Search

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.

Summary: Percutaneous dilatational tracheostomy (PDT) is a bedside medical procedure which sites a new tracheostomy tube in the front of the neck. The critical first step is accurate placement of a needle through the neck tissues into the trachea. Misplacement occurs in around 5% of insertions, causing morbidity, mortality, and delays to recovery. We aimed to develop and evaluate a prototype medical device to improve precision of initial PDT-needle insertion. The Guidance for Tracheostomy (GiFT) system communicates the relative locations of intra-tracheal target sensor and PDT-needle sensor to the operator. In simulated “difficult neck” models, GiFT significantly improved accuracy (mean difference 10.0 mm, ANOVA p