Matt C. Smith

Pain and knee stiffness are common problems following total knee replacement surgery, with 10–20% of patients reporting dissatisfaction following their procedure. A remote assessment of knee stiffness could improve outcomes through continuous monitoring, facilitating timely intervention. Using machine learning algorithms, computer vision can extract joint angles from video footage, offering a method to monitor knee range of motion in patients’ homes. This study outlines a protocol to provide proof of concept and validate a computer vision-based approach for measuring knee range of motion in individuals who have undergone total knee replacement. The study also explores the feasibility of integrating this technology into clinical practice, enhancing post-operative care. The study is divided into three components: carrying out focus groups, validating the computer vision-based software, and home testing. The focus groups will involve five people who underwent total knee replacement and ten healthcare professionals or carers who will discuss the deployment of the software in clinical settings. For the validation phase, 60 participants, including 30 patients who underwent total knee replacement surgery five to nine weeks prior and 30 healthy controls, will be recruited. The participants will perform five tasks, including the sit-to-stand test, where knee range of motion will be measured using computer vision-based markerless motion capture software, marker-based motion capture, and physiotherapy assessments. The accuracy and reliability of the software will be evaluated against these established methods. Participants will perform the sit-to-stand task at home. This will allow for a comparison between home-recorded and lab-based data. The findings from this study have the potential to significantly enhance the monitoring of knee stiffness following total knee replacement. By providing accurate, remote measurements and enabling the early detection of issues, this technology could facilitate timely referrals to non-surgical treatments, ultimately reducing the need for costly and invasive procedures to improve knee range of motion.

When collecting marker-based motion capture data from clinical populations, speed of collection and comfort for the participant is a priority. This could be achieved by attaching markers to motion capture Velcro suits, as opposed to the skin. This study aimed to ascertain the reliability of sagittal-plane gait parameters estimated using Plug-in Gait (PiG) and Conventional Gait Model 2 (CGM2) marker sets from data collected in Suited and Non-suited (markers placed onto skin) conditions. For ten participants, markers were placed based on PiG and CGM2 models and data captured during a 2-min treadmill walk. Trials were repeated in suited and non-suited conditions. PiG ankle flexion/extension measurements had poor/moderate reliability (Non-suited ICC = 0.531, Suited ICC = 0.435). CGM2 ankle flexion/extension measurements had good/excellent reliability (Non-suited ICC = 0.916, Suited ICC = 0.900). There were significant differences in minimal detectable change (MDC) between conditions at the ankle for PiG (Non-suited MDC = 2.32°, Suited MDC = 18.90°), but not for CGM2 (Non-suited MDC = 0.63°, Suited MDC = 0.95°). When using CGM2, knee (Non-suited ICC = 0.878, Suited ICC = 0.855) and hip (Non-suited ICC = 0.897, Suited ICC = 0.948) showed good/excellent reliability in both conditions. A motion capture suit is not a reliable solution when collecting joint angle data using the PiG model but is reliable enough to consider when using the CGM2 model.