Classification of inertial sensor-based gait patterns of orthopaedic conditions using machine learning: A pilot study

Elderly patients often have more than one disease that affects walking behavior. An objective tool to identify which disease is the main cause of functional limitations may aid clinical decision making. Therefore, we investigated whether gait patterns could be used to identify degenerative diseases using machine learning. Data were extracted from a clinical database that included sagittal joint angles and spatiotemporal parameters measured using seven inertial sensors, and anthropometric data of patients with unilateral knee or hip osteoarthritis, lumbar or cervical spinal stenosis, and healthy controls. Various classification models were explored using the MATLAB Classification Learner app, and the optimizable Support Vector Machine was chosen as the best performing model. The accuracy of discrimination between healthy and pathologic gait was 82.3%, indicating that it is possible to distinguish pathological from healthy gait. The accuracy of discrimination between the different degenerative diseases was 51.4%, indicating the similarities in gait patterns between diseases need to be further explored. Overall, the differences between pathologic and healthy gait are distinct enough to classify using a classical machine learning model; however, routinely recorded gait characteristics and anthropometric data are not sufficient for successful discrimination of the degenerative diseases.

Hip abductor muscle strength in patients after total or unicompartmental knee arthroplasty for knee osteoarthritis or avascular necrosis: a systematic review and meta-analysis protocol

INTRODUCTION

Reduced hip abductor strength may indirectly lead to changes in knee kinematics and functional impairment and has been reported in patients with patellofemoral pain and knee osteoarthritis (OA). Limited information is available regarding hip abductor strength following total or unicompartmental knee arthroplasty (TKA/UKA). The aims of this systematic review are to synthesise the evidence of hip abductor muscle strength deficits in patients following TKA/UKA and to determine influencing factors for these deficits.

METHODS AND ANALYSIS

Embase, Medline, SportDiscus, the Web of Science Core Collection and Scopus will be searched for human-based clinical studies investigating hip abductor muscle strength after TKA/UKA for knee OA or avascular necrosis (AVN). Articles studying hip abductor strength after knee arthroplasty for post-traumatic OA will not be considered. No restriction on study design, prosthesis design, surgical approach, patient characteristics or severity of OA/AVN will be applied. We will search articles published between 1 January 1990 and the date of our last search. Only articles in English or German language will be considered for inclusion. Studies reporting manually measured muscle strength or measurements performed at hip abduction angles other than 0° will be excluded. References will be screened by two reviewers independently. Where necessary, a third author will make the final decision. The assessment of quality and risk of bias will be performed with the modified Newcastle-Ottawa scale. Data will be extracted and presented in a tabular form. Depending on availability, comparable subgroup and meta-analyses will be conducted. Patient characteristics such as age, sex and surgical approach or rehabilitation programme will be analysed, if sufficient data are available.

ETHICS AND DISSEMINATION

No ethics approval is required. The results will be published in a peer-reviewed journal and as conference presentation.