Disease Predictor

The system takes symptoms of the user and feeds it as the input to the ML model deployed in the system, which predicts the most probable disease a user might have and suggests suitable treatment to it

The problem Disease Predictor solves

The symptoms submitted by a patient/ user will act as the input to a machine learning model that can predict diseases based on them. The model not only predicts the disease but also suggests specialization that is meant to deal with the prognosis and some relevant information about the same.
The model will be trained using multiple ML algorithms. The dataset consisting of at least 100 symptoms, is used to train the model to predict various diseases.
How does this system work?
The user is required to register with the system, in which upon submitting their symptoms, the model interpreted in the system, will predict the disease.

Challenges we ran into

The main challenge we faced was selecting the best fit algorithm to train our ML model. After some research we found suitable algorithms that gave us best results so far. We also faced issues with over-fitting of our model. We found an alternative approach to that . We used naive-bayes algorithm with gaussian nb model, which resolved most of our issues.