Optimized Management of Personal Health Archives in the Community Through Data Models

This paper briefly introduces the health archives of community residents and the convolutional neural network (CNN) algorithm used to classify the medical examination data in health archives. A case study was conducted on the residents of Guangzhou from January to March 2025, and the performance support vector machine, decision tree, back-propagation neural network, and CNN was compared. A regression analysis was performed on the factors affecting resident health. The results showed that the CNN had more accurate classification performance for medical examination data; family medical history, smoking, drinking, sleep duration, salt intake, fat intake, and fruit and vegetable intake had a significant impact on residents’ health.