Personalized Fall Risk Assessment Tool by using the Data Treasure contained in Mobile Electronic Patient Records.

Area of Science:

• Gerontology and Health Informatics
• Artificial Intelligence in Healthcare
• Distributed Systems

Background:

• Elderly fall risk assessment requires personalized and adaptive tools.
• Integrating diverse Electronic Patient Records (EPRs) presents challenges.
• Current methods may not fully capture dynamic patient needs.

Purpose of the Study:

• To develop a novel, self-learning fall risk assessment tool.
• To enhance personalized healthcare for elderly individuals through integrated EPR data.
• To create an adaptive system for identifying and tracking patient fall risk.

Main Methods:

• Utilizing an agent-based architecture to represent individual patients.
• Employing distributed information fusion for data integration.
• Implementing opinion aggregation techniques for indicator negotiation and elaboration.

Main Results:

• Successfully combined multiple EPRs into a unified fall risk assessment framework.
• Developed patient agents capable of negotiating and identifying novel fall risk indicators.
• Demonstrated the adaptability of the fall risk assessment tool based on negotiated indicators.

Conclusions:

• The agent-based approach effectively integrates EPRs for personalized fall risk assessment.
• Distributed information fusion and opinion aggregation enable the discovery of new fall risk indicators.
• The self-learning tool enhances the ability of home-visiting nurses to track and manage patient fall risk effectively.