Abstract:
The objective of this project is to develop a web application that will use scarped
dataset of disease and symptoms in order to predict diseases of patients’ symptoms,
also recommend them homeopathic medicines The usual process of diagnosis may
not be adequate in the case of a severe illness. Developing a medical diagnosis
method based on machine learning (ML) algorithms in predicting certain diseases
can benefit in a more reliable diagnosis than the traditional method. We have
developed a disease prediction system using multiple ML algorithms. The dataset
utilized had more than 200+ diseases and 513+ symptoms for training the models.
Based on the symptoms, the diagnosis system returns the output as the disease that
the person might be suffering from. The weighted Logistic Regression algorithm
returned the best results as compared to the other algorithms. The accuracy of the
weighted Logistic Regression algorithm for the prediction was 93.5 %. Our diagnosis
model can serve as a doctor for the initial diagnosis of a disease to ensure proper
medication can be given on time and lives can be saved through recommended
homeopathic medicines.
