Ambulatory Fall Event Detection with Integrative Ambulatory Measurement (IAM) Framework

Injuries associated with fall accidents pose a significant health problem to society, both in terms of human suffering and economic losses. Existing fall intervention approaches are facing various limitations. This dissertation presented an effort to advance indirect type of injury prevention approach. The overall objective was to develop a new fall event detection algorithm and a new integrative ambulatory measurement (IAM) framework which could further improve the fall detection algorithm's performance in detecting slip-induced backward falls. This type of fall was chosen because slipping contributes to a major portion of fall-related injuries. The new fall detection algorithm was designed to utilize trunk angular kinematics information as measured by Inertial Measurement Units (IMU).

Two empirical studies were conducted to demonstrate the utility of the new detection algorithm and the IAM framework in fall event detection. The first study involved a biomechanical analysis of trunk motion features during common Activities of Daily Living (ADLs) and slip-induced falls using an optical motion analysis system. The second study involved collecting laboratory data of common ADLs and slip-induced falls using ambulatory sensors, and evaluating the performance of the new algorithm in fall event detection.

Results from the current study indicated that the backward falls were characterized by the unique, simultaneous occurrence of an extremely high trunk extension angular velocity and a slight trunk extension angle. The quadratic form of the two-dimensional discrimination function showed a close-to-ideal overall detection performance (AUC of ROCa = 0.9952). The sensitivity, specificity, and the average response time associated with the specific configuration of the new algorithm were found to be 100%, 95.65%, and 255ms, respectively. The individual calibration significantly improved the response time by 2.4% (6ms).

Therefore, it was concluded that slip-induced backward fall was clearly distinguishable from ADLs in the trunk angular phase plot. The new algorithm utilizing a gyroscope and orientation sensor was able to detect backward falls prior to the impact, with a high level of sensitivity and specificity. In addition, individual calibration provided by the IAM framework was able to further enhance the fall detection performance.