Introduction. The purpose of this study was to demonstrate the feasibility of passively collecting objective data from a commercially available smartphone-based care management platform (sbCMP) and robotic assisted total knee arthroplasty (raTKA). Methods. Secondary data analysis was performed using de-identified data from a commercial database that collected metrics from a sbCMP combined with intraoperative data collection from raTKA. Patients were included in this analysis if they underwent unilateral raTKA between July 2020 and February 2021, and were prescribed the sbCMP (n=131). The population consisted of 76 females and 55 males, with a mean age of 64 years (range, 43 – 81). Pre-operative through six-week post-operative data included step counts from the sbCMP, as well as administration of the KOOS JR. Intraoperative data included surgical times, the hip-knee-ankle angle (HKA), and medial and lateral laxity assessments from the robotic assessment. Data are presented using descriptive statistics. Comparisons were performed using a paired samples t-test, or Wilcoxon Signed-rank test, with significance assessed at p<0.05. A minimal detectable change (MDC) in the KOOS JR score was considered ½ standard deviation of the preoperative values. Results. KOOS JR scores improved from a preoperative mean of 51.5 ± 11.5 to a 6-week postoperative mean of 64 ± 10.04 (p<0.001). An MDC of 5.75 units was achieved. Step counts decreased initially and returned to preoperative values by week 6 (Figure 1, p=0.196). When evaluating time requirements from landmarking to completed surgical cuts, the median surgical time was 40.2 minutes (IQR, 29.4 – 52.0). The median absolute deformity for HKA preoperatively was 6.9 degrees (IQR, 4.1 – 10.1) and the final intraoperative median HKA was 0.9 degrees (IQR, 0.1 – 3, p<0.001). There was a difference in medial and lateral joint laxity in flexion and extension at the initial intraoperative evaluation (p<0.01). At the final evaluation there was no difference in medial and lateral joint laxity in extension (p=0.239); however, a slight difference in flexion was noted (p=0.001). Given the median values of 1.2mm (0.8 – 2.4) medially vs. 1.4mm (0.9 – 3) laterally, this difference is not likely clinically relevant. Patients who had <1 mm of medial laxity in flexion had significantly fewer step counts at week 6 post-operatively (p=0.035). There was no difference in KOOS JR scores associated with tightness (p>0.05). Discussion. The use of passively collected objective measures in a commercial database across the episode of care was feasible and demonstrated associations between intraoperative and post-operative metrics. To our knowledge, this is the first integrated data collection and reporting platform to report on these measures in a commercial population. Future research is needed in order to understand the benefit of displaying these metrics, as well as the role of variations in alignment and gap balance on function. Conclusions. Contemporary data platforms may be used to improve the understanding of individual recovery paths through real-time passive data collection throughout the episode of care. For any figures or tables, please contact the authors directly

Objective. Wearable sensors have enabled objective functional data collection from patients before total knee replacement (TKR) and at clinical follow-ups post-surgery whereas traditional evaluation has solely relied on self-reported subjective measures. The timed-up-and-go (TUG) test has been used to evaluate function but is commonly measured using only total completion time, which does not assess joint function or test completion strategy. The current work employs machine learning techniques to distinguish patient groups based on derived functional metrics from the TUG test and expose clinically important functional parameters that are predictive of patient recovery. Methods. Patients scheduled for TKR (n=70) were recruited and instrumented with a wearable sensor system while performing three TUG test trials. Remaining study patients (n=68) also completed three TUG trials at their 2, 6, and 13-week follow-ups. Many patients (n=36) have also participated up to their 26-week appointment. Custom developed software was used to segment recorded tests into sub-activities and extract 54 functional metrics to evaluate op/non-operative knee function. All preoperative TUG samples and their standardized metrics were clustered into two unlabelled groups using the k-means algorithm. Both groups were tracked forward to see how their early functional parameters translated to functional improvement at their three-month assessment. Test total completion time was used to estimate overall functional improvement and to relate findings to existing literature. Patients that completed their 26-week tests were tracked further to their most recent timepoint. Results. Preoperative clustering separated two groups with different test completion times (n=46 vs. n=22 with mean times of 13s vs. 22s). Of the faster preoperative group, 63% of patients maintained their time, 26% improved, and 11% worsened whereas of the slower preoperative group, 27% maintained, 64% improved, and 9% worsened. The high improvement group improved their times by 4.9s (p<0.01) between preoperative and 13-week visits whereas the other group had no significant change. Test times were different between both groups preoperatively (p<0.001) and at 6 (p=0.01) and 13 (p=0.03) weeks but not at 26 weeks (p=0.67). The high improvement group reached an overall improvement of 9s (p<0.01) at 26 weeks whereas the low improvement group still showed no improvement greater than the TUG minimal detectable change of 2.2s (1.8s, p<0.01)[1]. Test sub-activity times for both groups at each timepoint can be seen in Figure 1. Conclusions. This work has demonstrated that machine learning has the potential to find patterns in preoperative functional parameters that can predict functional improvement after surgery. While useful for assigning labels to the distinguished clusters, test completion time was not among the top distinguishable metrics between groups at three months which highlights the necessity for these more descriptive performance metrics when analyzing patient recovery. It is expected that these early predictions will be used to realistically adjust patient expectations or highlight opportunities for physiotherapeutic intervention to improve future outcomes. For any figures or tables, please contact the authors directly