Healthcare Made Smarter: AI-Driven Drug Recommendation Systems

Authors: Dr. Radha Krishna Jana1, Dr. Atanu Kotal2, Asit Kumar Nayek3

1,2 JIS University, 3 Haldia Institute of Technology

radhakrishna.jana@jisuniversity.ac.in, atanukotal78@gmail.com, asit_nayek@ieee.org

Published in: Journal of Computer Science and Engineering in Innovations and Research (ISSN No: 3049-1762 online)

Publication Date: June 15, 2025

đź“„ Abstract

We are busy in social network today. We posted different tweets on different topics. We can analysis tweets using different techniques. Then the positive sentiments on particular subjects recommended in thw social network.This research work proposed a recommended system on drug tweets. This system help to healthcare providers in decision-making when prescribing medications, analyzing drug review sentiments to determine effectiveness and utilizing a hybrid method to overcome limitations of traditional recommender algorithms, ultimately aiming to improve patient care and digital healthcare pathways.

🔑 Keywords

Sentiment Analysis, Drug recommendation system,BERT

I. Introduction

The global community is actively engaged on social media, exchanging ideas and sharing diverse perspectives. This research examines the homophily phenomenon in the context of social media sentiment analysis[1]. This research explores and discusses different methods for sentiment analysis of social media posts[2]. Healthcare providers are strained by growing patient numbers and a persistent shortage of clinicians, which heightens the risk of medical errors such as wrong‑drug prescriptions. By adapting the personalized‑recommendation technology used in e‑commerce, such a system can assist clinicians in making safer, more informed prescribing decisions [3]. The proposed system can support healthcare professionals in choose the best medications for patients, reducing the burden of keeping up with the vast array of available drugs and potentially improving treatment outcomes[4]. Opinion mining and sentiment analysis can help extract useful information from patient feedback, determining whether reviews are positive, neutral, or negative, and supporting healthcare professionals in their decision-making[5]. Sentiment analysis on drug reviews helps healthcare professionals understand overall drug effectiveness. However, recommendation systems face challenges like cold start issues and adapting to changing customer preferences [6].

The aim of this study:
l Develop a drug recommendations system.
l Classify drug reviews.
l Create a web-based system .
l Facilitate knowledge sharing among healthcare professionals.

Section II discuss the related work, Methodology expressed in Section III, In Section IV discussed Result and discussion, Conclude all the work in Section V.