DISEASES FORECASTING USING DECISION TREE

This paper presents a unambiguous approach to health forecasting using a decision tree classifier, which is implemented in Python. We developed a model to categorize illness according to symptoms and provide corresponding preventive measures. The decision tree model was trained on a dataset where symptoms were represented as categorical variables rather than binary, making the dataset more intuitive and flexible. The model processes user inputs, converting them into numerical format, and predicts the most likely disease. Additionally, we visualize the decision tree to illustrate the decision-making process from symptoms to disease prediction, facilitating a better understanding the behaviour of model. This approach not only demonstrates the effectiveness of decision trees in medical diagnostics but also provides actionable precautions tailored to the predicted disease, enhancing both diagnosis and prevention strategies.