A fall risk detection method and device, electronic equipment and storage medium
By collecting and fusing motion data in wearable devices, a normal state space and a fall risk threshold range are constructed. Using Kalman filtering and information entropy algorithms, the problem of fall detection in multiple stages and scenarios for elderly patients with hip fractures in the perioperative period is solved, achieving accurate adaptation and continuous monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PEKING UNION MEDICAL COLLEGE HOSPITAL
- Filing Date
- 2026-05-29
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, fall detection devices have insufficient personalized adaptation and poor stage adaptation in elderly patients with hip fractures in the perioperative period, making it difficult to meet the needs of fall prevention and control in multiple stages and scenarios. In particular, they are prone to missed or misjudged cases during the preoperative bed rest period and the postoperative rehabilitation period.
Motion data is collected using sensors in wearable devices. Accelerometer and gyroscope data are fused using the Kalman filter method to construct a normal state space and fall risk level threshold range for different usage stages. The fall risk is judged and predicted using logarithmic weighted Euclidean distance and information entropy algorithms.
It enables personalized and precise adaptation of fall risk across multiple scenarios throughout the perioperative period, providing continuous and accurate detection and prediction, thus avoiding the need for equipment replacement and solution reconstruction.
Smart Images
Figure CN122398282A_ABST