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

Area of Science:

• Public Health
• Health Informatics
• Gerontology

Background:

• Community-based elderly care faces challenges in chronic disease management and monitoring.
• Digital transformation is crucial for enhancing the efficiency and effectiveness of elderly care services.
• Integrating big data analytics offers potential solutions for personalized health management.

Purpose of the Study:

• To develop and implement a digital innovation model using big data for chronic disease management in the elderly.
• To promote digital transformation within community-based elderly care settings.
• To evaluate the model's effectiveness, feasibility, and challenges.

Main Methods:

• A mixed-method approach combining big data technology with public health perspectives.
• Utilized Gradient Boosting Decision Tree (GBDT) for dynamic demand assessment in pilot communities (n=3).
• Implemented real-time monitoring of hypertension and diabetes (n=320) and IoT-based fall detection (n=150) in cohort studies.

Main Results:

• The GBDT model achieved significantly higher prediction accuracy (85.3%) compared to traditional methods (62.4%).
• Real-time monitoring increased hypertension management rates (54% to 72%) and reduced diabetes complications (19%).
• IoT fall monitoring reduced response time (22 to 8 minutes) and improved treatment success (35%), despite digital divide challenges.

Conclusions:

• A big data-driven model is feasible for community elderly care, facilitating digital transformation.
• The model shows promise in improving chronic disease management and emergency response for seniors.
• Addressing the digital divide and simplifying operational complexity are essential for broader adoption and success.