Journal of Alzheimer’s Disease ( IF 3.4 ) Pub Date : 2021-01-01 , DOI: 10.3233/jad-201101 Charalambos Themistocleous 1 , Bronte Ficek 1 , Kimberly Webster 1 , Dirk-Bart den Ouden 2 , Argye E Hillis 1 , Kyrana Tsapkini 1
Abstract
Background:
The classification of patients with primary progressive aphasia (PPA) into variants is time-consuming, costly, and requires combined expertise by clinical neurologists, neuropsychologists, speech pathologists, and radiologists.
Objective:
The aim of the present study is to determine whether acoustic and linguistic variables provide accurate classification of PPA patients into one of three variants: nonfluent PPA, semantic PPA, and logopenic PPA.
Methods:
In this paper, we present a machine learning model based on deep neural networks (DNN) for the subtyping of patients with PPA into three main variants, using combined acoustic and linguistic information elicited automatically via acoustic and linguistic analysis. The performance of the DNN was compared to the classification accuracy of Random Forests, Support Vector Machines, and Decision Trees, as well as to expert clinicians’ classifications.
Results:
The DNN model outperformed the other machine learning models as well as expert clinicians’ classifications with 80% classification accuracy. Importantly, 90% of patients with nfvPPA and 95% of patients with lvPPA was identified correctly, providing reliable subtyping of these patients into their corresponding PPA variants.
Conclusion:
We show that the combined speech and language markers from connected speech productions can inform variant subtyping in patients with PPA. The end-to-end automated machine learning approach we present can enable clinicians and researchers to provide an easy, quick, and inexpensive classification of patients with PPA.
中文翻译:
原发性进行性失语症个体的自动亚型
摘要
背景:
将原发性进行性失语症 (PPA) 患者分类为变种既费时又费钱,并且需要临床神经学家、神经心理学家、言语病理学家和放射科医师的综合专业知识。
客观的:
本研究的目的是确定声学和语言变量是否将 PPA 患者准确分类为三种变体之一:非流利 PPA、语义 PPA 和 logopenic PPA。
方法:
在本文中,我们提出了一种基于深度神经网络 (DNN) 的机器学习模型,使用通过声学和语言分析自动得出的组合声学和语言信息,将 PPA 患者分为三个主要变体。将 DNN 的性能与随机森林、支持向量机和决策树的分类准确性以及专家临床医生的分类进行了比较。
结果:
DNN 模型以 80% 的分类准确率优于其他机器学习模型以及专家临床医生的分类。重要的是,90% 的 nfvPPA 患者和 95% 的 lvPPA 患者被正确识别,从而将这些患者可靠地分型为相应的 PPA 变体。
结论:
我们表明,来自连接语音产品的组合语音和语言标记可以告知 PPA 患者的变异亚型。我们提出的端到端自动化机器学习方法可以使临床医生和研究人员能够对 PPA 患者进行简单、快速和廉价的分类。