Explainable Parkinson’s Disease Detection Using PaHaW Handwriting Signals and Novel Motion Biomarkers

DOI

10.2991/978-94-6239-723-1_32How to use a DOI?

Keywords

Parkinson’s illness; PaHaW Dataset; SVM Methodology

Abstract

This study provides a new explainable framework for handwriting-based classification of Parkinson’s disease with five domain-specific markers; (Tremor power Score (TPS), Air-Writing Complexity Index (AWCI), Pressure Instability Coefficient (PIC), Stroke Irregularity Ratio (SIR) and Micro-Motion Variance (MMV) as pathological novelty to account for frequency-domain tremor energy, lifted-pen motion entropy, grip-pressure instability, directional stroke deformation, and transition-phase kinematic noise, respectively. These biomarkers supplement the 86-feature representation, enhancing the clinical interpretability of certain features while remaining within a computationally pragmatic framework. We have evaluated five classifiers using discrimination and agreement metrics. Gradient Boosting had the greatest overall accuracy (0.696) and specificity (0.8182, TN = 54, FP = 12), indicating reliable healthy handwriting recognition and confident PD predictions (PPV = 0.7333). Logistic Regression identified the highest number of PD cases (TP = 37, sensitivity = 0.6271) and obtained the best harmonic precision-recall balance (F1 = 0.6491); confirming non-linearities in the PaHaW handwriting impairments from motor interactions coupled with partially linear pathological drifts throughout the handwriting period.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pranali Balkrishna Kashid
AU  - Pallavi Sagar Deshpande
PY  - 2026
DA  - 2026/07/14
TI  - Explainable Parkinson’s Disease Detection Using PaHaW Handwriting Signals and Novel Motion Biomarkers
BT  - Proceedings of the International Conference on Responsible, Risk-aware, and Regulated AI (RRRAI 2026)
PB  - Atlantis Press
SP  - 352
EP  - 365
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-723-1_32
DO  - 10.2991/978-94-6239-723-1_32
ID  - Kashid2026
ER  -