Machine learning and AI for advancing Parkinson's disease diagnosis: exploring promising applications

Parkinson's disease is a progressive neurodegenerative disorder affecting millions worldwide. It is characterized by tremors, stiffness, and movement problems, significantly impacting the quality of life for individuals affected by it. Early detection of this condition is crucial for effective management and treatment. Machine learning algorithms have shown promise in various medical applications, including disease detection. These algorithms can analyze large datasets, extract relevant patterns and features, and make accurate predictions. In the context of this neurological disorder, machine learning techniques offer the potential to develop efficient and reliable diagnostic tools. This study investigates the efficacy of three widely employed algorithms – Logistic Regression, Support Vector Machine, and Artificial Neural Network – in detecting Parkinson's disease using speech-related features. The analysis reveals that Artificial Neural Network achieves the highest accuracy of ۹۲.۴%, surpassing Logistic Regression and Support Vector Machine. Accordingly, further research should explore deep learning methods and integrate additional data sources, such as gait analysis and genetic markers, to enhance diagnostic capabilities for Parkinson's disease.

کلیدواژه ها:

Parkinson's disease ، Machine Learning ، Classification ، comparative analysis