Lim Wee Shin, Chiu Shu-I, Peng Pei-Ling, Jang Jyh-Shing Roger, Lee Sol-Hee, Lin Chin-Hsien, Kim Han-Joon
Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan.
Department of Computer Science, National Chengchi University, Taipei, Taiwan.
J Neural Transm (Vienna). 2025 Apr;132(4):579-590. doi: 10.1007/s00702-024-02874-z. Epub 2024 Dec 30.
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.
语音变化是帕金森病（PD）的一种生物特征标记。然而，评估不同语言间的语音变异性具有挑战性。我们旨在开发一种跨语言算法，利用台湾地区和韩国的语音数据集区分PD患者和健康对照。我们从台湾地区和韩国招募了299名健康对照和347名PD患者。PD患者在“开”期通过智能手机进行语音录音。每位韩国参与者执行各种语音文本，而台湾地区参与者阅读一篇标准化的固定长度文章。韩国的短语音（≦15个音节）和长语音（> 15个音节）录音与台湾地区语音数据集合并。合并后的数据集被分为训练集（对照与早期PD）和验证集（对照与晚期PD），以评估该模型基于语音长度在不同语言中区分PD患者和对照的有效性。提取了大量声学和语言语音特征，并与机器学习算法相结合以区分PD患者和对照。计算受试者工作特征（AUROC）曲线下面积以评估诊断性能。随机森林和AdaBoost分类器在区分早期PD患者和对照方面的AUROC为0.82。在验证队列中，随机森林算法在区分晚期PD患者时保持该值（0.90）。该模型在合并语言队列（AUROC 0.90）中的表现优于韩国队列（AUROC 0.87）或台湾地区队列（AUROC 0.88）单独的表现。然而，对于另一个字符数< 25的短语音录音合并语音数据集，从对照中识别早期PD患者的诊断性能降至0.72，并且区分晚期患者的能力进一步受限。利用包括声学和语言特征在内的多方面语音特征，即使在不同语言之间，也有助于区分PD患者和健康个体。
