Detection and differentiation of ataxic and hypokinetic dysarthria in cerebellar ataxia and parkinsonian disorders via wave splitting and integrating neural networks

被引：8

作者：

Song, Joomee ^{[1
]}

Lee, Ju Hwan ^{[2
,3
]}

Choi, Jungeun ^{[2
]}

Suh, Mee Kyung ^{[1
]}

Chung, Myung Jin ^{[2
,4
,5
]}

Kim, Young Hun ^{[1
]}

Park, Jeongho ^{[1
]}

Choo, Seung Ho ^{[1
]}

Son, Ji Hyun ^{[1
]}

Lee, Dong Yeong ^{[1
]}

Ahn, Jong Hyeon ^{[1
]}

Youn, Jinyoung ^{[1
]}

Kim, Kyung-Su ^{[2
,5
]}

Cho, Jin Whan ^{[1
]}

机构：

[1] Sungkyunkwan Univ, Samsung Med Ctr, Dept Neurol & Neurosci Ctr, Sch Med, Seoul, South Korea

[2] Samsung Med Ctr, Med AI Res Ctr, Res Inst Future Med, Seoul, South Korea

[3] Sungkyunkwan Univ, Dept Hlth Sci & Technol, SAIHST, Seoul, South Korea

[4] Sungkyunkwan Univ, Samsung Med Ctr, Dept Radiol, Sch Med, Seoul, South Korea

[5] Sungkyunkwan Univ, Dept Data Convergence & Future Med, Sch Med, Seoul, South Korea

来源：

PLOS ONE | 2022年 / 17卷 / 06期

关键词：

PROGRESSIVE SUPRANUCLEAR PALSY; CLINICAL-DIAGNOSIS; DISEASE; SPEECH; SYSTEM; EPIDEMIOLOGY; PREVALENCE; FEATURES; SIGNALS;

D O I：

10.1371/journal.pone.0268337

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Dysarthria may present during the natural course of many degenerative neurological conditions. Hypokinetic and ataxic dysarthria are common in movement disorders and represent the underlying neuropathology. We developed an artificial intelligence (Al) model to distinguish ataxic dysarthria and hypokinetic dysarthria from normal speech and differentiate ataxic and hypokinetic speech in parkinsonian diseases and cerebellar ataxia. We screened 804 perceptual speech analyses performed in the Samsung Medical Center Neurology Department between January 2017 and December 2020. The data of patients diagnosed with parkinsonian disorders or cerebellar ataxia were included. Two speech tasks (numbering from 1 to 50 and reading nine sentences) were analyzed. We adopted convolutional neural networks and developed a patch-wise wave splitting and integrating Al system for audio classification (PWSI-Al-AC) to differentiate between ataxic and hypokinetic speech. Of the 395 speech recordings for the reading task, 76, 112, and 207 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. Of the 409 recordings of the numbering task, 82, 111, and 216 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. The reading and numbering task recordings were classified with 5-fold cross-validation using PWSI-Al-AC as follows: hypokinetic dysarthria vs. others (area under the curve: 0.92 +/- 0.01 and 0.92 +/- 0.02), ataxia vs. others (0.93 +/- 0.04 and 0.89 +/- 0.02), hypokinetic dysarthria vs. ataxia (0.96 +/- 0.02 and 0.95 +/- 0.01), hypokinetic dysarthria vs. none (0.86 +/- 0.03 and 0.87 +/- 0.05), and ataxia vs. none (0.87 +/- 0.07 and 0.87 +/- 0.09), respectively. PWSI-Al-AC showed reliable performance in differentiating ataxic and hypokinetic dysarthria and effectively augmented data to classify the types even with limited training samples. The proposed fully automatic Al system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases.

引用

页数：24

共 55 条

[1]

Abayomi-Alli OO, 2020, 2020 15 C COMPUTER S

[2] Sporadic adult onset ataxia of unknown etiology - A clinical, electrophysiological and imaging study [J].