Clinical reliability and validity of a video-based markerless gait evaluation method

Abstract This study explored the reliability and validity of gait parameters obtained from gait assessment system software employing a human posture estimation algorithm based on markerless videos of children walking in clinical practice. Eighteen healthy children were recruited to walk along a designated sidewalk at a comfortable walking speed. A 3-dimensional gait analysis (3D GA) and a 2-dimensional markerless (2D ML) gait evaluation system were used to extract the gait kinematics parameters twice at an interval of 2 h. The two measurements of the children’s kinematic gait parameters revealed no significant differences (P > 0.05). Intra-class correlation coefficients(ICCs) were generally high(ICC>0.7), showing moderate to good relative reliability. The standard error of measurement (SEM) values of all gait parameters measured by the two walks were 1.26°– 2.91°. The system software had good to excellent validity compared to the 3D GA, with ICC values between 0.835 and 0.957 and SEM values of 0.87° to 1.71° for the gait parameters measured by both methods. The Bland-Altman plot analysis indicated no significant systematic errors. The results suggest that the markerless gait assessment method using the human posture estimation-based algorithm may provide reliable and valid gait analysis results for practical clinical applications.