Farrokhi Zahra, Zakavi Seyed Amirali, Sarafraz Arian, Valifard Maryam, Yousefzadeh Salar, Mashhadi Tafreshi Zahra, Anbiyaee Omid, Rostami Navid, Asadi Anar Mahsa, Deravi Niloofar
Student Research Committee, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Student Research Committee, Ardabil University of Medical Sciences, Ardabil, Iran.
eNeurologicalSci. 2025 Jul 30;40:100579. doi: 10.1016/j.ensci.2025.100579. eCollection 2025 Sep.
Amyotrophic Lateral Sclerosis (ALS) is a degenerative neurologic disease with no definitive biomarkers for early detection. This paper discusses the use of acoustic analysis of sustained vowel phonations (SVP) and machine learning in ALS detection.
An SVP corpus of 128 (64 /a/ and 64 /i/) from 31 patients with ALS and 33 healthy controls (HC) was employed. 131 acoustic features, including jitter, shimmer, Mel-Frequency Cepstral Coefficients (MFCCs), and Pathological Vibrato Index (PVI), were extracted. A LightGBM (Light Gradient Boosting Machine)-based model was built and optimized using 5-fold cross-validation to separate ALS cases. Model performance and feature importance were evaluated.
The model performed well with high predictability, yielding an RMSLE of 0.162 and most predictions closely correlating with actual diagnoses. The top features obtained were S55_i, CCI(2), and dCCa(12), which were consistently at the top of the ranking list, indicating their role in ALS detection. The PVI was determined to be a significant biomarker with high values having high correlations with ALS diagnoses. But the multimodal nature of the predictive values indicated some flaws in generalization.
This paper demonstrates the applicability of acoustic analysis and machine learning for early ALS detection. The proposed method provides an affordable, low-cost, and non-invasive way for ALS diagnosis with potential for application in telemedicine and clinical settings. Future research must expand datasets and integrate additional diagnostic modalities to improve the model's robustness and clinical translation.
肌萎缩侧索硬化症（ALS）是一种退行性神经疾病，尚无用于早期检测的确切生物标志物。本文讨论了持续元音发声（SVP）的声学分析和机器学习在ALS检测中的应用。
采用了一个包含31例ALS患者和33名健康对照（HC）的128个（64个/a/和64个/i/）SVP语料库。提取了131个声学特征，包括抖动、闪烁、梅尔频率倒谱系数（MFCC）和病理性颤音指数（PVI）。构建了一个基于LightGBM（轻梯度提升机）的模型，并使用5折交叉验证进行优化，以区分ALS病例。评估了模型性能和特征重要性。
该模型具有良好的预测性，均方根对数误差（RMSLE）为0.162，大多数预测与实际诊断密切相关。获得的顶级特征是S55_i、CCI(2)和dCCa(12)，它们始终排在排名列表的前列，表明它们在ALS检测中的作用。PVI被确定为一种重要的生物标志物，其高值与ALS诊断高度相关。但预测值的多模态性质表明在泛化方面存在一些缺陷。
本文证明了声学分析和机器学习在早期ALS检测中的适用性。所提出的方法为ALS诊断提供了一种经济、低成本且非侵入性的方法，具有在远程医疗和临床环境中应用的潜力。未来的研究必须扩大数据集并整合其他诊断方式，以提高模型的稳健性和临床转化能力。
