Personalized Medicine Recommendation and Disease Flagging Model Based on User’s Previous Orders
Pritam Bhuiya, Rohit Malik, Aritra Rana, Md Ashifuddin Mondal · 2023
The Recommendation systems gaining importance every passing day and are frequently used in e-commerce websites, content streaming platforms, social media platforms, and other applications to analyze large amounts of data and recommend products or services to users based on their past actions, preferences, and other pertinent factors. This kind of system can effectively be used in healthcare to provide personalized recommendations to patients. In this paper, a recommendation model has been proposed that flags the users with the diseases that they may have based on analyzing their historical medicine order and recommends them with alternate related medicines and products. The proposed model is based on a machine learning technique that takes into consideration the user’s medical history, disease diagnosis, and prescription orders and recommends other related medicine and products. The proposed model uses a combination of supervised and unsupervised learning algorithms. A sizable dataset of patient orders from a top pharmaceutical retailer served as the basis for training and validating the model. The simulation results show that the model can handle complex situations, such as multiple medications and medical conditions, and predict medication recommendations with high accuracy.