Design and development of WeChat applet for mind-body wisdom management of diabetic patients

The global prevalence of diabetes continues to rise, with comorbid anxiety and depression increasingly impacting patients’ quality of life and disease control. However, most current management systems focus solely on physiological parameters—such as blood glucose, diet, and exercise—while lacking mechanisms for psychological intervention or intelligent prediction. To address this gap, this study developed a WeChat mini-program that integrates physiological monitoring, emotional risk prediction, data visualization, and personalized intervention into a unified intelligent health management platform. The system adopts a front-end/back-end separation architecture, with Vue for the front end and Spring Boot plus MySQL on the back end to support multi-role access, data processing, and health goal management. It incorporates the REDAPM (Regional EHR for Depression and Anxiety Prediction Model), a deep learning model deployed via Flask, to assess psychological risks based on structured and unstructured electronic health data. Prediction results are returned to users in the form of intuitive visualizations and tailored emotional health suggestions. Core functions include user profile management, glucose and diet logging, activity tracking, psychological assessments, prediction feedback, and access to educational video content. System testing demonstrated stable performance and usability, enabling improved patient engagement and self-regulation. By embedding AI-driven emotional screening into a chronic disease platform, the system supports a “mind-body comanagement” model for diabetes care. This work offers practical and scalable insights for the development of intelligent health tools that address both physical and psychological needs in chronic disease populations.