A Web Application for exploratory data analysis and classification of Parkinson’s Disease patients using machine learning models on different datasets

Automated biomedical data analysis tools are crucial in research and clinical practice; however, they are not always accessible to everyone. This paper introduces a web-based system that facilitates exploratory data analysis and machine learning, focusing on identifying audio and video data patterns. This system applies to various biomedical contexts, such as the study of Parkinson’s disease. Developed using Python and the Streamlit framework, it offers an intuitive interface for data analysis, visualization, and automated classification. Its flexibility makes it a valuable resource for researchers and healthcare professionals, enabling meaningful insights and fostering advancements in biomedical research. • Development of a web-based tool integrating EDA and machine learning for Parkinson’s disease diagnosis. • Utilization of the PyCaret library, enabling comparison of 14 machine learning algorithms. • Support for diverse datasets (e.g., voice recordings, drawing patterns) with customizable preprocessing. • Accessibility for researchers with limited programming skills through an intuitive interface. • Open-source and adaptable for broader scientific applications beyond Parkinson’s research.