Gait biomechanics phenotypes among total knee arthroplasty candidates by machine learning cluster analysis

Abstract

Knee osteoarthritis patient phenotyping is relevant to developing targeted treatments and assessing the treatment efficacy of total knee arthroplasty (TKA). This study aimed to identify clusters among TKA candidates based on demographic and knee mechanic features during gait, and compare gait changes between clusters postoperatively. TKA patients underwent 3D gait analysis 1‐week pre (n = 134) and 1‐year post‐TKA (n = 105). Principal component analysis was applied to frontal and sagittal knee angle and moment waveforms, extracting major patterns of variability. Age, sex, body mass index, gait speed, and frontal and sagittal pre‐TKA angle and moment PC scores previously identified as relevant to TKA outcomes were standardized (mean = 0, SD = 1, [134 × 15]). Multidimensional scaling and machine learning‐based hierarchical clustering were applied. Final clusters were validated by examining intercluster differences pre‐TKA and gait feature changes (PostPCscore – PrePCscore) by k‐way Χ2 and ANOVA tests. Four TKA candidate phenotypes yielded optimum clustering metrics, interpreted as higher and lower functioning clusters that were predominantly male and female. Higher functioning clusters pre‐TKA (clusters 1 and 4) had more dynamic sagittal flexion moment (p < 0.001) and frontal plane adduction moment (p < 0.001) loading/un‐loading patterns during stance. Post‐TKA, higher functioning clusters demonstrated less knee mechanic improvements during gait (flexion angle p < 0.001; flexion moment p < 0.001). TKA candidates can be characterized by four clusters, predominately separated by sex and knee joint biomechanics. Post‐TKA knee kinematics and kinetics improvements were cluster‐specific; lower functioning clusters experienced more improvement. Cluster‐based patient profiling may aid in triaging and developing OA management and surgical strategies meeting group‐level function needs.

Multidimensional analysis of preoperative patient-reported outcomes identifies distinct phenotypes in patients booked for total knee arthroplasty: Secondary analysis of the SHARKS registry in a metropolitan hospital department

“…Phenotyping is an emerging field in orthopaedic research that offers a more nuanced understanding of patient heterogeneity and has the potential to guide management decisions (Nelson, 2018). While this study focused on PROMs, previous studies have stratified patients with OA can be stratified based on knee alignment, radiographic features, kinematics, metabolomics, and more (Dell'Isola, Allan, et al, 2016;Deveza et al, 2017;Dório & Deveza, 2022;Moser et al, 2020;Pan et al, 2020;Petersen et al, 2022;Young-Shand et al, 2023;Zhang et al, 2014). For instance, Moser et al (2020) identified diverse knee phenotypes based on knee alignment and recommended personalised TKA realignment for improved outcomes.…”

“…In recent years significant strides have been made in this direction. For instance, previous research has attempted to group patients with OA into phenotypes based on gait kinematics (Petersen et al, 2022; Young-Shand et al, 2023), joint aspirate metabolomics (Zhang et al, 2014), pain groups (Pan et al, 2020), functional knee characteristics (Moser et al, 2020), structural characteristics, and prognosis (Dell’Isola et al, 2016). Recent studies have found that phenotypes based on a combination of preoperative PROMs were associated with dissatisfaction after TKA and postoperative PROMs (Kung et al, 2023; Orr et al, 2022).…”

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

“…A comparison investigation led them to the conclusion that an LR classifier trained on six weeks of post-operative biomechanical data during walking was responsive to changes at 3, 6, and 12 months post-TKA (with a 67.3% accuracy). In contrast with the other studies, Young-Shand et al identified clusters among TKA candidates and postoperatively using knee biomechanical parameters during gait and demographic data and machine learning cluster analysis [25]. They performed 3D gait analysis on 134 pre-and 105 post-TKA patients, and they used PCA as a feature reduction technique.…”

“…The main inclusion criteria were knee OA and the wait time for total knee replacement. Young-Shand et al employed 135 subjects 1 week before and 109 subjects one year post-TKA with the main aim to determine clusters among TKA candidates and compare gait differences between clusters post-surgery [25]. The main inclusion criterion was the ability to walk 6 m without a walking aid.…”