ABSTRACT

Most of the people tend to live a long and healthy life, where they are more conscious about their health. But many studies show that almost many people die due to the medical errors caused in terms of taking wrong medicines and these errors are caused by doctors, who prescribe medicines based on their experiences which are quite limited. As machine learning, deep learning and data mining like technologies that are emerging day by day, these technologies can help us to explore the medical history and can reduce medical errors by being doctor friendly. In this paper proposes a medicine recommendation system , which takes the patient review data and performs sentiment analysis on it to find the best medicine for a disease by using NGram model. In order to increase the accuracy, a Lightgbm model is used to perform medication analysis. The paper also discusses the advantages, disadvantages and enhancements that can be incorporated to improve the accuracy.