Multiple Disease Prediction System using Machine Learning and Streamlit

• Main Authors: Gopisetti, Laxmi Deepthi, Kummera, Srinivas Karthik Lambavai, Pattamsetti, Sai Rohan, Kuna, Sneha, Parsi, Niharika, Kodali, Hari Priya
• Format: Conference Proceeding
• Language: English
• Subjects: Cancer; Chronic kidnev disease; Chronic kidney disease; Classification algorithms; Decision Tree; Diabetes; Gaussian naive bayes; Heart; Heart disease; K Nearest Neighbor; Predictive models; Random Forel Logistic Regression; Single user intetface; Support Vector Machine; Support vector machine classification; User interfaces
• ISSN: 2832-3017
• DOI: 10.1109/ICSSIT55814.2023.10060903

There are many existing machine learning models related to health care which mainly focuses on detecting only one disease. Therefore, this study has developed a system to forecast several diseases by using a single user interface. The proposed model can predict multiple diseases such as diabetes, heart disease, chronic kidney disease and cancer. If left untreated, these diseases pose a risk to humanity. As a result, many lives can be saved by early detection and diagnosis of these disorders. This research work attempts to implement various classification algorithms (K-Nearest Neighbor, Support Vector Machine, Decision Tree, Random Forest, and Logistic Regression, Gaussian naive bayes.) to perform disease prediction. The accuracy of each algorithm is validated and compared with each other to find the best one for prediction. Furthermore, multiple datasets (for each disease each dataset) are used to achieve utmost accuracy in the predicted results. The main goal is to create a web application capable of forecasting several diseases by using machine learning, including diabetes, heart disease, chronic kidney disease, and cancer.