Citation

Farfoura, Mahmoud E. and Alkhatib, Ahmad A. A. and Tee, Connie (2026) Self-Explaining Neural Networks for Transparent Parkinson’s Disease Screening. Sensors, 26 (9). p. 2671. ISSN 1424-8220

Text sensors-26-02671.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

first_pagesettingsOrder Article Reprints Open AccessArticle Self-Explaining Neural Networks for Transparent Parkinson’s Disease Screening by Mahmoud E. Farfoura 1,*ORCID,Ahmad A. A. Alkhatib 1 andTee Connie 2,*ORCID 1 Cybersecurity Department, Al-Zaytoonah University of Jordan, Amman 11733, Jordan 2 Faculty of Information Science & Technology, Multimedia University, Jalan Ayer Keroh Lama, Melaka 75450, Malaysia * Authors to whom correspondence should be addressed. Sensors 2026, 26(9), 2671; https://doi.org/10.3390/s26092671 Submission received: 22 February 2026 / Revised: 14 April 2026 / Accepted: 21 April 2026 / Published: 25 April 2026 (This article belongs to the Section Electronic Sensors) Downloadkeyboard_arrow_down Browse Figures Review Reports Versions Notes Abstract Transparent clinical decision-making remains a critical barrier to deploying deep learning in medical diagnosis. Post hoc explanation methods approximate model behaviour after training but cannot guarantee that explanations faithfully reflect the underlying reasoning. This study proposes a Self-Explaining Neural Network (SENN) for Parkinson’s Disease (PD) screening via Ground Reaction Force (GRF) gait analysis, enforcing intrinsic interpretability through learnable basis concepts and input-dependent relevance scores computed jointly with the prediction. The architecture combines a four-block residual CNN backbone with stochastic depth regularisation, a 16-concept encoder with diversity and stability constraints, and temperature-scaled probability calibration for reliable clinical operating points. Evaluated on the PhysioNet Gait in Parkinson’s Disease dataset (306 subjects, 16 GRF sensors per foot), SENN achieves a subject-level ROC-AUC of 0.916 [95% CI: 0.867–0.964], sensitivity of 0.913 [0.862–0.963], specificity of 0.671 [0.485–0.858], and Average Precision of 0.942 [0.918–0.967], reported across five independent random seeds. Comparative evaluation against four deep learning baselines—CNN-Residual, BiLSTM, CNN-LSTM, and CNN-Attention—confirms that the interpretability constraints impose no statistically significant reduction in discriminative performance, with all pairwise ROC-AUC confidence intervals overlapping. Concept-level analysis reveals that the three most discriminative concepts correspond to disrupted midfoot loading patterns, increased step-length variability, and bilateral cadence asymmetry—all established biomechanical hallmarks of parkinsonian gait—providing clinically grounded, patient-specific explanations without post hoc approximation. These findings demonstrate that rigorous intrinsic interpretability and competitive predictive accuracy are simultaneously achievable in deep gait analysis, supporting the clinical adoption of transparent diagnostic AI.

Item Type:	Article
Uncontrolled Keywords:	Parkinson’s disease detection, self-explaining neural networks
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science R Medicine > R Medicine (General) > R858-859.7 Computer applications to medicine. Medical informatics
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	05 Jun 2026 06:37
Last Modified:	05 Jun 2026 06:37
URII:	http://shdl.mmu.edu.my/id/eprint/16042

Downloads

Edit (login required)