Parkinson’s Disease Detection Using Keystroke Dynamics with PSO-Based Feature Selection and Ensemble Voting Classifier

DOI

10.2991/978-94-6463-948-3_19How to use a DOI?

Keywords

Parkinson's Disease; Keystroke Dynamics; Particle Swarm Optimization (PSO); Machine Learning; Ensemble Classifier; Non-Invasive Diagnosis

Abstract

Parkinson's Disease (PD) requires early, objective diagnosis, often hindered by subjective clinical assessments. This paper presents a novel, non-invasive PD screening system leveraging keystroke dynamics, a behavioral biometric, to quantify subtle motor deficiencies. Statistical features, including mean hold and flight times, were extracted from user typing logs. To enhance model efficiency and interpretability, Particle Swarm Optimization (PSO) was applied, identifying three optimal features. The resulting Ensemble Voting Classifier achieved superior diagnostic performance, demonstrating 99.2% accuracy and a critical 100% Recall on the test set. The methodology incorporates SMOTE for class imbalance mitigation and is rigorously benchmarked against advanced Deep Learning architectures (LSTM/Bi-LSTM), validating the efficiency of the feature-engineered approach. We include a mandatory discussion on ethical safeguards, prioritizing the minimization of False Negatives (FN = 0) essential for responsible clinical application. The final, high-performance model is deployed via a user-friendly Flask web application with a real-time typing test module, offering a scalable, accessible tool for preliminary PD screening.

Copyright

© 2025 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  - Gargi Padate
AU  - Samruddhi Chavan
AU  - Deepa Abin
PY  - 2026
DA  - 2026/01/06
TI  - Parkinson’s Disease Detection Using Keystroke Dynamics with PSO-Based Feature Selection and Ensemble Voting Classifier
BT  - Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
PB  - Atlantis Press
SP  - 265
EP  - 286
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-948-3_19
DO  - 10.2991/978-94-6463-948-3_19
ID  - Padate2026
ER  -