Revolutionizing Healthcare: Screening system to identify Diseases using Machine learning approach

When individuals experience mild symptoms, seeking medical attention often involves the inconvenience of scheduling appointments, which can be time-consuming and costly. In the realm of disease prediction based on symptoms, numerous machine learning models have been developed, but a significant shortcoming is their limited efficiency. This inefficiency is primarily attributed to the narrow scope of datasets utilized by other models. Few existing machine learning models have adopted methods that prove inefficient in classifying diseases based on symptoms. This paper introduces an intelligent disease detection tool that can serve as a prescreening portal for patients suffering from diseases. The main aim of the proposed model is to create a highly effective system for identifying diseases based on symptoms, utilizing a comprehensive dataset. The proposed system examines userinput symptoms and provides a disease classification as output. Disease identification is achieved through the utilization of three algorithms such as Random Forest classifier, Decision Tree, and Naïve Bayes classifier. The combined use of these algorithms in the proposed model demonstrates enhanced accuracy in disease detection. Ultimately, the most effective model is selected for integration into a web application, ensuring accessibility for individuals across society.