Ali Liaqat, He Zhiquan, Cao Wenming, Rauf Hafiz Tayyab, Imrana Yakubu, Bin Heyat Md Belal
Department of Electrical Engineering, University of Science and Technology, Bannu, Pakistan.
Guangdong Multimedia Information Service Engineering Technology Research Center, Shenzhen University, Shenzhen, China.
Front Neurosci. 2021 Nov 1;15:754058. doi: 10.3389/fnins.2021.754058. eCollection 2021.
Parkinson's disease (PD) is the second most common neurological disease having no specific medical test for its diagnosis. In this study, we consider PD detection based on multimodal voice data that was collected through two channels, i.e., Smart Phone (SP) and Acoustic Cardioid (AC). Four types of data modalities were collected through each channel, namely sustained phonation (P), speech (S), voiced (V), and unvoiced (U) modality. The contributions of this paper are twofold. First, it explores optimal data modality and features having better information about PD. Second, it proposes a MultiModal Data-Driven Ensemble (MMDD-Ensemble) approach for PD detection. The MMDD-Ensemble has two levels. At the first level, different base classifiers are developed that are driven by multimodal voice data. At the second level, the predictions of the base classifiers are fused using blending and voting methods. In order to validate the robustness of the propose method, six evaluation measures, namely accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and area under the curve (AUC), are adopted. The proposed method outperformed the best results produced by optimal unimodal framework from both the key evaluation aspects, i.e., accuracy and AUC. Furthermore, the proposed method also outperformed other state-of-the-art ensemble models. Experimental results show that the proposed multimodal approach yields 96% accuracy, 100% sensitivity, 88.88% specificity, 0.914 of MCC, and 0.986 of AUC. These results are promising compared to the recently reported results for PD detection based on multimodal voice data.
帕金森病（PD）是第二常见的神经系统疾病，目前尚无针对其诊断的特定医学检测方法。在本研究中，我们考虑基于通过智能手机（SP）和心形麦克风（AC）这两个通道收集的多模态语音数据进行帕金森病检测。通过每个通道收集了四种数据模态，即持续发声（P）、语音（S）、浊音（V）和清音（U）模态。本文的贡献有两个方面。首先，它探索了关于帕金森病具有更好信息的最优数据模态和特征。其次，它提出了一种用于帕金森病检测的多模态数据驱动集成（MMDD - 集成）方法。MMDD - 集成有两个层次。在第一个层次，开发了由多模态语音数据驱动的不同基分类器。在第二个层次，使用混合和投票方法融合基分类器的预测结果。为了验证所提出方法的鲁棒性，采用了六种评估指标，即准确率、灵敏度、特异性、马修斯相关系数（MCC）和曲线下面积（AUC）。从准确率和AUC这两个关键评估方面来看，所提出的方法优于最优单模态框架产生的最佳结果。此外，所提出的方法也优于其他现有最先进的集成模型。实验结果表明，所提出的多模态方法的准确率为96%，灵敏度为100%，特异性为88.88%，MCC为0.914，AUC为0.986。与最近报道的基于多模态语音数据的帕金森病检测结果相比，这些结果很有前景。
