Drug Recommendation System Using Machine Learning

The drug recommendation system employs a comprehensive dataset comprising patient demographics, medical history, genetic information, and existing medication records. Feature engineering techniques are applied to extract relevant features, and Naive Bays machine learning model is trained on this data. The model assesses potential drug interactions, contraindications, and adverse reactions, prioritizing treatment options that minimize risks. At 9 7 \% accuracy, the system worked excellently. The purpose of this research is to propose a medicine recommendation system that can significantly lessen the backlog of specialists. In this study, we construct a medication recommendation system that leverages patient reviews to infer sentiment via a variety of vectorization techniques, including Bow, TF-IDF, Word2Vec, and Manual Feature Analysis. This system can then recommend the best medication for a particular illness based on a variety of classification algorithms.