Enhanced Random Forest Approach in Digital Healthcare in Medicine Recommendation and Classification

Abstract

In the era of digital healthcare, the integration of machine learning techniques has revolutionised the field of medicine. This chapter presents an efficient approach for building a prediction system for medicine classification using machine learning algorithms. By accurately categorizing medicines based on various diseases such as fever, allergy, and many more. The web-based recommendation system aims to assist healthcare professionals in making informed decisions in healthcare designed with the Flask framework that helps users to discover possible medical diseases. The system takes symptoms as input and machine learning models, including support vector machines (SVM), random forests, gradient boosting, k-nearest neighbors (KNN), and multinomial naive bayes model to predict illnesses with efficient accuracy. The enhanced random forest technique was proposed which obtains the classification accuracy of 0.942, precision of 0.9124, recall of 0.895, and F1-score of 0.914. This improves decision-making and increases accessibility to healthcare services. All things considered, the medicine recommendation system is a useful resource for those looking for first advice on health-related issues, improving both general health and healthcare results.