•  
  •  
 

Abstract

Drug reviews play a very important role in providing crucial medical care information for both healthcare professionals and consumers. Also, in the absence of an actual practicing healthcare professional, a consumer can look for an online review of drugs before making a purchase. But these reviews are generally unstructured in nature and often do not provide concise information on the disease/nature of the disease, the drugs are prescribed for. In this scenario, a learning model that can be trained to predict the disease/type of disease, when provided with a drug name and its corresponding review, becomes very important. To mitigate the above-mentioned issue, we present and compare various machine learning-based prediction models. Also, the performance of each of the models has been quantified using metrics such as precision, recall, F1-Score, and accuracy.

Share

COinS