Machine learning and deep learning approach to Parkinson’s disease detection: present state-of-the-art and a bibliometric review

Parkinson’s disease (PD) is a neurodegenerative disorder that affects millions of people worldwide, necessitating accurate and timely diagnostic methods for effective disease management. This study proposes a novel approach for PD detection using deep features extracted from magnetic resonance imaging (MRI) scans, employing a pattern recognition neural network architecture based on DenseNet201. The developed model demonstrated exceptional performance, achieving validation and test accuracies of 99.4% and 99.2%, respectively, indicating its robustness and efficacy in distinguishing between patients with PD and healthy individuals. Furthermore, the model achieved a precision of 99.5%, recall of 99.3%, and an F1 score of 99.4%. For the test set, the accuracy was 99.2%, with precision at 99.3%, recall at 99.1%, and an F1 score of 99.2%. The rapid convergence of the model during training further underscores its efficiency in learning discriminative features from MRI images. These findings underscore the promising role of deep learning techniques, particularly convolutional neural networks (CNNs), in medical image analysis for disease diagnosis. The proposed approach holds significant potential for assisting clinicians in early PD diagnosis and personalized treatment planning, ultimately improving patient outcomes and quality of life.

show abstract

Exploring the Potential Imaging Biomarkers for Parkinson’s Disease Using Machine Learning Approach

Mushta,

Koks,

Popov

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by motor and neuropsychiatric symptoms resulting from the loss of dopamine-producing neurons in the substantia nigra pars compacta (SNc). Dopamine transporter scan (DATSCAN), based on single-photon emission computed tomography (SPECT), is commonly used to evaluate the loss of dopaminergic neurons in the striatum. This study aims to identify a biomarker from DATSCAN images and develop a machine learning (ML) algorithm for PD diagnosis. Using 13 DATSCAN-derived parameters and patient handedness from 1309 individuals in the Parkinson’s Progression Markers Initiative (PPMI) database, we trained an AdaBoost classifier, achieving an accuracy of 98.88% and an area under the receiver operating characteristic (ROC) curve of 99.81%. To ensure interpretability, we applied the local interpretable model-agnostic explainer (LIME), identifying contralateral putamen SBR as the most predictive feature for distinguishing PD from healthy controls. By focusing on a single biomarker, our approach simplifies PD diagnosis, integrates seamlessly into clinical workflows, and provides interpretable, actionable insights. Although DATSCAN has limitations in detecting early-stage PD, our study demonstrates the potential of ML to enhance diagnostic precision, contributing to improved clinical decision-making and patient outcomes.

show abstract

Machine learning and deep learning approach to Parkinson’s disease detection: present state-of-the-art and a bibliometric review

Cited by 3 publications

References 76 publications

Research Trends in Application of Artificial Intelligence in Alzheimer’s Disease: Bibliometric and Visualization Analysis

Research Trends in Application of Artificial Intelligence in Alzheimer’s Disease: Bibliometric and Visualization Analysis

Enhanced Parkinson’s Disease Diagnosis via MRI Analysis: Integrating Deep Features From DenseNet201 With Neural Network Techniques

Exploring the Potential Imaging Biomarkers for Parkinson’s Disease Using Machine Learning Approach

Contact Info

Product

Resources

About