Exploring the potential of the sit-to-stand test for self-assessment of physical condition in advanced knee osteoarthritis patients using computer vision

Abstract

Introduction: Knee osteoarthritis (KOA) is a prevalent condition often associated with a decline in patients' physical function. Objective self-assessment of physical conditions poses challenges for many advanced KOA patients. To address this, we explored the potential of a computer vision method to facilitate home-based physical function self-assessments.

Methods: We developed and validated a simple at-home artificial intelligence approach to recognize joint stiffness levels and physical function in individuals with advanced KOA. One hundred and four knee osteoarthritis (KOA) patients were enrolled, and we employed the WOMAC score to evaluate their physical function and joint stiffness. Subsequently, patients independently recorded videos of five sit-to-stand tests in a home setting. Leveraging the AlphaPose and VideoPose algorithms, we extracted time-series data from these videos, capturing three-dimensional spatiotemporal information reflecting changes in key joint angles over time. To deepen our study, we conducted a quantitative analysis using the discrete wavelet transform (DWT), resulting in two wavelet coefficients: the approximation coefficients (cA) and the detail coefficients (cD).

Results: Our analysis specifically focused on four crucial joint angles: "the right hip," "right knee," "left hip," and "left knee." Qualitative analysis revealed distinctions in the time-series data related to functional limitations and stiffness among patients with varying levels of KOA. In quantitative analysis, we observed variations in the cA among advanced KOA patients with different levels of physical function and joint stiffness. Furthermore, there were no significant differences in the cD between advanced KOA patients, demonstrating different levels of physical function and joint stiffness. It suggests that the primary difference in overall movement patterns lies in the varying degrees of joint stiffness and physical function among advanced KOA patients.

Discussion: Our method, designed to be low-cost and user-friendly, effectively captures spatiotemporal information distinctions among advanced KOA patients with varying stiffness levels and functional limitations utilizing smartphones. This study provides compelling evidence for the potential of our approach in enabling self-assessment of physical condition in individuals with advanced knee osteoarthritis.

Keywords: body pose; computer vision; knee osteoarthritis; physical function; sit-to-stand; spatiotemporal information; stiffness.

Figure 1

Schematic process of extracting sit-to-stand (STS) test data. Participants followed instructions to complete the STS test, recording full-body movements in videos. Subsequently, we used AlphaPose to extract crucial body points and generate two-dimensional positions from the videos. Finally, VideoPose was employed to estimate three-dimensional body positions based on the extracted two-dimensional pose information.

Figure 2

Schematic results of two-dimensional and three-dimensional body position extracted from the videos.

Figure 3

Visualized results from the sit-to-stand (STS) test. The graphical representation consists of a horizontal axis denoting the timeline and a vertical axis indicating the key position angle. The red line signifies the average variation observed in the dataset. The following provide time series data for different subsets of advanced knee osteoarthritis (KOA) patients: (A) Time series data of advanced knee osteoarthritis (KOA) patients with mild joint stiffness. (B) Time series data of advanced KOA patients with severe joint stiffness. (C) Time series data of advanced KOA patients with mild limitations of physical function. (D) Time series data of advanced KOA patients with severe limitations of physical function.

Figure 4

Visualized results of quantitative analysis. In the plots of the wavelet coefficients, the horizontal coordinates depict the indexes of the data points, signifying their positions on the averaged curves. The vertical coordinates represent the coefficient values derived from the discrete wavelet transform (DWT) process. These values denote the various band components resulting from the DWT decomposition. (A,B) Presents the results of a quantitative analysis conducted on patients categorized by joint stiffness. The abbreviations used are cA1: approximation coefficients of the angular variation curves in advanced knee osteoarthritis (KOA) patients with mild joint stiffness; cA2: approximation coefficients of the angular variation curves in advanced KOA patients with severe joint stiffness; cD1: detail coefficients in advanced KOA patients with mild joint stiffness; cD2: detail coefficients in advanced KOA patients with severe joint stiffness. (C,D) Presents the results of a quantitative analysis conducted on patients categorized by physical function limitations. The abbreviations used are cA3: approximation coefficients of the angular variation curves in advanced knee osteoarthritis (KOA) patients with mild limitations of physical function; cA4: approximation coefficients of the angular variation curves in advanced KOA patients with severe limitations of physical function; cD3: detail coefficients in advanced KOA patients with mild limitations of physical function; cD4: detail coefficients in advanced KOA patients with severe limitations of physical function.