemedicine, AI, diagnostic tools, and personalized medicine are the most important areas of sustainable innovation that can revolutionize the healthcare landscape [11].

This approach uses universal frameworks such as SDG 3 (Good Health and Well-being) and SDG 13 (Climate Action). SDG 3 involves ensuring universal health across age demographics through access to quality healthcare; on the other hand, SDG 13 deals with climate action within the healthcare system. EBM addresses both these goals because it uses a data analysis process to improve the quality of services while decreasing the number of resources wasted. For example, telemedicine and the use of artificial intelligence for diagnoses are less detrimental to the environment, while extending availability, reinforcing healthcare equity, and supporting healthcare frameworks’ commitment to addressing border- and climate-related injustices.

An analysis of Saudi Arabia’s Vision 2030 highlights how global sustainability frameworks such as the SDGs can be used to solve a local health issue. Inspired by the Triple Bottom Line (TBL) framework, Vision 2030 encourages risk sharing between parties, such as the government and private companies, productivity, and incorporating changes into economic, social, and environmental plans [8]. This shift has been observed globally, as classical decision-making frameworks are increasingly viewed as inadequate in the face of modern healthcare complexity [12]. This strategy helps fill gaps in healthcare equity and sustainability, overcoming demographic and technological hurdles. These concepts help Vision 2030 align with SDG principles in a replicable manner, showing the global community how local policies can lead to new health innovations in the context of continually dwindling resources alongside environmental pressures.

Technology is especially crucial in fast-developing countries for sustaining health management. Advanced analytics, machine learning, and data-driven decision tools improve healthcare organizations’ performance by providing better management strategies. EBM can help healthcare organizations design more effective, efficient, sustainable, and flexible patient-centered management systems and solve modern problems in the healthcare system [13].

The emerging issues of an aging population, digitization, and post-COVID-19 realities have made the subject of sustainable healthcare solutions even more topical. The demographics of the aging population require personalized and labor-intensive care, which poses equity and efficiency issues, particularly in countries and regions such as Saudi Arabia, which have a high level of socioeconomic differences. Forging ahead are innovations in fast-growing sectors like artificial intelligence, telemedicine, etc. At the same time, these can revolutionize healthcare delivery, but if not implemented, they may perpetuate inequality in access to services. Moreover, the COVID-19 pandemic highlighted crucial vulnerabilities fundamental to societies and exposed the healthcare sector’s need for stronger and more diverse adaptive capabilities.

EBM provides a structured alternative to ad hoc planning, aligning with recent findings on evidence-based leadership effectiveness in healthcare [14]. Based on these challenges, evidence-based management (EBM) is a potent approach to resource distribution and planning using data. EBM helps balance value creation, distribution, and sustainability through integration with loyalty-focused ideas like the SDGs and Vision 2030. It allows systems to pursue more equity and sustainability while managing tension resulting from demographic and technological fluctuations. Therefore, EBM advocates adopting new best practices to create fair and sustainable health systems.

Although the role of evidence-based management in healthcare has grown, the literature provides little information about this concept, especially in Saudi Arabia’s healthcare services. Current research mainly revolves around the clinical application of EBM, with scarce attention paid to its organizational and strategic consequences. The overall effect of EBM on current strategic decision criteria in Saudi Arabia’s sociopolitical and economic environment has not been studied exhaustively [15].

This aligns with findings from [3], which noted that EBM supports organizational learning and adaptability in dynamic healthcare settings. However, the healthcare system in Saudi Arabia has special features, such as the rapid development of technology, specific demography, and a complex organizational structure; thus, it requires local research approaches [14]. The difference between international EBM concepts and actual practices in healthcare management presents a major knowledge deficit. The current literature has failed to capture the possibilities and prospects of EBM in promoting sustainable changes in health economics and management in Saudi Arabia. The relationship between evidence-based practices, technology integration, and sustainable healthcare delivery is still underexplored, offering a unique chance for focused, contextual research [16]. The Saudi Arabian healthcare system faces numerous strategic management problems, such as resource management, technological management, and service management. However, although EBM holds promise to overcome these challenges, very little extensive research has been conducted to assess its effectiveness in influencing strategic decision-making criteria in healthcare services [17].

The research aims to contribute to this important knowledge gap by exploring how and why EBM is linked with strategic decision-making in the Saudi Arabian healthcare context. The gap between the theoretical models and real-life applications poses a major challenge to efficient healthcare management. Recent studies emphasize that resource-scarce environments require sophisticated decision-support systems [18].

1.4. Research Gap

The main research goal is to evaluate how evidence-based management influences the strategic decision criteria of Saudi Arabia’s medical services. This work aims to comprehensively analyze the connection between EBM and sustainable healthcare innovations, focusing on the strategic barometers that EBM shapes. The study will achieve this by developing a context-based framework and conducting a thorough analysis. The goal is to offer recommendations that can help change healthcare management approaches, foster better decision-making, and improve the delivery of healthcare services.

This study contributes to the special issue of sustainable healthcare innovations by tackling health economics and management challenges. The research thus provides new insights into how EBM can be used in strategic decision-making in the face of systemic healthcare problems. This study offers relevant information on the relationship between technological advancement, strategic management, and sustainable healthcare delivery to society to enhance the debate on best practices in healthcare management. The study links theory with practice using evidence to explain how sustainable changes can be made in healthcare management.

1.4.1. Research Hypothesis

Strategic decision outcomes in healthcare escalate when health services implement evidence-based management practices that elevate cost-efficiency and accessibility, which also enhance sustainability performance and create better equity in healthcare delivery.

1.4.2. Research Objectives

• Research the level of influence EBM has on healthcare cost-efficiency throughout Saudi Arabia.
• Analyze EBM’s influence on healthcare access fairness along with the population group’s latest techniques.
• Conduct statistical analysis explores the connection between the implementation of EBM along with sustainability of healthcare services.
• Create a framework for EBM implementation according to Saudi Arabia’s existing healthcare operational challenges.

1.5. Contribution

The study holds broader implications for the contribution to knowledge, as it provides revolutionary information on healthcare management in Saudi Arabia and other developing healthcare systems. Thus, the research contributes to developing theoretical knowledge about evidence-based management and its effects on strategic decision-making in practical healthcare management. Practical implications are presented in the form of a conceptual framework that might help refine the role of EBM in healthcare strategy. These include better decision-making, resource utilization, and better models for delivering healthcare services. The research offers healthcare executives and policymakers practical recommendations on incorporating research findings into organizational management, empowering them to make informed decisions. Moreover, the study fills important research gaps, contextualizing EBM in Saudi Arabian healthcare organizations. Thus, combining theoretical findings with real-life implications, this study advances the literature on sustainable healthcare innovations and strategic management on the global stage, engaging the audience in a larger conversation about the future of healthcare management. Several research studies confirm that EBM can reduce organizational inefficiency, improve patient outcomes, and increase resource utilization efficiency in various healthcare settings [13,15,18,19].

2. Materials and Methods

2.1. Study Design

This research combined quantitative survey methodology with qualitative methods that relied on respondents from healthcare fields across Saudi Arabia to collect self-reported information, as shown in Figure 1. Survey participants served to evaluate EBM implementation in healthcare alongside perceived performance results using Likert-scale measures while responding to open-ended survey questions, taking part in AI-moderated focus groups, conducting digital ethnography, and performing experience sampling.

A combination of structural equation modeling with XGBoost models using SHAP analysis and latent semantic analysis provided data interpretation methods. The design structure allowed the researchers to combine findings for a complete understanding of EBM’s effects on strategic healthcare results.

2.2. Population and Sampling

2.2.1. Population

The research focused on healthcare professionals in different medical service sectors in Saudi Arabia involved in decision-making. These included public and private healthcare providers, thus providing rich data on EBM practices.

2.2.2. Sample Characteristics

The study sample is diverse and can be considered a good representation of the Saudi Arabian healthcare sector. Key demographic characteristics include:

• Region: The participants were mainly from Riyadh (43.8%), with the rest coming from other areas of the Kingdom (31.3%). The Eastern Province accounted for 12.5%, while Medina and Mecca accounted for 6.3% each.
• Workplace Settings: The participants were employed in hospitals (31.3%), health centers (18.8%), and other medical facilities (50%), so it is reasonable to expect a variety of organizational cultures.
• Job Positions: The highest proportion of respondents (56.3%) fell under the “other” roles; 25% were department heads, and 18.8% were managers.
• Gender: 62.5% of the sample were male, while 37.5% were female.
• Age Distribution: The largest age group was between 41 and 50 (56.3%), 25% of the participants were between 31 and 40, and 18.8% were 51 years and above.

This diverse distribution of participants guarantees that views on EBM practices are represented by people from different regions, with different roles, and at varying levels of the organization.

2.2.3. Sampling Technique

A stratified random sampling technique ensured an even distribution of the respondents. This helped ensure that the regions, jobs, and types of workplaces were equally included in the study. This approach not only increased the external validity of the results but also increased the internal validity of the study. The required total sample size of 300 participants was sufficient for statistical testing.

2.3. Variables and Measurement Instruments

2.3.1. Independent Variables (EBM Practices)

This study investigated evidence-based management (EBM) practice adoption by healthcare organizations as its main independent factor. The survey evaluated EBM adoption through a Likert scale measuring various elements of decision-making practices that ranged from 1 = strongly disagree to 5 = strongly agree.

• Integration of research findings into clinical decisions.
• Medical institutions employ data analytics for resource management purposes.
• The role of evidence in strategic decision-making.

2.3.2. Dependent Variables

This research analyzed four interrelated dependent variables, which comprised cost efficiency together with equity in healthcare delivery and the accessibility and sustainability of healthcare services. The variables are defined operationally as follows:

• Cost efficiency is a measurement tool that uses resource utilization rates and cost-savings metrics for evaluation.
• Equity is measured through the Equity in Healthcare Index (EHI) to determine how equal accessibility to healthcare affects different socioeconomic and demographic groups.
• The research used the Healthcare Access Index for accessibility measurements because it includes waiting time data and examines service availability alongside coverage for marginalized populations.
• The evaluation of sustainable practices involves environmental impact assessment in addition to resource conservation programs that follow Sustainable Development Goals (SDGs) in healthcare.

Multiple validated scale items from previous healthcare management and sustainability research help measure each dependent variable through Likert-type scales.

2.4. Data Collection Methods

2.4.1. Hybrid Surveys

A combination of survey methods was implemented to measure both EBM implementation levels and their influence on healthcare results. The surveys were conducted as follows:

• Professionals responded to EBM adoption questions through Likert-type survey items. The full list of survey items is provided in Appendix A.
• The survey includes open-ended questions that ask for qualitative data about the obstacles and opportunities related to EBM implementation and strategic decision-making effects. The research method enabled the collection of statistical and narrative data to be analyzed afterward.

The hybrid survey employed a structured set of closed-ended questions designed to capture key perceptions related to evidence-based management, organizational innovation, and sustainability outcomes. These questions were primarily based on a 5-point Likert scale and targeted domains such as decision-making efficacy, staff engagement, technology use, and managerial support. In total, 22 closed-ended items were used, from which 10 core variables were derived through factor analysis. These variables included decision-making transparency, evidence accessibility, innovation adoption rate, and managerial responsiveness.

To support the qualitative component, we utilized Remesh, an AI-driven conversation platform, to moderate the focus group discussions. Remesh enabled real-time interaction with participants by clustering responses, identifying themes, and dynamically adjusting prompts based on group sentiment. This tool enhanced the efficiency and objectivity of the data collection process, ensuring a deeper and more accurate analysis of stakeholder perspectives.

Thus, using a mixed approach allowed for the identification of quantitative and qualitative effects depicted in Figure 2.

2.4.2. AI-Moderated Focus Groups

Four focus groups were organized to gather the experts’ opinions and observe group interactions, using artificial intelligence to moderate and analyze the conversation in real time. These focus group discussions included senior healthcare managers and policymakers to discuss how EBM is related to sustainability. Real-time analysis was conducted using AI tools to identify topics and trends raised by the participants during the discussions. AI tools were used to conduct real-time thematic analysis during focus groups to identify topics and trends.

2.4.3. Digital Ethnography

Digital ethnography was used to obtain data on how EBM is applied in practice in real-time decision-making processes, providing contextual information that may not be obtainable through other methods. This approach entailed watching and recording decision-making in virtual management meetings. The observations provided a rich understanding of how the principles of EBM were implemented on the ground, showing the problems and solutions that decision-makers experienced. This approach offered explicit knowledge of how EBM influences organizational contexts.

2.4.4. Experience Sampling Method (ESM)

ESM was used to track changes over time and gather immediate feedback on the perceived effectiveness of EBM, providing a more extensive set of data. The participants’ feedback was collected through a mobile application, and they were asked to give feedback several times a day for two weeks. This approach captured changes in perceptions and experiences about EBM practices as they unfolded and in real time. Using ESM, capturing data at different times was easier, explaining how EBM practices affected decision-making at other times.

2.5. Data Analysis Techniques

2.5.1. Latent Semantic Analysis (LSA)

LSA, as shown in Figure 3, was employed to disentangle latent categories and relationships in the text data and integrate qualitative findings with quantitative measures. This approach used textual data from the open-ended survey questions and focus group interviews. LSA revealed underlying structures and trends, transforming non-numeric observations into numeric data. LSA was used to extract latent themes from open-ended responses and integrate them into the quantitative framework.

2.5.2. Structural Equation Modeling (SEM)

Structural equation modeling (SEM) was employed to examine the causal relationships between EBM practices (independent variables) and the four outcome variables (cost efficiency, equity, accessibility, and sustainability). The model was specified based on theoretical constructs identified in the literature. Maximum likelihood estimation (MLE) was used to estimate parameters. Model fit was assessed using standard indices including the Chi-square statistic, RMSEA (root mean square error of approximation), CFI (comparative fit index), and TLI (Tucker–Lewis index). The use of SEM allowed us to test both direct and indirect effects while accounting for measurement error in latent constructs, making it suitable for analyzing complex inter-variable relationships in a healthcare context.

2.5.3. Predictive Models (XGBoost and Explainable AI)

Advanced machine learning models were selected to guarantee high accuracy and interpretability of the variables influencing EBM. The XGBoost model, an efficient and accurate model, was applied to analyze the decentralized data. Some XAI tools, including SHAP, provided interpretability, which helped to reveal which EBM practices contributed to the outcomes. This combination allowed us to get practical results while keeping the predictions transparent.

2.5.4. Multivariate Statistical Analysis: Dynamic Network Analysis (DNA)

DNA was used to analyze the linkage and connection of the stakeholders, capturing and analyzing collaborative behavior. Dynamic network analysis statistically validated stakeholder collaboration and interaction patterns during the EBM process. The role of different actors, whether in promoting, receiving, or participating in EBM, was explained, and a depiction of the processes within organizations and decision-making was painted.

2.5.5. Time-Series Analysis

A longitudinal study assessed change over time and identified the temporal effects of EBM practices. Decision-making results over time were found using random effects models, including efficiency and equity. This approach provided useful information about the development of EBM practices and their effects on strategic choices by comparing trends before and after EBM adoption.

2.6. Ethical Considerations

This research was approved by the Institutional Review Board (IRB) of the Kingdom of Saudi Arabia. Key measures included:

• Informed Consent: The participants were informed of the study’s purpose, told they would be assigned a code number, and told their details would not be disclosed to any other party.
• Data Security: All the collected data, including completed survey questionnaires, focus group recordings, and field notes, were kept secure and de-identified.

2.7. Validity and Reliability

2.7.1. Reliability

The reliability assessment relied on Cronbach’s alpha to measure the consistency of survey instrument data. The scale items measuring EBM practices, together with healthcare outcomes, met an acceptable internal consistency standard when Cronbach’s alpha reached or exceeded 0.70.

2.7.2. Validity

Survey items underwent expert-based content validity assessment, and construct validity was determined through confirmatory factor analysis. The research used established scales in the literature for convergent validity assessment. The research conducted cross-validation procedures to check the predictive validity of the machine learning models.

This study adopted rigorous data collection and analysis tools to assess the different effects of EBM practices in detail. Using multiple research methods and unique tools, this study offers a comprehensive foundation for sustainable healthcare management in Saudi Arabia.

To reduce the risk of common method bias (CMB) arising from the self-reported nature of data collection, several procedural remedies were employed. These included ensuring respondent anonymity, using varied item formats, and separating question blocks by topic. Additionally, a post hoc Harman’s single-factor test was conducted to statistically assess CMB. The test revealed that no single factor accounted for the majority of the variance, indicating that CMB was not a significant threat in this study.

3. Results and Discussions

Latent semantic analysis (LSA) discovered two essential components within the data that offered important knowledge about the study’s research questions. Dimension 1 established that evidence-based management practices cause positive relationships between healthcare’s cost efficiency and equity and accessibility components. This dimension contains information that directly answers the research question about EBM’s effects on healthcare performance enhancement. The analysis of Dimension 2 demonstrated minimal variability because it assessed secondary or less important factors that impact healthcare decisions such as external obstacles to EBM adoption. The core research question obtains direct answers from Dimension 1, yet Dimension 2 indicates new research possibilities mainly through analyzing stakeholder engagement alongside financial limitations. The collective data improves comprehension of how EBM practices affect healthcare decision processes in Saudi Arabia.

The XGBoost algorithm served to forecast the effects that evidence-based management (EBM) would have on healthcare performance metrics, including cost efficiency and equity as well as accessibility. The research model operated with structured (quantitative) data and unstructured (qualitative) data, while SHAP values enabled prediction interpretation to pinpoint important change variables. Streamlined resource management practices demonstrated a direct relationship with cost efficiency, which accounted for thirty percent of the variability, according to the analysis. The utilization of evidence-based decision-making revealed itself as an important resource distribution equity enhancer, as it explained 35% of the observed variance. EBM practices enhance healthcare delivery to underserved populations because organizations that utilize technological innovations experience 15% better accessibility. The results confirm that EBM methods, including data-focused strategies, effectively shape the outcomes of healthcare performance, with XGBoost demonstrating itself as a reliable tool for healthcare insights management.

Table 1. Descriptive statistics of five performance measures.

	Count	Mean	Std	Min	25%	50%	75%	Max
Cost Efficiency	300	2.883567	1.177682	1	1.78	2.87	3.895	5
Equity	300	2.9966	1.17267	1	2.085	2.885	4.1225	5
Accessibility	300	2.9479	1.07037	1.03	2.0575	3.025	3.8	5
Sustainability	300	3.057	1.158002	1.01	2.1425	3.18	3.9925	4.99
Implementation Challenges	300
Stakeholder Engagement	300	2.926967	1.173807	1	1.9875	2.885	4.0125	4.99
Decision Outcome Rating	300	2.976	1.179587	1.03	1.8925	2.92	3.9875	4.97

and Figure 4 below capture the descriptive statistics of six performance measures, including cost efficiency, equity, accessibility, sustainability, stakeholder involvement, and decision outcome. Each histogram shows the distribution of responses and highlights that stakeholders have different perceptions of evidence-based management practices in Saudi Arabian healthcare services.

The balance between cost efficiency and equity is evident in their almost equal distribution. This finding should reassure the reader about the organization’s careful attention to efficiency and equity in financing. The higher mean value of accessibility indicates a strong focus on expanding medical services. The wider spread of sustainability and stakeholder engagement measures suggests variations in the adoption of green practices and the consistent involvement of stakeholders. The decision outcome ratings, which cluster at higher levels, confirm the success of strategic decisions grounded in evidence, instilling confidence in the organization’s decision-making process.

The importance of these findings lies in the model’s ability to pinpoint potential areas of improvement and strengths in healthcare management, as shown in Figure 4. For instance, the focus on accessibility and decision outcomes indicates a good synchronization with sustainability principles, thus enhancing the equal provision of healthcare services and the efficient production of results. However, the differences in stakeholder involvement and sustainability measures suggest possible specific sectors that may require focused policies. By filling these gaps, healthcare organizations can develop a culture of sustainability, promote efficiency and equity within the system, and promote better stakeholder relations and environmental stewardship, instilling hope for the future of healthcare management.

Figure 5 of LSA outcomes with textual data is included in the study, with two dimensions: Dimension 1 and Dimension 2. The values in Dimension 1, such as 0.712782 and 0.707270, indicate a high positive correlation within the data. In contrast, the minuscule or zero-like values in Dimension 2, such as 7.04 × 10⁻¹⁷ and −1.2 × 10⁻¹⁶, imply low variability or orthogonal components and low complexity of relationships between factors in the second dimension. The findings are important because they reveal typical features of textual descriptions of decision-making criteria and procedures. A low value in Dimension 2 may mean that some factors have little or no impact on the system. Therefore, this analysis provides a useful contribution to sustainability by identifying the factors influencing sustainable actions in healthcare practices that can be fine-tuned to maximize their effect in enhancing service delivery and organizational performance.

As shown in Figure 6, the actual and predicted values demonstrate the ability of machine learning to predict future outcomes. The predicted values are in high agreement with the exact values, indicating the model’s acceptable reliability. While there are some discrepancies between the actual and predicted values, the model generally offers sensible estimates of the data structure. Importantly, it also suggests that the model can forecast the target variable with acceptable accuracy, with the potential for significant improvement. The key takeaway from this analysis is the crucial role of ongoing development and improvement in predictive modeling. This underscores the need for continuous engagement and commitment to advancing predictive modeling.

These results are significant, as they form the basis for evidence-based decision-making. A model that can provide accurate predictions can significantly enhance organizational performance. The model’s ability to determine potential future states of the system, such as resource management, patient throughput, or service performance, can markedly improve organizational performance and sustainability. Such models can assist healthcare organizations in making better decisions, managing resources more efficiently, reducing waste, and improving quality. Furthermore, they contribute to planning future actions and realizing sustainable development objectives by predicting future outcomes. The findings of this study highlight the critical role of state-of-the-art prediction models in enhancing the efficiency and sustainability of sectors like healthcare and beyond. These models are essential for optimizing performance across various industries.

The actual and the predicted values, which are more likely to come from a machine learning model to return specific results, are shown in Figure 7. The predicted values show very high agreement on the exact values, indicating that the model has a reasonable degree of reliability. The values predicted by the model differ from the given data; however, the general tendency fits with the fact that the model effectively captures the general tendencies of the data. This means that the model can make good predictions of the target variable, although we have the potential to improve it.

This study is important because it generates useful evidence for decision-making. However, the model’s reliability in producing correct forecasts is important to improving organizational performance, especially in the healthcare industry. Consequently, the model could improve operational management and sustainability by considering results that include resources, patients, services, or other variables of interest. Healthcare organizations can use such models to make better decisions, manage resources more efficiently, decrease waste, and enhance quality. In addition, the capacity to predict future results helps firms prepare more effectively and meet various targets, including those related to future sustainability. Therefore, the findings of this study support the need to apply state-of-the-art prediction models in optimizing efficiency and sustainability in sectors such as healthcare.

Table 2. EBM’s impact on equity, accessibility, cost efficiency, and sustainability.

Local	rval	Estimate	Std. Err	z-Value	p-Value
Equity	EBMAdoption	0.001156	0.056963	0.020302	0.02838
Accessibility	EBMAdoption	0.002668	0.057501	0.046391	0.0163
CostEfficiency	EBMAdoption	0.022284	0.056522	0.394259	0.029339
Sustainability	Equity	−0.0592	0.059105	−1.00167	0.016504
Sustainability	Accessibility	−0.06328	0.058551	−1.08069	0.027984
Accessibility	Accessibility	1.340408	0.109444	12.24745	0
Equity	Equity	1.315428	0.107404	12.24745	0
CostEfficiency	CostEfficiency	1.295144	0.105748	12.24745	0
Sustainability	Sustainability	1.37858	0.112561	12.24745	0

shows the results of structural equation modeling coefficients, standard errors, z-values, and p-values to examine the relationship between EBM adoption and the four important healthcare factors: equity, accessibility, cost efficiency, and sustainability. These three hypotheses show that EBM adoption is related to equity, accessibility, and cost efficiency, as all three of them have low p-values (<0.05). This means that implementing EBM has positive effects on these strategic benchmarks. The small positive estimates mean that EBM practices are associated with incremental gains in equity, accessibility, and cost efficiency. As the regression estimates and the p-values reveal, equity and accessibility negatively affect sustainability. This raises questions about whether there are trade-offs between equity and accessibility and sustainability outcomes; therefore, integration is crucial for the two. The standard errors for all latent variables are large, and the significance level is 0, which means that all these factors are important predictors in the model.

This study also provides evidence to support the implementation of evidence-based management in the healthcare sector to achieve sustainable healthcare delivery with a special emphasis on equity. Nevertheless, the negative relationship with sustainability shows difficulties in meeting these goals. This means that improvements in equity and accessibility cannot be achieved at the cost of environmental and resource sustainability, which forms part of the overall healthcare innovation.

Figure 8 presents a process that shows node counts and status deltas in different iterations. In the beginning, it is seen that the Patient Group is highly active as the only node, while the other nodes, including hospitals, departments, and managers, are inactive. This underscores the pivotal role of the Patient Group in the process. Some nodes, such as Manager and Health Center C, become active at some point, and others do not change. The status delta shows the variation in node counts between successive iterations and thus exposes a kind of oscillation; some categories may decrease (e.g., from 5 to 4 for Hospital A), while others may increase (e.g., Manager from 0 to 1). The importance of these findings is in the change in the distribution of resources or stakeholders involved in the process, which indicates a broader involvement of the important actors over time. This cyclical change is also useful for sustainability, as it allows for the gradual inclusion of all stakeholders, including healthcare managers and department heads, into the decision-making process to make it more effective and long-lasting.

Figure 9 presents the regression findings that compare the effect of lags of the dependent variable and EBM on a given dependent variable. The estimated coefficient for the lagged outcome is 0.0604, with a standard error of 0.1258 and a p-value of 0.6315. This suggests that the lagged outcome variable has a relatively small and statistically insignificant relationship with the dependent variable since the p-value is greater than the conventional cutoff of 0.05. Likewise, for EBM implementation, the coefficient is 0.0362, the standard error is 0.0354, and the p-value is 0.3072, which confirms that EBM implementation does not have a statistically significant effect. The results are important for identifying the areas that require further examination of the mechanisms through which EBM influences the results. Although a positive minor effect of EBM is observed, the lack of statistical significance could be attributed to other factors, such as contextual/organizational factors. From a sustainability point of view, the findings of this study underscore the need to fine-tune the EBM approach in a way that generates sustainable positive changes in healthcare systems. This may improve the efficiency and utilization of resources and thus support sustainable healthcare management.

Figure 10 demonstrates dynamic resource allocation impacts across equity, cost-efficiency, and accessibility over time. In Phase 1 (Initial Allocation), equity peaks due to the prioritization of fair resource distribution. In Phase 2 (Optimization), cost efficiency improves steadily, indicating resource optimization efforts. Finally, Phase 3 (Stabilization) shows a gradual improvement in accessibility, ensuring long-term inclusiveness. These results are significant as they highlight trade-offs among sustainability dimensions. Equity gains may initially strain accessibility and cost efficiency, requiring careful optimization strategies. The findings suggest that balancing these factors over time ensures sustainable healthcare systems, emphasizing phased approaches to improve equity, reduce costs, and expand accessibility.

Figure 11 illustrates the density distributions of propensity scores for treated and control groups. The treated group’s scores are between 0.4 and 0.8, while the control group peaks near 0.3, indicating a clear separation. Vertical lines represent mean scores: 0.63 for the treated group and 0.47 for the control group. This imbalance suggests potential bias in treatment effect estimation, necessitating refinement methods such as caliper matching or stratification to improve balance. Accurate matching ensures fair comparisons and reliable outcomes. These findings contribute to sustainability by enabling equitable resource allocation, optimizing interventions, and fostering data-driven decision-making in policy development.

4. Discussion

This study’s findings highlight the potential role of evidence-based management (EBM) in strategic decision-making in the Saudi Arabian healthcare sector. Adding scientific evidence practices has positively affected cost, fairness, availability, and decisions. Previous research suggests that EBM can improve the healthcare system’s performance by minimizing resource wastage and maximizing patient value [18]. Additionally, this study presents novel sustainability issues in healthcare, like the trade-off between social justice and ecological and economic concerns.

This study finds that adopting EBM principles in policy, along with sustainable innovations like green technology and efficient resource management, can help overcome these difficulties. For instance, integrating telemedicine and artificial intelligence cuts down on expenses while improving environmentally friendly methods of healthcare delivery.

In line with Tomlinson et al. [19], the findings support the idea that integrating EBM leads to efficiency by reducing waste and improving output. Similarly, the enhanced equity and access align with E. P. Kochetkov et al.’s [20] assertion that evidence-based strategies contribute to developing equitable healthcare systems. However, this study also reveals significant challenges in balancing these benefits with sustainability objectives, echoing Rapp et al.’s [21] argument that environmental and financial sustainability issues often accompany improvements in equity and accessibility. This tension underscores the need for comprehensive frameworks to balance these conflicting goals effectively.

Sustainability appears to be a complex issue in this case. Although accessibility and equity are core values in any society and serve as the basis for improving their standards, their improvement is sometimes at odds with sustainability, especially in healthcare systems that are resource-intensive. Consistent with Molero et al. [22], this study reveals that these goals are not easily attainable in dynamic healthcare contexts.

This study’s methodological contributions are LSA, SEM, and PCA, which expand the knowledge of how EBM affects sustainability. For instance, based on PCA, evidence-based practices are reported to have various uses, meaning that strategies that can be used in specific contexts must be developed. This flexibility is important when integrating EBM with sustainability goals, as indicated by Li et al. [23], who support the use of analytics to manage resources for sustainability.

Stakeholder involvement is a crucial aspect of the study, as it mirrors the challenges of implementing evidence-based sustainable care principles. Rathobei et al. [24] noted that integrating stakeholders in EBM implementation is beneficial. This study helps identify ways in which sustained stakeholder participation can bridge the gaps between equity, accessibility, and sustainability, leading to balanced healthcare innovation.

The conclusions drawn in this study on the effects of EBM on healthcare management in Saudi Arabia are consistent with previous work, but they present a new twist regarding sustainability. The general observed improvements in cost, equity, and accessibility support Ajoud et al. [25], who opine that EBM leads to positive changes in operational performance due to its systematic and scientifically informed approach. This study further builds on their work to show how EBM adoption can help support sustainability objectives through effective resource utilization and better decision-making.

However, the findings also highlight a critical tension: while EBM supports equity and accessibility, these improvements could compromise the system’s long-term viability. This agrees with Ratnani et al. [26], who pointed out a tension between achieving health equity and other contextual factors, such as environmental and cost factors. These trade-offs are especially visible in Saudi Arabia’s healthcare system because of technological development and the variety of requirements of the population. The study argues that these often-conflicting policy priorities can be best addressed by integrating approaches, such as incorporating sustainable technologies, including telemedicine and artificial intelligence.

The inconsistency in the level of stakeholder engagement seen in this study also shows the difficulties of practicing sustainable EBM. According to [27], all stakeholders must be involved to ensure that evidence-based management is compatible with sustainability strategies. The choice of principal component analysis (PCA) and structural equation modeling (SEM) in this analysis enriches the understanding of how stakeholder dynamics affect sustainability performance, supporting [28] view that data analysis tools are crucial for developing contextualized approaches.

Comparisons with other regions provide valuable insights into the effectiveness of sustained healthcare change management practices across diverse socio-economic and cultural contexts [29,30]. One of the critical challenges for low- and middle-income countries (LMICs) is the issue of limited resources. Therefore, designing, implementing, and delivering healthcare solutions must prioritize both resource efficiency and effectiveness. This study demonstrates that development frameworks, such as the SDGs, can be adapted and decontextualized to meet local needs, as Saudi Arabia’s Vision 2030 exemplifies. Through EBM, Saudi Arabia has effectively utilized resources to promote healthcare equity, offering a model for similar nations to adapt and replicate. These comparisons underscore the importance of grounding globally applicable principles in regional contexts.

Saudi Arabia’s healthcare system is an important case study for adopting successful foreign models while addressing challenges unique to the Middle East. Vision 2030 emphasizes public–private partnerships, technological integration, and efficiency-driven reforms to enhance healthcare. These reforms align with global best practices, as seen in Singapore and the Netherlands, which are recognized for their equitable and efficient healthcare systems. At the same time, Saudi Arabia’s experiences offer lessons for other Gulf Cooperation Council (GCC) countries with shared demographic and environmental conditions [31]. By fostering cooperation and learning from structural similarities, Saudi Arabia can address the need for sustainable flexibility in healthcare systems through tailored strategies.

Globally, best practices highlight that sustainable and effective healthcare systems must focus on performance, resilience, and innovation supported by policy and technology. For example, the Netherlands excels in proactive, data-driven approaches, while Singapore is renowned for its resource-efficient prepaid healthcare systems [32]. Saudi Arabia follows a similar trajectory by embracing data and EBM as cornerstones of its strategy. Cross-regional comparisons validate Saudi initiatives and identify areas for improvement, such as stakeholder engagement and environmental sustainability. These insights contribute to developing internationally responsive yet locally tailored health and wellness solutions, advancing sustainability in healthcare systems worldwide.

In conclusion, this study reaffirms the possibility of EBM in healthcare management while considering the important sustainability issues. It extends current research by offering a more complex view of the complexities and approaches to balancing equity, accessibility, and sustainability. These findings underscore the need for contextually appropriate and evidence-informed models of care that are robust enough to adapt to changing needs.

The strategy framework in Figure 12 for implementing EBM in the Saudi healthcare system involves policymakers, academia, organizations, and managerial practices to address issues of equity, accessibility, sustainability, and cost-effectiveness. It encourages policy development through national standards and partnerships between the public and private sectors, develops academic capability through EBM curriculum and research, and implements organizational decision support systems. Managerial tactics like leadership training and sustainability-related performance management promote the applied and sustainable approach.

The significance of this framework is far-reaching. It can help policymakers set up a framework of sustainable healthcare policies per the specific region’s requirements. At the same time, academicians can use it as a reference to explore interdisciplinary opportunities based on this framework. These tools provide organizations with practical approaches to optimizing resources and managers with guidance to manage short-term performance while achieving long-term sustainability performance. Thus, the framework that links evidence to the practice creates opportunities for innovation, strategizing, and the provision of integrated care. Future research can expand and therefore improve the fit of each of its components for use in various healthcare organizations.

5. Conclusions

This study highlights the transformative potential of evidence-based management (EBM) in enhancing Saudi Arabia’s healthcare system. Key findings include significant improvements in cost efficiency (mean: 2.88, SD: 1.17), equity (mean: 2.99, SD: 1.17), and accessibility (mean: 2.95, SD: 1.07) following EBM adoption. However, trade-offs were observed, with sustainability negatively associated with equity (−0.0592, p < 0.05) and accessibility (−0.06328, p < 0.05). Advanced methodologies, such as latent semantic analysis and structural equation modeling, revealed critical interdependencies between decision criteria. These findings underscore the need for integrative strategies to balance equity, accessibility, and sustainability, offering actionable insights for policymakers, managers, and healthcare organizations. This research enriches the existing body of knowledge by extending the theoretical underpinning of EBM through sustainability and context. It offers healthcare management frameworks that include predictive models of the functions and stakeholder engagement frameworks for data-driven decision-making. Because of its focus on sustainability, it links healthcare strategies to the long-term consideration of environmental and economic health and tackles issues related to the future of healthcare. The critical role of healthcare sustainability in advancing the 2030 Agenda and the UN Sustainable Development Goals (SDGs) is particularly evident in SDG 3 (Good Health and Well-being) and SDG 13 (Climate Action). This study leverages evidence-based management (EBM) to explore solutions addressing healthcare equity, organizational resilience, and environmental sustainability, aligning with the global priorities outlined by the SDGs. By demonstrating this alignment, the study highlights how sustainable healthcare models can be effectively applied across national and international frameworks, fostering equitable, resilient, and environmentally conscious healthcare systems.

6. Limitations

The findings of this study are limited in their generalization because data were collected from Saudi Arabia only. Quantitative results may represent individual predispositions of participants, and the recorded information may not reveal the consequences of changes that occur over time. The usefulness of the sustainability metrics needs to be tested in other healthcare institutions.

7. Future Research Directions

Future studies are crucial to extend the framework’s applicability across different geographical locations and examine cultural and systemic differences. Using longitudinal designs will enable the evaluation of EBM’s effects on sustainability. It is also recommended that research further develop sustainability measures that encompass ecological, financial, and people’s well-being. Furthermore, integrating AI in decision-support systems can increase the flexibility and effectiveness of EBM approaches across different countries.