The use of vocal biomarkers in the detection of Parkinson's disease: a robust statistical performance comparison of classic machine learning models

2025-11-20

AI Summary

This study addresses the need for non-invasive, low-cost early screening of Parkinson’s disease (PD) using speech-based biomarkers. We systematically compare deep neural networks (DNNs) against conventional machine learning methods for PD classification. Models are trained on Mel-frequency cepstral coefficients (MFCCs) extracted from two benchmark datasets: the Italian Speech Corpus and the Parkinson’s Disease Remote Monitoring Dataset. Robustness is evaluated via 1,000 independent random train-test splits, and statistical significance is rigorously assessed using the Kruskal–Wallis test with Bonferroni correction. Results show that DNNs achieve mean classification accuracies of 98.65% and 92.11% on the respective datasets—significantly outperforming all baseline models (p < 0.001). These findings demonstrate the superior stability and discriminative capacity of DNNs in speech biomarker analysis, establishing a generalizable deep learning framework for clinical decision support in PD diagnosis.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Evaluation and Analysis
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Parkinson's disease (PD) is a progressive neurodegenerative disorder that, in addition to directly impairing functional mobility, is frequently associated with vocal impairments such as hypophonia and dysarthria, which typically manifest in the early stages. The use of vocal biomarkers to support the early diagnosis of PD presents a non-invasive, low-cost, and accessible alternative in clinical settings. Thus, the objective of this cross-sectional study was to consistently evaluate the effectiveness of a Deep Neural Network (DNN) in distinguishing individuals with Parkinson's disease from healthy controls, in comparison with traditional Machine Learning (ML) methods, using vocal biomarkers. Two publicly available voice datasets were used. Mel-frequency cepstral coefficients (MFCCs) were extracted from the samples, and model robustness was assessed using a validation strategy with 1000 independent random executions. Performance was evaluated using classification statistics. Since normality assumptions were not satisfied, non-parametric tests (Kruskal-Wallis and Bonferroni post-hoc tests) were applied to verify whether the tested classification models were similar or different in the classification of PD. With an average accuracy of $98.65%$ and $92.11%$ on the Italian Voice dataset and Parkinson's Telemonitoring dataset, respectively, the DNN demonstrated superior performance and efficiency compared to traditional ML models, while also achieving competitive results when benchmarked against relevant studies. Overall, this study confirms the efficiency of DNNs and emphasizes their potential to provide greater accuracy and reliability for the early detection of neurodegenerative diseases using voice-based biomarkers.

Problem

• Comparing machine learning models for Parkinson's detection using vocal biomarkers
• Evaluating Deep Neural Network performance against traditional classification methods
• Assessing voice-based biomarkers for early Parkinson's disease diagnosis

Innovation

• Deep Neural Network for Parkinson's detection
• Vocal biomarkers enable non-invasive diagnosis
• MFCC features extracted from voice samples