AI-Based Quality of Voice Analysis Models for Clinical Use, Insights of Quality of Models from 19 Parkinson’s Disease Studies (2013-2023)
Journal Title: Journal of Clinical Medical Research - Year 2024, Vol 6, Issue 1
Abstract
Voice analysis, powered by Artificial Intelligence (AI) and Machine Learning (ML), has emerged as a valuable tool for detecting and monitoring voice disorders. By identifying vocal biomarkers, AI-driven models can facilitate early diagnosis, track disease progression and support clinical decision-making. This study systematically evaluates the effectiveness and quality of various ML models applied in the 19 studies of AI-related voice analysis in Parkinson’s’ Disease retrieved from The Royal Society of Medicine Library UK, spanning the period from 2013 to 2023. The models assessed include Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), Random Forest (RF) and hybrid CNN-LSTM architectures. Their performance is examined based on accuracy, sensitivity, specificity and error metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Findings indicate that SVM consistently delivers high accuracy (up to 96%) and is particularly effective for small to medium-sized voice-related datasets with pre-engineered datasets. CNNs achieve superior performance (up to 97%) on large, feature-rich datasets; however, their computational demands and limited validation constrain scalability. Random forest models demonstrate robustness in handling imbalanced datasets, while CNN-LSTM hybrids show potential by integrating spatial and temporal feature extraction, though they require further validation. A critical limitation identified in the analyzed studies is the lack of detailed dataset descriptions, diversity and real-world applicability, which restricts comparison with other studies and generalizability. This paper highlights the strengths and limitations of current models for AI-driven voice analysis approaches and emphasizes the need for standardized, diverse datasets and enhanced evaluation metrics to advance AI applications in voice disorder diagnostics and monitoring.
Authors and Affiliations
Pedersen M1*, Meiner VG2
Keywords
Related Articles
- EP ID EP761341
- DOI https://doi.org/10.46889/JCMR.2025.6107
- Views 35
- Downloads 0
Parkinson’s Disease: A Neurodegenerative Disease
Parkinson’s disease is characterized by tremor, stiffness, rigid muscles, bradykinesia, slowness of movement, instability leading to falls, memory and talking difficulties, fatigue, writing modifications (micrography) an...
Efficacy of Resin-Modified Glass Ionomer Cement Varnish and Sodium Fluoride Varnish in The Prevention of White Spot Lesions During Fixed Orthodontic Treatment- A Split Mouth Study
Objective: Evaluating efficacy of Resin-Modified Glass Ionomer Varnish and Sodium Fluoride Varnish in prevention of White Spot Lesions (WSLs) during early fixed orthodontic treatment; comparing the incidence of white spo...
Screening Pilot Study of Fruit Seed Compositions by GC-MS and Their Potential Scenario Anti ACE2 and 2rh1 Receptors as a Recycling Possibility in the Coronavirus Pandemic
Background: Since 2019, several critical effects of the coronavirus pandemic have surfaced, including its psychological problems such as depression. The World Health Organization has approved a group of drugs and vacci...
Next-Generation Sequencing of Microbial Cell-Free DNA to Rapidly Detect Fluoribacter Bozemanae Pneumonia in an Immunocompromised Host
Background: Fluoribacter bozemanae is an uncommon pathogen that accounts for just 3-5% of cases of pneumonia caused by the different Legionella species. The mortality rate has been reported to be up to 40%. This organis...
Internal Mammary Artery Graft Flow Steal by a Large Dialysis Arteriovenous Fistula Characterized by Electrical Storm
Background: Steal syndrome describes a condition in which a dilated vessel distal to a smaller artery attempts to compensate for decreased blood flow by “stealing” from the smaller artery. Steal syndrome is not uncommon...