Automated detection and explainability of pathological gait patterns using a one-class support vector machine trained on inertial measurement unit based gait data

Abstract

Background: Machine learning approaches for the classification of pathological gait based on kinematic data, e.g. derived from inertial sensors, are commonly used in terms of a multi-class classification problem. However, there is a lack of research regarding one-class classifiers that are independent of certain pathologies. Therefore, it was the aim of this work to design a one-class classifier based on healthy norm-data that provides not only a prediction probability but rather an explanation of the classification decision, increasing the acceptance of this machine learning approach. Methods: The inertial sensor based gait kinematics of 25 healthy subjects was employed to train a one-class support vector machine. 25 healthy subjects, 20 patients after total hip arthroplasty and one transfemoral amputee served to validate the classifier. Prediction probabilities and feature importance scores were estimated for each subject. Findings: The support vector machine predicted 100% of the patients as outliers from the healthy group. Three healthy subjects were predicted as outliers. The feature importance calculation revealed the hip in the sagittal plane as most relevant feature concerning the group after total hip arthroplasty. For the misclassified healthy subject with the lowest probability score the knee flexion and the pelvis obliquity were identified. Interpretation: The support vector machine seems a useful tool to identify outliers from a healthy norm-group. The feature importance examination proved to provide valuable information on the musculoskeletal status of the subjects. In this combination, the present approach could be employed in various disciplines to identify abnormal gait and suggest subsequent training.

Conceptual structure and current trends in Artificial Intelligence, Machine Learning, and Deep Learning research in sports: A bibliometric review

“…At this point, it should be noted that our analysis probably does not depict topics that have arisen very recently. For example, few recent publications have addressed the black-box character of AI models [96, 97], which does not comply with the General Data Protection Regulation (GDPR) [98], using explainable AI. However, this theme does not appear as a trend topic using the author keywords at present, although it may be visible in a bibliometric analysis in the next few years.…”

Machine Learning and Explainable Artificial Intelligence using Counterfactual Explanations for Evaluating Posture Parameters

“…Another practical limitation is that the resulting models can only recognize characteristics for which they have been trained (here, hyperlordosis and hyperkyphosis) and are therefore pathology-dependent. Recently, interpretable, pathology-independent classifiers have been proposed to deal with this limitation [16,49]. Transferring the methodology of the present study to these classifiers could potentially create a powerful tool and could further increase the practical relevance of the ML methodology in biomechanical research.…”

Machine Learning and Explainable Artificial Intelligence Using Counterfactual Explanations for Evaluating Posture Parameters

“…Another practical limitation is that the resulting models can only recognize characteristics for which they have been trained (here, hyperlordosis and hyperkyphosis) and are therefore pathology-dependent. Recently, interpretable, pathologyindependent classifiers have been proposed to deal with this limitation [16,59].…”