Improving Handwriting-Based Parkinson’s Disease Classification Through Transfer Learning and Generative Data Augmentation
Gallo-Aristizabal JD, Escobar-Grisales D, Ríos-Urrego CD, Vargas-Bonilla JF, Orozco-Arroyave JR (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 2701 CCIS
Pages Range: 167-179
Conference Proceedings Title: Communications in Computer and Information Science
Event location: Cali, COL
ISBN: 9783032082022
DOI: 10.1007/978-3-032-08203-9_14
Abstract
Parkinson’s disease (PD) is a neurodegenerative disorder that leads to various motor impairments, including bradykinesia, muscular rigidity, and resting tremor. These symptoms affect fine motor skills including handwriting. One possible way to model this biosignal is with deep learning methods; however the lack of large enough annotated datasets imposes a major challenge in this topic. This paper focuses on using data augmentation (DA) and transfer learning (TL) techniques to improve the classification performance of PD patients vs. healthy control (HC) subjects across five handwriting tasks. Three methodological approaches were explored: (1) a baseline, (2) DA and TL using micrographia emulation with EMNIST characters, and (3) denoising diffusion probabilistic model (DDPM). Among these approaches, the second one achieved the highest classification accuracy of 67%, representing a 9.7% improvement over the baseline. The DDPM method provided moderate improvements, particularly in tasks that were shape-similar to the pretraining data (e.g., Numbers and ID), achieving accuracy gains of up to 8.7%. Overall, the findings suggest that incorporating domain-specific TL strategies and generative models like DDPMs help in addressing data scarcity and enhancing classification performance.
Involved external institutions
Colombia (CO)How to cite
APA:
Gallo-Aristizabal, J.D., Escobar-Grisales, D., Ríos-Urrego, C.D., Vargas-Bonilla, J.F., & Orozco-Arroyave, J.R. (2026). Improving Handwriting-Based Parkinson’s Disease Classification Through Transfer Learning and Generative Data Augmentation. In Juan Carlos Figueroa-García, Elvis Eduardo Gaona-García, Jesús Alfonso López-Sotelo, John Freddy Moreno-Trujillo (Eds.), Communications in Computer and Information Science (pp. 167-179). Cali, COL: Springer Science and Business Media Deutschland GmbH.
MLA:
Gallo-Aristizabal, Jeferson David, et al. "Improving Handwriting-Based Parkinson’s Disease Classification Through Transfer Learning and Generative Data Augmentation." Proceedings of the 12th Workshop on Engineering Applications, WEA 2025, Cali, COL Ed. Juan Carlos Figueroa-García, Elvis Eduardo Gaona-García, Jesús Alfonso López-Sotelo, John Freddy Moreno-Trujillo, Springer Science and Business Media Deutschland GmbH, 2026. 167-179.
BibTeX: Download