Explaining Machine Learning Models for Clinical Gait Analysis

Abstract

Machine Learning (ML) is increasingly used to support decision-making in the healthcare sector. While ML approaches provide promising results with regard to their classification performance, most share a central limitation, their black-box character. This article investigates the usefulness of Explainable Artificial Intelligence (XAI) methods to increase transparency in automated clinical gait classification based on time series. For this purpose, predictions of state-of-the-art classification methods are explained with a XAI method called Layer-wise Relevance Propagation (LRP). Our main contribution is an approach that explains class-specific characteristics learned by ML models that are trained for gait classification. We investigate several gait classification tasks and employ different classification methods, i.e., Convolutional Neural Network, Support Vector Machine, and Multi-layer Perceptron. We propose to evaluate the obtained explanations with two complementary approaches: a statistical analysis of the underlying data using Statistical Parametric Mapping and a qualitative evaluation by two clinical experts. A gait dataset comprising ground reaction force measurements from 132 patients with different lower-body gait disorders and 62 healthy controls is utilized. Our experiments show that explanations obtained by LRP exhibit promising statistical properties concerning inter-class discriminativity and are also in line with clinically relevant biomechanical gait characteristics.

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

“…2. One of the significant drawbacks of XAI-based AD diagnosis is the absence of ground truth data [164]. Several neuroimaging and clinical biomarker datasets exist for AD, but none provide ground truth to validate the explainability elicited by XAI models.…”

Explainable AI for clinical and remote health applications: a survey on tabular and time series data

“…Results demonstrate that the proposed FCN model is accurate in locating relevant time points in both case studies, and it is also more consistent as it indicates mostly the same time steps as relevant for its predictions when trained with different random initialisation. Slijepcevic et al (2021) proposed a complementary strategy to evaluate class-specific explanations for gait classification from 3-D ground reaction force (GRF) sensors data, including both quantitative and qualitative analysis. To this aim, they first trained CNN, SVM, and MLP classifiers on the GaitRec dataset (Horsak et al 2020), a clinical database including bilateral GRF measurements from 132 patients with 3 classes of orthopedic gait disorders and from 62 healthy controls, then LRP technique has been used to explain the most relevant signal characteristics learned by the models.…”

Understanding person identification via gait

“…Alvarez Melis and Jaakkola [32] proposes faithfulness as an important metric for evaluating explainable machine learning, which is measured by removing/perturbing the feature and then measuring the drop in classification performance. Explainable machine learning has been used to analyze gait patterns for clinical analysis [33]. Horst et al [34] used LRP to study which part of the gait cycle is relevant to a non-linear machine learning model to recognize an individual.…”