Explainable hypergraphs for gait based Parkinson classification

• Published in: Pattern recognition letters Vol. 186; pp. 198 - 204
• Main Authors: Choudhury, Anirban Dutta, Chowdhury, Ananda S.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-10-2024
• Subjects: Deep learning; Explainability; Gait data; Hypergraph; Parkinson classification; Hypergraph; Deep learning; Gait data; Parkinson classification; Explainability
• ISSN: 0167-8655
• DOI: 10.1016/j.patrec.2024.09.026

Parkinson Disease (PD) classification using Vertical Ground Reaction Force (VGRF) sensors can help in unobtrusive detection and monitoring of PD patients. State-of-the-art (SOTA) research in PD classification reveals that Deep Learning (DL), at the expense of explainability, performs better than Shallow Learning (SL). In this paper, we introduce a novel explainable weighted hypergraph, where the interconnections of the SOTA features are exploited, leading to more discriminative derived features, and thereby, forming an SL arm. In parallel, we create a DL arm consisting of ResNet architecture to learn the spatio-temporal patterns of the VGRF signals. Probabilities of PD classification scores from the SL and the DL arms are adaptively fused to create a hybrid pipeline. The pipeline achieves an AUC value of 0.979 on the Physionet Parkinson Dataset. This AUC value is found to be superior to the SL as well as the DL arm used in isolation, yielding respective AUCs of 0.878 and 0.852. The proposed pipeline demonstrates explainability through improved permutation feature importance and contrasting examples of use cases, where incorrect misclassification of the DL arm gets rectified by the SL arm and vice versa. We further demonstrate that our solution achieves comparable performance with SOTA methods. To the best of our knowledge, this is the first approach to analyze PD classification with a hypergraph based xAI (Explainable Artificial Intelligence).
•Addresses explainability in Parkinson classification from VGRF signals.•Proposes an explainable hypergraph constructed from state-of-the-art features.•Demonstrates a hybrid pipeline consisting of shallow and deep learning.•Exhibits model agnostic explainability reusable in other classification problems.