Decision Strategies Research Articles

Unraveling nonlinear effects of environment features on green view index using multiple data sources and explainable machine learning

Urban greening plays a crucial role in maintaining environmental sustainability and enhancing people’s well-being. However, limited by the shortcomings of traditional methods, studying the heterogeneity and nonlinearity between environmental factors and green view index (GVI) still faces many challenges. To address the concerns of nonlinearity, spatial heterogeneity, and interpretability, an interpretable spatial machine learning framework incorporating the Geographically Weighted Random Forest (GWRF) model and the SHapley Additive exPlanation (Shap) model is proposed in this paper. In this paper, we combine multi-source big data, such as Baidu Street View data and remote sensing images, and utilize semantic segmentation models and geographic data processing techniques to study the global and local interpretation of the Beijing region with GVI as the key indicator. Our research results show that: (1) Within the Sixth Ring Road of Beijing, GVI shows significant spatial clustering phenomenon and positive correlation linkage, and at the same time exhibits significant spatial differences; (2) Among many environmental variables, the increase of green coverage rate has the most significant positive effect on GVI, while the increase of building density shows a strong negative correlation with GVI; (3) The performance of the GWRF model in predicting GVI is excellent and far exceeds that of comparison models.; (4) Whether it is the green coverage rate, urban built environment or socioeconomic factors, their influence on GVI shows non-linear characteristics and a certain threshold effect. With the help of these non-linear influences and explicit threshold effects, quantitative analyses of greening are provided, which can help to assist urban planners in making more scientific and rational decisions when allocating greening resources.

Bayesian Decision Curve Analysis With Bayesdca

ABSTRACTClinical decisions are often guided by clinical prediction models or diagnostic tests. Decision curve analysis (DCA) combines classical assessment of predictive performance with the consequences of using these strategies for clinical decision‐making. In DCA, the best decision strategy is the one that maximizes the net benefit: the net number of true positives (or negatives) provided by a given strategy. Here, we employ Bayesian approaches to DCA, addressing four fundamental concerns when evaluating clinical decision strategies: (i) which strategies are clinically useful, (ii) what is the best available decision strategy, (iii) which of two competing strategies is better, and (iv) what is the expected net benefit loss associated with the current level of uncertainty. While often consistent with frequentist point estimates, fully Bayesian DCA allows for an intuitive probabilistic interpretation framework and the incorporation of prior evidence. We evaluate the methods using simulation and provide a comprehensive case study. Software implementation is available in the bayesDCA R package. Ultimately, the Bayesian DCA workflow may help clinicians and health policymakers adopt better‐informed decisions.

Collective effect of self-learning and social learning on language dynamics: a naming game approach in social networks.

Linguistic rules form the cornerstone of human communication, enabling people to understand and interact with one another effectively. However, there are always irregular exceptions to regular rules, with one of the most notable being the past tense of verbs in English. In this work, a naming game approach is developed to investigate the collective effect of social behaviours on language dynamics, which encompasses social learning, self-learning with preference and forgetting due to memory constraints. Two features that pertain to individuals' influential ability and affinity are introduced to assess an individual's role of social influence and discount the information they communicate in the Bayesian inference-based social learning model. Our findings suggest that network heterogeneity and community structure significantly impact language dynamics, as evidenced in synthetic and real-world networks. Furthermore, self-learning significantly enhances the process of language regularization, while forgetting has a relatively minor impact. The results highlight the substantial influence of network structure and social behaviours on the transition of opinions, from consensus to polarization, demonstrating its importance in language dynamics. This work sheds new light on how individual learners adopt language rules through the lenses of complexity science and decision science, advancing our understanding of language dynamics.

Restoration and evaluation for severed streams in high-density urban areas based on a multi-objective framework: A case study of Heping Stream in Nanjing

Numerous severed streams that emerge during rapid urbanization has been negatively impacting regional water systems and urban environments. Traditional restoration efforts are prone to focus on water quality, overlooking the complex of urban severed stream as natural-social ecosystems. However, current literature indicates a lack of systematic restoration methods and post-implementation evaluations tailored to severed streams, which adversely affects water resource management and sustainable urban development. This study bases on research of the severed streams in Nanjing’s Hexi New District to develop methods for the restoration and evaluation of severed streams in high-density urban areas. Taking the Heping Stream as a case study, it took three years to complete a full-process study encompassing the design, implementation, and post-occupancy evaluation of the restoration of the severed stream. We developed a multi-objective framework, including five measures for the restoration of severed streams, along with performance evaluation indicators from environmental, social, and economic perspectives to compare the state of the severed-stream before and after the restoration. So as to assess the effectiveness of the restoration methods and to put forward suggestions for the improvement of the restoration measures. The results showed that the method had a positive effect on the quality of the water environment, public evaluation, capital investment and energy consumption. Some of the environmental performance indicators were significantly improved after the restoration, especially the dissolved oxygen content, water flow. Most of the social performance indicators were better after the restoration than before. In terms of economic performance indicators, the use of photovoltaic energy resulted in significant savings in electricity and pumping costs. Performance evaluation confirmed comprehensive benefits of the method, with Run off Control, Waterfalls Construction and Riverbank Ecological Restoration being most effective. To improve the benefits of restoration, diverse strategies should be combined together, including runoff control, artificial wetlands, vegetated buffers, and riverbank restoration. This research can support the optimization of future restoration measures and scientific decision-making in urban severed-stream restoration.

Landslide susceptibility evaluation and determination of critical influencing factors in eastern Sichuan mountainous area, China

Landslide susceptibility evaluation and determination of critical influencing factors is a prerequisite for preventing hazardous risks, especially in landslide-prone mountainous areas. However, in densely vegetated Southwest mountainous areas, identifying assessment approach of shallow landslides susceptibility and their major inducing factors is still a huge challenge. To address this challenge, we applied five advanced machine learning models (Logistic Regression Model, Generalized Additive Model, Random Forest Model, Support Vector Machine Model, Artificial Neural Network Model) to assess the spatial distribution of shallow landslide susceptibility, considering several relevant factors that affect landslide occurrence. These factors include geological, topographic and vegetation factors, as well as four new vegetation factors: stock volume, stand density, average tree age, and stand types. Furthermore, we employed SHAP algorithm and Structural Equation Models to quantify the relative importance and explanatory power of these factors on shallow landslide susceptibility and to clarify the interaction mechanisms among various factors in Huaying Mountain. The results shown that Random Forest Model proves to be the most accurate (95.1 %) in assessing the spatial distribution of shallow landslides susceptibility, followed by the Artificial Neural Network model (78.6 %), the Support Vector Machine model (69.8 %), the Generalized additive model (68.1 %) and the Logistic Regression model (67.6 %).The area with high susceptible landslide possibility was 25.3 km2 occupying 14.8 % of the study region, it is mainly distributed in the west of Tianchi Lake, southeast of Huaying City and west of the study area, along with Xiangyu Railway. Geographical environment and vegetation features were found to significantly explain 67.4 % and 32.6 % of the total effects in shallow landslides susceptibility, respectively. Specifically, the spatial distribution of shallow landslides susceptibility were primarily influenced by geological engineering rock group, distance to faults、stand types and distance to river. Geographical environment factors could indirectly affect changes in vegetation features, thereby indirectly affecting the spatial distribution of shallow landslides susceptibility. Findings from this research could be helpful for scientific decision-making and technical assistance for early warning, prevention, and control of rainstorm-induced landslides in highly vegetation covered areas.

Chaos Theory and Garbage Can Model as Effective Strategies for Decision Making in Educational Institutions

Chaos is explained as complexity, instability, unpredictability, nonlinearity, and in the trash can model, conflicts, restrictions, differences, dynamic environment, instability of participation, complex organizations, and unstable conditions have importance. The garbage can model explains this tendency in organizations that often experience very high degrees of uncertainty. The aim of the current study is to discuss how the manager can benefit from the trash can model within the framework of their proactive personality in cases of chaos that may occur during the education management process. A case study design from qualitative research methods was used in the study. The research data were obtained, analyzed, evaluated and interpreted with the document analysis technique. The literature on chaos theory and the garbage can model used in administrative decision-making was systematically examined and synthesized. In general, the question sought to be answered is how education and school systems can effectively manage chaos and complexity. Thus, a new and different understanding and perspective will be tried to be created for effective school management. Within the scope of the current research, the following suggestions can be offered to education administrators: Creating a simple and flexible organization and organizational structure, giving importance to the detection of pre-learning and experiences (cognitive, emotional, motor, social aspects) in individuals, the need for education and school administrators to be proactive and behave accordingly. As a result, in school improvement efforts, despite linear organizational charts and development plans, schools are not linear but chaotic systems. This situation brings about the fact that schools cannot be managed from the top. Also, plans in schools should be short-term (1-2 years) rather than long-term (5-10 years) and should focus on the process rather than the product.

Study on Territorial Spatial Equilibrium Based on Ecosystem Service Value: A Case Study of the Southwest Guangxi Karst‐Beibu Gulf, China

ABSTRACTExploring the regional territorial spatial equilibrium state (TSES) has emerged as a key goal of “Two Mountains” planning and decision‐making, as well as territorial spatial governance. However, there is still a shortage of perspectives that consider the ecosystem service value (ESV) to reveal and predict TSES. To this end, this study develops a framework for analyzing the interaction between ESV and socio‐economic value (SEV), investigates the pattern, process, and mechanism of their interaction employing spatial equilibrium model, and couples the MOP‐PLUS model to predict the interaction between the two under different scenarios, in order to fill in the gaps of the current research. The results show that: (1) From 1980 to 2020, the ESV (decreasing trend) and SEV (increasing trend) in the Southwest Guangxi Karst‐Beibu Gulf (SGK‐BG) show opposite trends and distribution patterns. Under all three simulated projection scenarios, the projected ESV of SGK‐BG in 2030 shows different degrees of decreases, with economic development leading to the greatest fluctuations in the rate of decrease; the implementation of an ecological protection strategy leads to a small decrease in the SEV, and vice versa. (2) The TSE for coordinated equilibrium state (CES) districts and counties are mainly clustered in the GSK region, with the number in 2020 increasing by 30% compared to 1980; the ecological imbalance state (EIS) areas are mainly located in the central part of the study area and some districts along the coast of the Beibu Gulf, and the developmental imbalance state (DIS) areas are located in the northwestern part of the study area. The above three TSES have the highest number of distributions in the business as usual scenario (BAUS), the economic development first scenario (EDFS), and the ecological conservation first scenario (ECFS), respectively. The above differences in different spatial equilibriums reveal a serious developmental imbalance between economic development and ecological conservation. This study emphasizes the pathways evolution of different equilibrium subregions under the realization of ESV, and the evaluation results are not only a useful supplement to the research on the “Two Mountains” theory, but also can help policymakers to provide scientific decisions in promoting the synergistic, equilibrium and orderly development of the region.

Path Analysis of Recycling of Urban Solid Waste Based on Multi-Objective Optimization Model

With the acceleration of urbanization and rapid economic development, the problem of urban solid waste (SW) has become increasingly prominent. Traditional SW disposal treatment methods, mainly landfill and incineration, pose issues of environmental pollution and resource waste. This study aims to analyze the recycling pathways of urban SW and establish a multi-objective optimization model to achieve comprehensive optimization of economic, environmental, and social goals. Through data collection, quantification and standardization, establishment of a multi-objective optimization problem model, NSGA-II algorithm solution, and simulation and result analysis, this paper seeks to provide scientific decision support and technical guidance for urban SW management. Taking Wuhan as an example, this study analyzes the treatment methods of six different types of SW and seeks the optimal treatment pathways through the multi-objective optimization model. The results show that the multi-objective optimization model can effectively balance economic costs, environmental costs, and utilization efficiency in SW treatment and utilization, providing new ideas for achieving urban sustainable development and resource recycling.

Mechanisms of residential spatial differentiation and heritage identity in residential historic district: a case study of the Barkhor Street, Tibet

ABSTRACT Under the dual background of urban renewal and heritage conservation, it is not clear what changes have taken place in the heritage identity and what is the connection with the residential spatial differentiation. This study takes a socio-spatial approach, uses a quantitative analysis approach to assess Barkhor Street’s residential space in terms of two factors: residential quality and heritage utilization. It also looks at how spatial differentiation affects residential historic districts’ heritage identities. It aims to re-understand the transformation process of heritage identity in different contexts. This study revealed that (1) variations in living spaces among people in residential historic districts can yield both positive and negative outcomes for their heritage identity. (2) Heritage identity is mediated in part by residential quality and the use of historical resources. (3) There is also a combined effect of individual attributes like the annual per capita household income, age, and ethnicity. Factors influencing people’ heritage identification include the per capita housing area, type of housing ownership, distance from religious heritage, and store form type. It is advised that mixed-use housing patterns be used to increase housing suitability and that procedures for community involvement and democratic, scientific decision-making be set up for preservation and renewal.

A prospect theory-driven three-way decision framework: Integrating prior probability tolerance and dominance relations in fuzzy incomplete information systems

This study proposes a novel method that integrates Prospect Theory (PT) with a Three-Way Decision (TWD) framework to enhance decision quality in Fuzzy Incomplete Information Systems (FIIS). The method first applies prior probability tolerance dominance relations to manage and evaluate binary relationships among decision options, laying the groundwork for subsequent calculations. Based on this foundation, PT is used to construct objective weight and value functions, effectively reducing uncertainties due to subjective factors in the decision-making process. Unlike traditional methods, this PT-based TWD approach can address incomplete data while fully considering decision-makers’ psychological preferences under risk, enabling more precise and scientific decision support. Extensive experimental studies and comparative analyses demonstrate that this method outperforms existing approaches in terms of stability, effectiveness, and superiority, highlighting its potential for applications in fields with high data diversity and uncertainty, such as healthcare.

Research on the Architecture of Maritime Regulatory Data Platform

The maritime regulatory data platform serves as the brain of the smart maritime regulatory platform. It collects data on navigation resources and port & waterway resources, unifies data norms and standards, and achieves comprehensive data resource management covering all elements including ships, crew members, companies, ports, waterways, and pilotage. Through data aggregation, mining, and analysis, it enables intelligent judgment, precise profiling, scientific decision-making, and multi-dimensional panoramic display. This platform provides maritime regulatory departments with scientific and reasonable decision-making suggestions, helping them better formulate and implement regulatory policies.

Optimal metacognitive decision strategies in signal detection theory.

Signal detection theory (SDT) has long provided the field of psychology with a simple but powerful model of how observers make decisions under uncertainty. SDT can distinguish sensitivity from response bias and characterize optimal decision strategies. Whereas classical SDT pertains to "type 1" judgments about the world, recent work has extended SDT to quantify sensitivity for metacognitive or "type 2" judgments about one's own type 1 processing, e.g. confidence ratings. Here we further advance the application of SDT to the study of metacognition by providing a formal account of normative metacognitive decision strategies - i.e., type 2 (confidence) criterion setting - for ideal observers. Optimality is always defined relative to a given objective. We use SDT to derive formulae for optimal type 2 criteria under four distinct objectives: maximizing type 2 accuracy, maximizing type 2 reward, calibrating confidence to accuracy, and maximizing the difference between type 2 hit rate and false alarm rate. Where applicable, we consider these optimization contexts alongside their type 1 counterparts (e.g. maximizing type 1 accuracy) to deepen understanding. We examine the different strategies implied by these formulae and further consider how optimal type 2 criterion setting differs when metacognitive sensitivity deviates from SDT expectation. The theoretical framework provided here can be used to better understand the metacognitive decision strategies of real observers. Possible applications include characterizing observers' spontaneously chosen metacognitive decision strategies, assessing their ability to fine-tune metacognitive decision strategies to optimize a given outcome when instructed, determining over- or under-confidence relative to an optimal standard, and more. This framework opens new avenues for enriching our understanding of metacognition.

Semi-Overlap Functions on Complete Lattices, Semi-Θ-Ξ Functions, and Inflationary MTL Algebras

As new kinds of aggregation functions, overlap functions and semi overlap functions are widely applied to information fusion, approximation reasoning, data classification, decision science, etc. This paper extends the semi-overlap function on [0, 1] to the function on complete lattices and investigates the residual implication derived from it; then it explores the construction of a semi-overlap function on complete lattices and some fundamental properties. Especially, this paper introduces a more generalized concept of the ‘semi-Θ-Ξ function’, which innovatively unifies the semi-overlap function and semi-grouping function. Additionally, it provides methods for constructing and characterizing the semi-Θ-Ξ function. Furthermore, this paper characterizes the semi-overlap function on complete lattices and the semi-Θ-Ξ function on [0, 1] from an algebraic point of view and proves that the algebraic structures corresponding to the inflationary semi-overlap function, the inflationary semi-Θ-Ξ function, and residual implications derived by each of them are inflationary MTL algebras. This paper further discusses the properties of inflationary MTL algebra and its relationship with non-associative MTL algebra, and it explores the connections between some related algebraic structures.

Automatic knee osteoarthritis severity grading based on X-ray images using a hierarchical classification method

BackgroundThis study aims to develop a hierarchical classification method to automatically assess the severity of knee osteoarthritis (KOA).MethodsThis retrospective study recruited 4074 patients. Clinical diagnostic indicators and clinical diagnostic processes were applied to develop a hierarchical classification method that involved four sub-task classifications. These four sub-task classifications were the classification of Kellgren-Lawrence (KL) grade 0–2 and KL grade 3–4, KL grade 3 and KL grade 4, KL grade 0 and KL grade 1–2, and KL grade 1 and KL grade 2, respectively. To extract the features of clinical diagnostic indicators, four U-Net models were first used to segment the total joint space (TJS), the lateral joint space (LJS), the medial joint space (MJS), and osteophytes, respectively. Based on the segmentation result of TJS, the region of knee subchondral bone was generated. Then, geometric features were extracted based on segmentation results of the LJS, MJS, TJS, and osteophytes, while radiomic features were extracted from the knee subchondral bone. Finally, the geometric features, radiomic features, and combination of geometric features and radiomic features were used to construct the geometric model, radiomic model, and combined model in KL grading, respectively. A strict decision strategy was used to evaluate the performance of the hierarchical classification method in all X-ray images of testing cohort.ResultsThe U-Net models achieved relatively satisfying performances in the segmentation of the TJS, the LJS, the MJS, and the osteophytes with the dice similarity coefficient of 0.88, 0.86, 0.88, and 0.64 respectively. The combined models achieved the best performance in KL grading. The accuracy of combined models was 98.50%, 81.65%, 82.07%, and 74.10% in the classification of KL grade 0–2 and KL grade 3–4, KL grade 3 and KL grade 4, KL grade 0 and KL grade 1–2, and KL grade 1 and KL grade 2, respectively. For all X-ray images of the testing cohort, the accuracy of the hierarchical classification method was 65.98%.ConclusionThe hierarchical classification method developed in the current study is a feasible approach to assess the severity of KOA.

Research on Fault Diagnosis of Agricultural IoT Sensors Based on Improved Dung Beetle Optimization–Support Vector Machine

The accuracy of data perception in Internet of Things (IoT) systems is fundamental to achieving scientific decision-making and intelligent control. Given the frequent occurrence of sensor failures in complex environments, a rapid and accurate fault diagnosis and handling mechanism is crucial for ensuring the stable operation of the system. Addressing the challenges of insufficient feature extraction and sparse sample data that lead to low fault diagnosis accuracy, this study explores the construction of a fault diagnosis model tailored for agricultural sensors, with the aim of accurately identifying and analyzing various sensor fault modes, including but not limited to bias, drift, accuracy degradation, and complete failure. This study proposes an improved dung beetle optimization–support vector machine (IDBO-SVM) diagnostic model, leveraging the optimization capabilities of the former to finely tune the parameters of the Support Vector Machine (SVM) to enhance fault recognition under conditions of limited sample data. Case analyses were conducted using temperature and humidity sensors in air and soil, with comprehensive performance comparisons made against mainstream algorithms such as the Backpropagation (BP) neural network, Sparrow Search Algorithm–Support Vector Machine (SSA-SVM), and Elman neural network. The results demonstrate that the proposed model achieved an average diagnostic accuracy of 94.91%, significantly outperforming other comparative models. This finding fully validates the model’s potential in enhancing the stability and reliability of control systems. The research results not only provide new ideas and methods for fault diagnosis in IoT systems but also lay a foundation for achieving more precise, efficient intelligent control and scientific decision-making.

Risky hybrid foraging: The impact of risk, reward value, and prevalence on foraging behavior in hybrid visual search.

In hybrid foraging, foragers search for multiple targets in multiple patches throughout the foraging session, mimicking a range of real-world scenarios. This research examines outcome uncertainty, the prevalence of different target types, and the reward value of targets in human hybrid foraging. Our empirical findings show a consistent tendency toward risk-averse behavior in hybrid foraging. That is, people display a preference for certainty and actively avoid taking risks. While altering the prevalence or reward value of the risky targets does influence people's aversion to risk, the overall effect of risk remains dominant. Additionally, simulation results suggest that the observed risk-averse strategy is suboptimal in the sense that it prevents foragers from maximizing their overall returns. These results underscore the crucial role of outcome uncertainty in shaping hybrid foraging behavior and shed light on potential theoretical developments bridging theories in decision making and hybrid foraging. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Green degree decision and pricing strategy of dual-channel supply chains

With the prevalence of green supply chains, the government has basic requirements for companies’ green investments and outcomes while consumers increasingly favor green products. Thus, green degree decision has garnered significant attention from manufacturers. This paper incorporates green degree decisions into a dual-channel supply chain and adopts a Stackelberg model to analyze the green degree and pricing strategies under centralized and decentralized decisions. We find that, when the manufacturer only decides on price, dual-channel choice is always the optimal strategy under centralized decision-making; however, under decentralized decision-making, the dual-channel choice will be chosen only when the wholesale price is low. Considering green degree decision, both direct and indirect channel prices increase with the green degree, and the indirect channel price is more sensitive to changes in the green degree under centralized decision-making; and higher green degrees are always advantageous for the retailer, but the manufacturer’s profit initially decreases and then increases as the green degree rises under decentralized decision-making. Moreover, the wholesale price is used as a strategic tool for the manufacturer to control the distribution channel, particularly when the green degree is not introduced, the manufacturer can always ensure the introduction of dual channels. Besides, higher consumers’ environmental awareness is always beneficial to channel members, as it promotes channel prices and green degree. This study provides strategic insights for optimizing pricing and green degree decisions in dual-channel supply chains to achieve better economic and environmental outcomes.

Neural reward system reflects individual value comparison strategy in cost-benefit decisions

A core assumption in decision neuroscience is that individuals decide between options by comparing option-specific subjective reward values. Psychological accounts challenge this view and suggest that decisions are better explained by comparisons between choice attributes than by comparisons between option-specific values, casting doubts on the interpretation of activation in the neural reward system as subjective value signals. Here, we provide neuroimaging and pharmacological evidence that value-related neural activity follows the value comparison strategy employed by an individual on the psychological level. Neural model comparisons reveal that activation in the striatum, rather than generally reflecting attribute-wise or option-wise value comparisons, reflects the value comparison strategy that provides the best explanation for an individual’s choice behavior. Strikingly, manipulating activation in the dopaminergic reward system reveals that dopamine antagonism counteracts the engagement in an individual’s dominant value comparison strategy. Together, our findings provide evidence for the biological plausibility of psychological accounts of decision making and emphasize the importance of neural model comparisons to prevent misinterpretations of brain activation.

Hotspots and future trends of dermatofibrosarcoma protuberans.

Dermatofibrosarcoma protuberans (DFSP) is a moderately malignant soft tissue sarcoma with localized infiltrative growth. The extensive surgical scope and high recurrence rate of DFSP brings dysfunctional, aesthetic, psychological and economic problems to patients. The aim of this study is to explore the global publication characteristics, research hotspots and future trends of DFSP over the past 32 years via an intuitive visualized way. The Web of Science Core Collection (WoSCC) database was searched for papers related to DFSP published from 1990 to 2022. Then bibliometric analysis of these publications was performed, including collaborative networks, co-citation analysis of journals and references, and cluster analysis of keywords. A total of 1588 papers were retrieved between 1990-2022. The United States was the most prolific country, followed by China. The article Imatinib Mesylate in Advanced Dermatofibrosarcoma Protuberans: Pooled Analysis of Two Phase II Clinical Trials, received most citations. Research hotspots and future trends are mainly focused on disease diagnosis, COL1A1-PDGFB fusion gene, drug and surgical treatment, fibrosarcomatous transformation, and immunotherapy. The research on DFSP faces several clinical challenges. This study provides novel insights into future research directions and scientific decisions for DFSP.

Regional healthcare resource allocation and decision-making: Evaluating the effectiveness of the three-stage super-efficiency DEA model

This study addresses the challenge of achieving a more rational allocation of medical resources at the regional level, using Guangxi Province, China, as a case study. A three-stage super-efficiency Data Envelopment Analysis (DEA) model is employed to assess and analyze the effectiveness of resource allocation. The research methodology involves identifying input, output, and environmental variable indicators to construct a healthcare resource allocation index system. The indicator data are processed using Excel software. The three-stage super-efficiency DEA model is then applied to evaluate the healthcare system in Guangxi Province, focusing on Pure Technical Efficiency Change (PEC), Scale Efficiency Change (SEC), Efficiency Change (EC), Technological Change (TC), and Total Factor Productivity (TFP). Finally, the Malmquist index method is utilized to measure and dynamically analyze the efficiency of healthcare resource allocation. The study's results show that, from a static perspective, the average comprehensive efficiency is 1.067 before adjustment and 1.054 after adjustment, indicating relatively high overall efficiency in healthcare resource allocation in Guangxi Province. However, environmental factors and random errors have led to an overestimation of healthcare resource allocation efficiency, which the three-stage super-efficiency DEA model effectively corrects. Additionally, the average SEC and PEC values are 0.997 and 0.998, respectively, both below 1. This indicates that both scale efficiency and pure technical efficiency contribute to a decline in technical efficiency. Based on the results of the sensitivity analysis, the conclusions regarding the efficiency of healthcare resource allocation in Guangxi are deemed highly reliable. Despite the influence of uncertain factors, the model consistently provides stable and coherent assessment results in most scenarios. Therefore, special attention is needed to improve scale efficiency in healthcare resource allocation within the region, alongside enhancing management and technological capabilities in the healthcare sector. Overall, this study provides valuable reference and guidance for researchers and practitioners in related fields and offers scientific decision support for healthcare resource allocation.