Wearable sensors to predict improvement following an exercise intervention in patients with knee osteoarthritis

Abstract

Background: Muscle strengthening exercises consistently demonstrate improvements in the pain and function of adults with knee osteoarthritis, but individual response rates can vary greatly. Identifying individuals who are more likely to respond is important in developing more efficient rehabilitation programs for knee osteoarthritis. Therefore, the purpose of this study was to determine if pre-intervention multi-sensor accelerometer data (e.g., back, thigh, shank, foot accelerometers) and patient reported outcome measures (e.g., pain, symptoms, function, quality of life) can retrospectively predict post-intervention response to a 6-week hip strengthening exercise intervention in a knee OA cohort.

Methods: Thirty-nine adults with knee osteoarthritis completed a 6-week hip strengthening exercise intervention and were sub-grouped as Non-Responders, Low-Responders, or High-Responders following the intervention based on their change in patient reported outcome measures. Pre-intervention multi-sensor accelerometer data recorded at the back, thigh, shank, and foot and Knee Injury and Osteoarthritis Outcome Score subscale data were used as potential predictors of response in a discriminant analysis of principal components.

Results: The thigh was the single best placement for classifying responder sub-groups (74.4%). Overall, the best combination of sensors was the back, thigh, and shank (81.7%), but a simplified two sensor solution using the back and thigh was not significantly different (80.0%; p = 0.27).

Conclusions: While three sensors were best able to identify responders, a simplified two sensor array at the back and thigh may be the most ideal configuration to provide clinicians with an efficient and relatively unobtrusive way to use to optimize treatment.

Keywords: Accelerometers; Biomechanics; Gait analysis; Knee osteoarthritis; Machine learning; Rehabilitation; Wearable sensors.

Conflict of interest statement

Ethics approval and consent to participate

This research was approved by the Conjoint Health Research Ethics Board at the University of Calgary and all participants provided written, informed consent prior to participating.

Consent for publication

Not applicable.

Competing interests

The authors declare that they have no competing interests.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Figures

Fig. 1

Diagram of patient screening and flow throughout study

Fig. 2

Positioning of inertial sensors on the back, thigh, shank, and foot of the most affected side of knee osteoarthritis patients

Fig. 3

Absolute change in Knee Injury and Osteoarthritis Outcome Score (KOOS) subscale scores following 6-week intervention, organized by responder sub-groups. The dotted line represents the minimal clinically important improvement [18]. Abbreviations: ADL = Function in Daily Living; QoL = Knee Related Quality of Life.. Note: KOOS is measured on a scale of 100, with 100 best (e.g., no pain) and 0 being worst (e.g., most pain imaginable)

Fig. 4

Representative example of accelerometer data processing steps (i) attitude correction, (ii) gait cycle segmentation, and (iii) data reduction. The four sensor placement signals are ordered from back (top) to foot (bottom)

Fig. 5

Baseline Knee Injury and Osteoarthritis Outcome Score (KOOS) subscale scores. Abbreviations: ADL = Function in Daily Living; QoL = Knee Related Quality of Life.. Note: KOOS is measured on a scale of 100, with 100 best (e.g., no pain) and 0 being worst (e.g., most pain imaginable)

Fig. 6

Classification accuracy for single accelerometer placements (diamond) and the best 2, 3, and 4 sensor arrays (circles). *Significantly greater than all other single sensor arrays. †Significantly greater than all other sensor arrays

Fig. 7

Relative importance (i.e., proportion of loading in model out of 100%) of the gait data and patient reported outcome (PRO) measures in the best single sensor (top) and multi-sensor (bottom) classification models, based on sum of squared coefficient loadings in discriminant analysis

Fig. 8

Mean acceleration waveforms of responder sub-groups, with relative positive (blue) and negative (orange) loading of gait principal components from the back, thigh, and shank sensors used in the three sensor classification model