Convolutional slime mold deep learning model for diagnosis of PD.

Area of Science:

• Computational intelligence
• Biomedical signal processing
• Machine learning for healthcare

Background:

• Early detection of Parkinson's disease (PD) is crucial for effective management.
• Current diagnostic methods can be invasive or lack sensitivity in early stages.
• Voice analysis offers a non-invasive approach for PD detection.

Purpose of the Study:

• To develop an efficient and accurate Parkinson's disease detection scheme.
• To leverage a novel optimized deep learning mechanism for voice analysis.
• To reduce healthcare costs associated with late-stage disease identification.

Main Methods:

• Pre-processing of human voice recordings to reduce noise.
• Feature selection using a chi-square statistical model to reduce complexity.
• Implementation of an Enhanced Convolutional Slime Mold Attention (ECSMA) model for voice categorization.

Main Results:

• The proposed PD detection model demonstrates superior performance compared to existing methods.
• The ECSMA model effectively categorizes voice recordings for PD detection.
• The approach shows potential for early identification of disease progression.

Conclusions:

• The developed deep learning-based voice analysis scheme offers an efficient method for Parkinson's disease detection.
• Optimized feature selection and the ECSMA model contribute to high detection accuracy.
• This non-invasive technique can aid in early diagnosis and potentially lower healthcare expenditures.