Machine learning-based classification of Parkinson's disease using acoustic features: Insights from multilingual speech tasks.

This study advances the automation of Parkinson's disease (PD) diagnosis by analyzing speech characteristics, leveraging a comprehensive approach that integrates a voting-based machine learning model. Given the growing prevalence of PD, especially among the elderly population, continuous and efficient diagnosis is of paramount importance. Conventional monitoring methods suffer from limitations related to time, cost, and accessibility, underscoring the need for the development of automated diagnostic tools. In this paper, we present a robust model for classifying speech patterns in Korean PD patients, addressing a significant research gap. Our model employs straightforward preprocessing techniques and a voting-based machine learning approach, demonstrating superior performance, particularly when training data is limited. Furthermore, we emphasize the effectiveness of the eGeMAPSv2 feature set in PD analysis and introduce new features that substantially enhance classification accuracy. The proposed model, achieving an accuracy of 84.73 % and an area under the ROC (AUC) score of 92.18 % on a dataset comprising 100 Korean PD patients and 100 healthy controls, offers a practical solution for automated diagnosis applications, such as smartphone apps. Future research endeavors will concentrate on enhancing the model's performance and delving deeper into the relationship between high-importance features and PD.
Competing Interests: Declaration of competing interest We, the authors of the manuscript titled "Machine Learning-Based Classification of Parkinson's Disease Using Acoustic Features: Insights from Multilingual Speech Tasks," declare that we have no conflicts of interest or financial interests that could be construed as influencing the research presented in this paper. We confirm that the research presented in this manuscript was conducted impartially, and we have not received any financial support or incentives that might create a conflict of interest with the results and conclusions of this research. Our primary aim is to contribute to the field of Parkinson's disease diagnosis using machine learning and acoustic features, and we have adhered to ethical standards and best practices throughout the research process. If, in the future, any potential conflicts of interest arise related to this work, we commit to promptly disclosing them to the relevant parties. We have submitted this manuscript to "Computers in Biology and Medicine" with the understanding that the information provided in this Declaration of Interest Statement accurately represents our current affiliations and interests.
(Copyright © 2024 Elsevier Ltd. All rights reserved.)