Kang Kyurim, Nunes Adonay S, Potter Ilkay Yildiz, Mishra Ram Kinker, Geronimo Andrew, Adams Jamie L, Isroff Catherine, Wang Jesse E, Vaziri Ashkan, Wills Anne-Marie, Pantelyat Alexander
Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
BioSensics LLC, 57 Chapel St, Newton, MA, USA.
Clin Park Relat Disord. 2025 Aug 28;13:100389. doi: 10.1016/j.prdoa.2025.100389. eCollection 2025.
Speech impairment is a prevalent symptom of neurological disorders, including Parkinson's disease (PD), Progressive Supranuclear Palsy (PSP), Huntington's disease (HD), and Amyotrophic Lateral Sclerosis (ALS), with mechanisms and severity varying across and within conditions. Scalable digital health tools and machine learning (ML) are essential for diagnosing and tracking neurodegenerative disease.
A total of 92 individuals were included in this study (21 PSP, 21 PD, 18 HD, 15 ALS, and 16 healthy elderly controls (CTR)). The Rainbow Passage was collected on a digital device and analyzed to extract 12 speech features representing speech production. A set of Elastic Net ML models was trained on these speech features to differentiate between diagnostic classes. A specialized Support Vector Machine ML model was then developed to differentiate PSP from PD.
Elastic Net models achieved a balanced accuracy of 77% over 5 diagnostic classes (group-specific sensitivities of 76% for PSP, 67% for PD, 83% for HD, 73% for ALS, and 88% for CTR) and 83% over 4 diagnostic classes (group-specific sensitivities of 83% for PSP-PD, 83% for HD, 73% for ALS, and 94% for CTR). The PSP vs. PD classification model demonstrated a balanced accuracy of 85%, with sensitivity of 88% for PSP and 82% for PD. Key speech features differentiated clinical conditions, with being the strongest positive feature for combined PSP-PD. In HD, ALS, and CTR, , and were the most strongly differentiating features, respectively. emerged as the most distinguishing feature between PD and PSP.
Our findings highlight the potential of digital health technology and ML in identifying and monitoring speech features in neurodegenerative diseases.
言语障碍是包括帕金森病（PD）、进行性核上性麻痹（PSP）、亨廷顿舞蹈病（HD）和肌萎缩侧索硬化症（ALS）在内的神经系统疾病的常见症状，其机制和严重程度在不同疾病及同一疾病内部存在差异。可扩展的数字健康工具和机器学习（ML）对于神经退行性疾病的诊断和跟踪至关重要。
本研究共纳入92名个体（21名PSP患者、21名PD患者、18名HD患者、15名ALS患者和16名健康老年对照（CTR））。通过数字设备收集《彩虹段落》并进行分析，以提取代表言语产生的12个言语特征。基于这些言语特征训练了一组弹性网络ML模型，以区分不同诊断类别。随后开发了一种专门的支持向量机ML模型，以区分PSP和PD。
弹性网络模型在5个诊断类别上的平衡准确率达到77%（PSP的组特异性敏感性为76%，PD为67%，HD为83%，ALS为73%，CTR为88%），在4个诊断类别上的平衡准确率为83%（PSP-PD的组特异性敏感性为83%，HD为83%，ALS为73%，CTR为94%）。PSP与PD分类模型的平衡准确率为85%，PSP的敏感性为88%，PD的敏感性为82%。关键言语特征可区分临床状况， 是PSP-PD组合的最强正向特征。在HD、ALS和CTR中， 、 和 分别是最具区分性的特征。 成为PD和PSP之间最具区分性的特征。
我们的研究结果凸显了数字健康技术和ML在识别和监测神经退行性疾病言语特征方面的潜力。
