Improving AI Interpretability for Multilingual Parkinson’s Disease Classification through Voice Analysis
Hemmerling D, Zakrzewski M, Wodzinski M, Dudek M, Gaciarz F, Wojcik-Pedziwiatr M, Orozco-Arroyave JR, Nöth E, Sztaho D, Rumezhak T (2025)
Publication Type: Conference contribution
Publication year: 2025
Publisher: ML Research Press
Book Volume: 281
Pages Range: 49-55
Conference Proceedings Title: Proceedings of Machine Learning Research
Event location: Philadelphia, PA, USA
Abstract
Addressing the imperative need for interpretability in medical models based on machine learning and artificial intelligence, our study focuses on the crucial task of Parkinson’s disease detection. In this paper, we introduce a vision transformer incorporating multilingual vowel phonations, achieving a classification accuracy of 89%. To enrich the input representation for vision transformer, we utilized images of mel-spectrograms and regular spectrograms. The success of our model goes beyond performance metrics, as we strategically integrate explainable artificial intelligence techniques. The synergy between robust classification results and explainability underscores the effectiveness of our approach in opening the black-box nature of neural networks. This, in turn, contributes to enhanced medical decision-making and reinforces the potential of artificial intelligence in advancing diagnostic methodologies for Parkinson’s disease.
Authors with CRIS profile
Involved external institutions
University of Science and Technology (AGH) / Akademia Górniczo-Hutnicza
Poland (PL)
Andrzej Frycz Modrzewski Krakow University / Krakowska Akademia im. Andrzeja Frycza Modrzewskiego
Poland (PL)
Universidad de Antioquía (UDEA)
Colombia (CO)
Budapest University of Technology and Economics (BME) / Budapesti Műszaki és Gazdaságtudományi Egyetem
Hungary (HU)
Poland (PL)
Andrzej Frycz Modrzewski Krakow University / Krakowska Akademia im. Andrzeja Frycza Modrzewskiego
Poland (PL)
Universidad de Antioquía (UDEA)
Colombia (CO)
Budapest University of Technology and Economics (BME) / Budapesti Műszaki és Gazdaságtudományi Egyetem
Hungary (HU)
How to cite
APA:
Hemmerling, D., Zakrzewski, M., Wodzinski, M., Dudek, M., Gaciarz, F., Wojcik-Pedziwiatr, M.,... Rumezhak, T. (2025). Improving AI Interpretability for Multilingual Parkinson’s Disease Classification through Voice Analysis. In Junde Wu, Jiayuan Zhu, Min Xu, Yueming Jin (Eds.), Proceedings of Machine Learning Research (pp. 49-55). Philadelphia, PA, USA: ML Research Press.
MLA:
Hemmerling, Daria, et al. "Improving AI Interpretability for Multilingual Parkinson’s Disease Classification through Voice Analysis." Proceedings of the 1st AAAI Bridge Program on AI for Medicine and Healthcare, Philadelphia, PA, USA Ed. Junde Wu, Jiayuan Zhu, Min Xu, Yueming Jin, ML Research Press, 2025. 49-55.
BibTeX: Download