Can the Output of a Learned Classification Model Monitor a Person’s Functional Recovery Status Post-Total Knee Arthroplasty?

Abstract

Osteoarthritis is a common musculoskeletal disorder. Classification models can discriminate an osteoarthritic gait pattern from that of control subjects. However, whether the output of learned models (probability of belonging to a class) is usable for monitoring a person’s functional recovery status post-total knee arthroplasty (TKA) is largely unexplored. The research question is two-fold: (I) Can a learned classification model’s output be used to monitor a person’s recovery status post-TKA? (II) Is the output related to patient-reported functioning? We constructed a logistic regression model based on (1) pre-operative IMU-data of level walking, ascending, and descending stairs and (2) 6-week post-operative data of walking, ascending-, and descending stairs. Trained models were deployed on subjects at three, six, and 12 months post-TKA. Patient-reported functioning was assessed by the KOOS-ADL section. We found that the model trained on 6-weeks post-TKA walking data showed a decrease in the probability of belonging to the TKA class over time, with moderate to strong correlations between the model’s output and patient-reported functioning. Thus, the LR-model’s output can be used as a screening tool to follow-up a person’s recovery status post-TKA. Person-specific relationships between the probabilities and patient-reported functioning show that the recovery process varies, favouring individual approaches in rehabilitation.

Incorporating Wearable Technology for Enhanced Rehabilitation Monitoring after Hip and Knee Replacement

“…This study demonstrates several notable strengths that enhance its robustness and scientific significance. Foremost among these strengths is the study’s commitment to real-world relevance, evident in its recognition of the critical importance of assessing patients in ecological environment and conditions [ 61 , 62 , 63 , 64 ]. This approach stands in stark contrast to conventional clinical tests, providing a more ecologically valid perspective on the rehabilitation process.…”

Identifying Gait-Related Functional Outcomes in Post-Knee Surgery Patients Using Machine Learning: A Systematic Review

“…Various limitations were observed in the reviewed studies. The small number of employed subjects, the feature extraction [24], the non-use of transfer learning, the no existence of information on selfreported patient scores, and the absence of clinical equipoise in the opinion of both clinicians were the main limitations.…”

“…Emmerzaal et al investigated if the functional recovery status after TKA can be estimated by a classification model [24]. In total, 17 inertial measurement units were used to record different tasks (e.g., walking and descending stairs).…”

“…In the TKA category, Emmerzall et al, used 20 healthy subjects as the control group, 19 subjects with unilateral knee OA and 17 of them, which were re-evaluated at 1.5, 3, 6, and 12 months post-TKA surgery with the main aim to develop an ML model for monitoring functional recovery status post-TKA [24]. The main inclusion criteria were knee OA and the wait time for total knee replacement.…”