Disease Prediction Using Symptoms based on Machine Learning Algorithms and Natural Language Processing

Health became an important aspect in today's world. People are suffering from various viruses, infections etc. Citizens are getting terrified even if they have some symptoms. This stress is just because of not knowing the disease and its seriousness. Sometimes it becomes too late for a disease to be diagnosed and treated which may become a life threat. Additionally, in some situations patients may not be in a position to visit a doctor at times it may become a serious issue. If a system predicts the disease of a patient, then he/she might get out of the anxiety. This can be done by using some machine learning algorithms like Naïve Bayes, Random Forest and Decision Trees. The ultimate result will be the result of the model with high accuracy. Since communicating will be a difficult, a chatbot is implemented. This is done by using Natural Language Processing (NLP). The final result will be shown on the interface using all three machine learning techniques, and feature extraction will be done depending on their symptoms. Five modules make up the proposed methodology. Preprocessing will be done on the dataset in the first module. The decision tree classifier is used to generate a prediction model in the second module. The Random forest method is used for forecast the illness in the third module, the Naive Bayes technique is utilized in the fourth model, Natural Language Processing is used for chatbot mechanism is the fifth module, with the outputs from all the three models taken into account to find best model.