دورية أكاديمية
أعرض في EDS

Convolutional neural network ensemble for Parkinson's disease detection from voice recordings.

التفاصيل البيبلوغرافية
العنوان: Convolutional neural network ensemble for Parkinson's disease detection from voice recordings.
المؤلفون: Hireš M; Intelligent Information Systems Lab, Technical University of Košice, Letná 9, 42001, Košice, Slovakia., Gazda M; Intelligent Information Systems Lab, Technical University of Košice, Letná 9, 42001, Košice, Slovakia., Drotár P; Intelligent Information Systems Lab, Technical University of Košice, Letná 9, 42001, Košice, Slovakia. Electronic address: peter.drotar@tuke.sk., Pah ND; University of Surabaya, Indonesia; RMIT, Australia., Motin MA; RMIT, Australia., Kumar DK; RMIT, Australia.
المصدر: Computers in biology and medicine [Comput Biol Med] 2022 Feb; Vol. 141, pp. 105021. Date of Electronic Publication: 2021 Nov 09.
نوع المنشور: Journal Article; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: Elsevier Country of Publication: United States NLM ID: 1250250 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-0534 (Electronic) Linking ISSN: 00104825 NLM ISO Abbreviation: Comput Biol Med Subsets: MEDLINE
أسماء مطبوعة: Publication: New York : Elsevier
Original Publication: New York, Pergamon Press.
مواضيع طبية MeSH: Parkinson Disease*/diagnosis , Voice*, Databases, Factual ; Humans ; Neural Networks, Computer ; Speech
مستخلص: The computerized detection of Parkinson's disease (PD) will facilitate population screening and frequent monitoring and provide a more objective measure of symptoms, benefiting both patients and healthcare providers. Dysarthria is an early symptom of the disease and examining it for computerized diagnosis and monitoring has been proposed. Deep learning-based approaches have advantages for such applications because they do not require manual feature extraction, and while this approach has achieved excellent results in speech recognition, its utilization in the detection of pathological voices is limited. In this work, we present an ensemble of convolutional neural networks (CNNs) for the detection of PD from the voice recordings of 50 healthy people and 50 people with PD obtained from PC-GITA, a publicly available database. We propose a multiple-fine-tuning method to train the base CNN. This approach reduces the semantical gap between the source task that has been used for network pretraining and the target task by expanding the training process by including training on another dataset. Training and testing were performed for each vowel separately, and a 10-fold validation was performed to test the models. The performance was measured by using accuracy, sensitivity, specificity and area under the ROC curve (AUC). The results show that this approach was able to distinguish between the voices of people with PD and those of healthy people for all vowels. While there were small differences between the different vowels, the best performance was when/a/was considered; we achieved 99% accuracy, 86.2% sensitivity, 93.3% specificity and 89.6% AUC. This shows that the method has potential for use in clinical practice for the screening, diagnosis and monitoring of PD, with the advantage that vowel-based voice recordings can be performed online without requiring additional hardware.
(Copyright © 2021 Elsevier Ltd. All rights reserved.)
فهرسة مساهمة: Keywords: Automatic voice analysis; CNN ensemble; Convolutional neural network; Parkinson's disease; Transfer learning
تواريخ الأحداث: Date Created: 20211120 Date Completed: 20220317 Latest Revision: 20220317
رمز التحديث: 20231215
DOI: 10.1016/j.compbiomed.2021.105021
PMID: 34799077
قاعدة البيانات: MEDLINE
كن أول من يترك تعليقا!
يجب تسجيل دخولك أولا