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

Abstract

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 (AI) 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 AI system for audio classification (PWSI-AI-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-AI-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-AI-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 AI system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases.

Applied Machine Learning Techniques to Diagnose Voice-Affecting Conditions and Disorders: Systematic Literature Review

“…Combined: 20 [ 49 , 51 , 53 , 60 , 65 , 66 , 71 , 73 , 98 , 101 , 118 , 123 , 125 , 133 , 134 , 171 , 180 , 181 , 185 , 188 ]…”

Automatic stridor detection using small training set via patch-wise few-shot learning for diagnosis of multiple system atrophy

“…As a result, deterioration caused by this neurodegenerative disease may be mitigated at an early stage. Medical audio classification using AI and few training samples has previously been demonstrated [17][18][19][20][21][22] . However, our method is the first one to use few training samples for accurate classification of snoring and stridor using AI.…”

“…We achieve high diagnostic performance by applying textitfew-shot learning to binary classification using audio recordings in the medical field. Existing AI solutions [17][18][19][20][21][22] have performed audio classification without considering correlations between samples during inference, like in the baseline scheme illustrated in Fig. 2, which simply outputs a probability vector for the classes of an input sample while neglecting the similarity between samples.…”

“…After the last block, global average pooling 30 was applied to extract the 2D feature map of each channel. We used the same implementation reported by Song et al 22 . For training, we set the minibatch size to 8, the number of epochs to 500, the binary cross-entropy loss with an initial learning rate of 0.01, and an adaptive moment estimation 31 for optimization.…”

Ataxic speech disorders and Parkinson’s disease diagnostics via stochastic embedding of empirical mode decomposition

“…Secondly, if the data is unbalanced, the designed training and testing procedure combined with the classification method must handle such an issue to avoid introducing undesired bias. The standard practice followed by ASR methodologies is to refine standard glottal/voice features for the classification task or search for a more complex classifier based on deep learning techniques ( [30][31][32][33][34][35][36]). The third point is that [17] the ASR speech method should account for gender since male and female voices enclose distinct resonant frequencies of the vocal cords and a joint classification would reduce accuracy of the classifier.…”