Open Access

ARTICLE

A Convolutional Neural Network-Based Deep Support Vector Machine for Parkinson’s Disease Detection with Small-Scale and Imbalanced Datasets

Kwok Tai Chui^1,*, Varsha Arya¹, Brij B. Gupta^2,3,4,*, Miguel Torres-Ruiz⁵, Razaz Waheeb Attar⁶

1 School of Science and Technology, Hong Kong Metropolitan University, Hong Kong, China
2 Department of Computer Science and Information Engineering, Asia University, Taichung, 41354, Taiwan
3 Department of Medical Research, China Medical University Hospital, China Medical University, Taichung, 40447, Taiwan
4 Symbiosis Centre for Information Technology (SCIT), Symbiosis International University, Pune, 411057, India
5 Instituto Politécnico Nacional, CIC, UPALM-Zacatenco, Mexico City, 07320, Mexico
6 Management Department, College of Business Administration, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia

* Corresponding Authors: Kwok Tai Chui. Email: ; Brij B. Gupta. Email:

(This article belongs to the Special Issue: Emerging Trends and Applications of Deep Learning for Biomedical Signal and Image Processing)

Computers, Materials & Continua 2026, 86(1), 1-23. https://doi.org/10.32604/cmc.2025.068842

Received 07 June 2025; Accepted 25 September 2025; Issue published 10 November 2025

Abstract

Parkinson’s disease (PD) is a debilitating neurological disorder affecting over 10 million people worldwide. PD classification models using voice signals as input are common in the literature. It is believed that using deep learning algorithms further enhances performance; nevertheless, it is challenging due to the nature of small-scale and imbalanced PD datasets. This paper proposed a convolutional neural network-based deep support vector machine (CNN-DSVM) to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets. A customized kernel function reduces the impact of biased classification towards the majority class (healthy candidates in our consideration). An improved generative adversarial network (IGAN) was designed to generate additional training data to enhance the model’s performance. For performance evaluation, the proposed algorithm achieves a sensitivity of 97.6% and a specificity of 97.3%. The performance comparison is evaluated from five perspectives, including comparisons with different data generation algorithms, feature extraction techniques, kernel functions, and existing works. Results reveal the effectiveness of the IGAN algorithm, which improves the sensitivity and specificity by 4.05%–4.72% and 4.96%–5.86%, respectively; and the effectiveness of the CNN-DSVM algorithm, which improves the sensitivity by 1.24%–57.4% and specificity by 1.04%–163% and reduces biased detection towards the majority class. The ablation experiments confirm the effectiveness of individual components. Two future research directions have also been suggested.

---

Keywords

---