A cross-language speech model for detection of Parkinson's disease

Wee Shin Lim; Shu-I Chiu; Pei-Ling Peng; Jyh-Shing Roger Jang; Sol-Hee Lee; Chin-Hsien Lin; Han-Joon Kim

doi:10.1007/s00702-024-02874-z

A cross-language speech model for detection of Parkinson's disease

J Neural Transm (Vienna). 2024 Dec 30. doi: 10.1007/s00702-024-02874-z. Online ahead of print.

Authors

Wee Shin Lim¹, Shu-I Chiu², Pei-Ling Peng³, Jyh-Shing Roger Jang¹, Sol-Hee Lee⁴, Chin-Hsien Lin^{5

6

7

8}, Han-Joon Kim⁹

Affiliations

¹ Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan.
² Department of Computer Science, National Chengchi University, Taipei, Taiwan.
³ Department of Neurology, College of Medicine, National Taiwan University Hospital, National Taiwan University, Taipei, 100, Taiwan.
⁴ Department of Neurology, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, Korea.
⁵ Department of Neurology, College of Medicine, National Taiwan University Hospital, National Taiwan University, Taipei, 100, Taiwan. chlin@ntu.edu.tw.
⁶ Colleague of Medicine, National Taiwan University, Taipei, Taiwan. chlin@ntu.edu.tw.
⁷ Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan. chlin@ntu.edu.tw.
⁸ Institute of Molecular Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan. chlin@ntu.edu.tw.
⁹ Department of Neurology, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, Korea. movement@snu.ac.kr.

PMID: 39739129
DOI: 10.1007/s00702-024-02874-z

Abstract

Speech change is a biometric marker for Parkinson's disease (PD). However, evaluating speech variability across diverse languages is challenging. We aimed to develop a cross-language algorithm differentiating between PD patients and healthy controls using a Taiwanese and Korean speech data set. We recruited 299 healthy controls and 347 patients with PD from Taiwan and Korea. Participants with PD underwent smartphone-based speech recordings during the "on" phase. Each Korean participant performed various speech texts, while the Taiwanese participant read a standardized, fixed-length article. Korean short-speech (≦15 syllables) and long-speech (> 15 syllables) recordings were combined with the Taiwanese speech dataset. The merged dataset was split into a training set (controls vs. early-stage PD) and a validation set (controls vs. advanced-stage PD) to evaluate the model's effectiveness in differentiating PD patients from controls across languages based on speech length. Numerous acoustic and linguistic speech features were extracted and combined with machine learning algorithms to distinguish PD patients from controls. The area under the receiver operating characteristic (AUROC) curve was calculated to assess diagnostic performance. Random forest and AdaBoost classifiers showed an AUROC 0.82 for distinguishing patients with early-stage PD from controls. In the validation cohort, the random forest algorithm maintained this value (0.90) for discriminating advanced-stage PD patients. The model showed superior performance in the combined language cohort (AUROC 0.90) than either the Korean (AUROC 0.87) or Taiwanese (AUROC 0.88) cohorts individually. However, with another merged speech data set of short-speech recordings < 25 characters, the diagnostic performance to identify early-stage PD patients from controls dropped to 0.72 and showed a further limited ability to discriminate advanced-stage patients. Leveraging multifaceted speech features, including both acoustic and linguistic characteristics, could aid in distinguishing PD patients from healthy individuals, even across different languages.

Keywords: Biomarkers; Deep-learning model; Face; Parkinson’s disease; Speech.

Abstract

Grants and funding