Open AccessDisease Prediction and Doctor Recommendation System using Machine Learning Approaches
Author(s) -
Anand Kumar
Publication year - 2021
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2021.36234
Subject(s) - disease , naive bayes classifier , random forest , machine learning , computer science , logistic regression , sort , audit , artificial intelligence , identification (biology) , interface (matter) , bayes' theorem , heart disease , medicine , support vector machine , information retrieval , pathology , bayesian probability , botany , management , bubble , maximum bubble pressure method , biology , parallel computing , economics
In our everyday life we go over numerous individuals who are experiencing some sort of Diseases. Prediction of disease is an integral part of treatment. In this project the disease is accurately predicted by looking at the symptoms of the patient where the patient can input his/her symptom and the system will predict the disease patient is suffering from. Classification Algorithms like the Naïve Bayes (NB), Random Forest, Logistic Regression and KNN have been broadly utilized to anticipate the Disease, where different accuracies were obtained. In corresponding to a particular Disease, for example, Heart Disease, Diabetes and so on is additionally anticipated by demonstrating “True” or “False” i.e. if an individual is having or not having that Disease. Prediction of such a system can have a very large potential in the medical treatment of the future. Once the Disease is predicted by the system, It then recommends which type of doctor to consult. In this paper, an audit of some new works identified with utilization of Machine Learning in expectation of disease is predicted. An interactive interface is built as front-end to facilitate interaction with the symptoms. The whole model is implemented using Django and is connected to the Django Server.