A Study on Optimising Material Characteristics of Hospital Waiting Areas from a Social Medicine Perspective and Their Impact on Mental Health

Background The deepening implementation of the “Healthy China” strategy has elevated psychological safety in healthcare settings to a critical dimension of public health. Hospital waiting areas, as critical touchpoints before patients receive clinical services, directly influence the psychological states and emotional regulation of both patients and medical staff. This impact is particularly pronounced in high-traffic settings like tertiary hospitals and urban general hospitals. Therefore, there is an urgent need to transform waiting spaces from purely functional areas into “healing environments” that offer preventive and health-promoting benefits. Objective To achieve quantitative analysis of material characteristics, a model based on Support Vector Machines (SVM) and Genetic Algorithms (GA) was constructed. This enables scientific adjustment of material properties in hospital waiting areas to promote patient psychological recovery. Consequently, it provides a technical pathway for creating health-promoting spaces with precise preventative capabilities within a broader public health framework. Methods This study treats hospital waiting areas as sites for preventive interventions and integrates material design into health promotion toolkits. First, grounded in social medicine theory, we employed cluster analysis and semantic differential methods to extract core emotional imagery vocabulary associated with materials from both medical staff and patients, establishing key affective dimensions such as “oppressive-soothing.” Subsequently, computer vision technology was employed to extract physical characteristics of materials, including glossiness, texture, and transparency. A material-emotion mapping model was constructed using Support Vector Machines (SVM), enabling quantitative prediction of psychological effects from physical parameters. Finally, genetic algorithms (GA) were applied for global optimization of model parameters, yielding optimal material combination schemes. Results The optimised material characteristics significantly enhance the comfort and tranquillity of the waiting environment. The model achieved a prediction accuracy of 0.67, with the deviation between the optimised target value and the theoretical optimum being merely 0.0007. This validates the reliability and practicality of this methodology in health environment design, providing a replicable technical pathway for precision interventions in the ‘environment-mood-health’ continuum within the public health sector. Conclusions From a public health perspective, this data-driven material optimisation strategy not only provides quantifiable decision-making tools for hospital design but also propels a paradigm shift in healthcare environments from “function-oriented” to “health promotion-oriented”. This holds profound significance for improving doctor-patient relationships and enhancing the quality of healthcare services. Future research may further integrate neuroarchitecture methodologies to explore the impact of dynamic environmental factors on emotional states, thereby supporting the creation of more comprehensive health-promoting medical spaces.