Validity of multiple human pose estimation tools for measuring knee impact angles in video-captured falls of older...

Falls are a major cause of injury in older adults. Although bending the knees during a fall has been shown to reduce stress on the hip, knee motion during falls is not well understood because laboratory fall studies are limited by safety concerns and marker occlusion in motion capture systems. AI-based pose estimation may help overcome these challenges, but its accuracy in measuring joint angles during falls has not yet been validated. We evaluated three pose estimation models (OpenPose, VideoPose3D, WHAM) for analyzing knee kinematics in video-captured falls. A total of 121 videos of 13 older adults (64.0 ± 5.9 years) falling sideways, utilizing diverse fall strategies (knee block, stick-like, tuck-and-roll), in a lab setting were analyzed. Each model generated time series of knee angles from the videos, from which knee flexion angles at ground impact were calculated and compared to ground truth data from a motion capture system. Agreement with the ground truth was assessed using mean absolute error (MAE), mean absolute percentage error (MAPE), and bias, analyzed across viewing planes (sagittal vs. frontal) and leg sides (impact vs. opposite). WHAM demonstrated the highest accuracy (MAPE:13.61 ± 10.55%) with minimal bias (<10%), consistently performing well across all views and leg sides. OpenPose performed similar to WHAM in the sagittal view (MAPE:14.38 ± 9.63%) but poorly in the frontal view (MAPE:71.33 ± 17.24%) due to substantial underestimation (bias:-71.33 ± 17.24%). VideoPose3D showed poor accuracy across all conditions (MAPE:39.09 ± 20.54%). WHAM also characterized differences in knee flexion kinematics between fall strategies (e.g., least vs. most knee flexion) but did not fully reproduce side-specific kinematic differences between legs, particularly for tuck-and-roll falls. This is the first study to validate pose estimation algorithms for estimating knee impact angles from video-captured falls in older adults. Future work should fine-tune WHAM using fall-specific data to further improve its performance in tracking body movements during falls.