Digital Transformation for Community-Based Elderly Care Model: An Innovative Prediction Service for Managing and...

This research aimed to develop and implement a digital innovation model integrating big data for chronic disease management and monitoring, and to promote digital transformation in community-based elderly care. A mixed-method approach centered on big data technology and public health perspectives was adopted. In pilot communities (n=3), the dynamic demand assessment model using Gradient Boosting Decision Tree (GBDT) achieved significantly higher prediction accuracy than traditional experiential judgment (85.3% vs. 62.4%, p<0.01). In Shandong cohort (n=320), real-time monitoring of blood pressure and blood glucose via smart devices increased hypertension management rate from 54% to 72% (p<0.05) and reduced diabetes complication incidence by 19%. In Beijing cohort (n=150), IoT-based fall monitoring shortened average response time from 22 minutes to 8 minutes and improved treatment success rate by 35%. The model demonstrated favorable data security and technical applicability, but faced challenges of digital divide-only 42% of adults aged 65+ could independently use service-booking apps, with 58% relying on family or volunteer assistance. The big data-driven prediction model is feasible for community elderly care and can facilitate its digital transformation, whereas further simplification of operational complexity is required.