RECOMED: A Comprehensive Pharmaceutical Recommendation System

TL;DR

This paper presents RECOMED, an AI-driven pharmaceutical recommendation system that integrates patient history, drug features, and interactions to personalize medication suggestions, utilizing deep learning and knowledge-based rules.

Contribution

It introduces a novel approach that considers patient conditions and drug interactions in recommendation models, combining neural networks with knowledge-based systems.

Findings

Deep learning model trained on 2304 patients

Effective filtering of drugs with severe interactions

Improved personalized drug recommendations

Abstract

A comprehensive pharmaceutical recommendation system was designed based on the patients and drugs features extracted from Drugs.com and Druglib.com. First, data from these databases were combined, and a dataset of patients and drug information was built. Secondly, the patients and drugs were clustered, and then the recommendation was performed using different ratings provided by patients, and importantly by the knowledge obtained from patients and drug specifications, and considering drug interactions. To the best of our knowledge, we are the first group to consider patients conditions and history in the proposed approach for selecting a specific medicine appropriate for that particular user. Our approach applies artificial intelligence (AI) models for the implementation. Sentiment analysis using natural language processing approaches is employed in pre-processing along with neural network-based methods and recommender system algorithms for modeling the system. In our work, patients conditions and drugs features are used for making two models based on matrix factorization. Then we used drug interaction to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. After that, we used knowledge from critical information about drugs and combined the outcome of the model into a knowledge-based system with the rules obtained from constraints on taking medicine.