Convolutional Neural Network-based Classification of Parkinsonian Voice Disorders: A Spectrogram Approach DOI

Alisson Constantine-Macías,

Carlos Jiménez-Farfán,

Michael Arce

et al.

Published: Oct. 15, 2024

Language: Английский

Clinical Decision Support Using Speech Signal Analysis: Systematic Scoping Review of Neurological Disorders DOI Creative Commons
Upeka De Silva, Samaneh Madanian, Sharon Olsen

et al.

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e63004 - e63004

Published: Jan. 13, 2025

Background Digital biomarkers are increasingly used in clinical decision support for various health conditions. Speech features as digital can offer insights into underlying physiological processes due to the complexity of speech production. This process involves respiration, phonation, articulation, and resonance, all which rely on specific motor systems preparation execution speech. Deficits any these cause changes signal patterns. Increasing efforts being made develop speech-based systems. Objective systematic scoping review investigated technological revolution recent analysis trends understand key concepts research from technical perspectives. Methods A was undertaken 6 databases guided by a set questions. Articles that focused decision-making were identified, included studies analyzed quantitatively. narrower scope investigating neurological diseases using qualitative content analysis. Results total 389 articles met initial eligibility criteria, 72 (18.5%) In studies, Parkinson disease, Alzheimer cognitive disorders most frequently The literature explored potential feature diagnosis, differentiating between, assessing severity monitoring treatment common tasks sustained phonations, diadochokinetic tasks, reading activity-based picture descriptions, prompted tasks. From conventional (such fundamental frequency, jitter, shimmer), advanced processing–based wavelet transformation–based features), spectrograms form audio images analyzed. Traditional machine learning deep approaches build predictive models, whereas statistical assessed variable relationships reliability features. Model evaluations primarily analytical validations. significant gap identified: need structured guide toward intervention settings. To address this, framework proposed adapts design science methodology systematically. Conclusions findings highlight how data techniques enhance decision-making. By combining knowledge practice, science, within framework, future may achieve greater relevance.

Language: Английский

Citations

2
Voxtranspd: A Dynamic Cross-Channel Transformer for Noise-Resilient Early Parkinson's Detection from Heterogeneous Speech DOI

Tianhua Qu,

Aite Zhao,

Tao Ren

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Voice analysis in Parkinson’s disease - a systematic literature review DOI Creative Commons

Daniela Xavier,

Virginie Felizardo, Beatriz Ferreira

et al.

Artificial Intelligence in Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 103109 - 103109

Published: March 1, 2025

Language: Английский

Citations

0
Artificial intelligence-enabled detection and assessment of Parkinson’s disease using multimodal data: A survey DOI
Aite Zhao, Yongcan Liu,

Xinglin Yu

et al.

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 103175 - 103175

Published: April 1, 2025

Language: Английский

Citations

0
Convolutional Neural Network-based Classification of Parkinsonian Voice Disorders: A Spectrogram Approach DOI

Alisson Constantine-Macías,

Carlos Jiménez-Farfán,

Michael Arce

et al.

Published: Oct. 15, 2024

Language: Английский

Citations

0