AI-BASED MULTI DISEASE PREDICTION SYSTEM USING MACHINE LEARNING

The AI-Based Multi-Disease Prediction System successfully demonstrates the application of Machine Learning in healthcare by providing early prediction of multiple diseases through a single integrated platform. The system uses the Random Forest Classifier to predict the likelihood of six major diseases: Diabetes, Heart Disease, Stroke, Lung Cancer, Liver Disease, and Parkinson's Disease. By utilizing patient medical information, the application delivers fast and accurate predictions that can support early diagnosis and preventive healthcare. The developed system combines several advanced features, including a Streamlit-based interactive interface, Explainable AI (XAI) for transparent predictions, Risk Assessment for interpreting disease severity, PDF report generation using ReportLab, and SQLite database management for storing patient records and prediction history. These features make the application more comprehensive, user-friendly, and suitable as a healthcare decision-support tool. The Random Forest algorithm demonstrated reliable performance due to its ability to reduce overfitting and improve prediction accuracy through ensemble learning. The modular architecture of the system also allows easy maintenance and future expansion. Although the application is not intended to replace professional medical diagnosis, it serves as an effective preliminary screening tool that assists healthcare professionals and patients in making informed decisions.

[1]   L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [2]     F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. VanderPlas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay, "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [3]   W. McKinney, Python for Data Analysis, 2nd ed. Sebastopol, CA, USA: O'Reilly Media, 2017. [4]   T. E. Oliphant, A Guide to NumPy, USA: Trelgol Publishing, 2006. [5]            Python Software Foundation, Python Documentation. Available: https://docs.python.org/3/ [6]   Streamlit Inc., Streamlit Documentation. Available: https://docs.streamlit.io/ [7]       SQLite Consortium, SQLite Documentation. Available: https://www.sqlite.org/docs.html