Personalized Medicine Recommendation System Using Optimized Light Gradient Boosting Machine for Enhanced Healthcare Analytics

Author(s)	Mr. Kumar Gaurav Tiwari, Ms. Srishti Sati, Ms. Harshita Nayal
Country	India
Abstract	The current work is a proposal of a Personalized Medicine Recommendation System that can be used to improve healthcare decision-making by incorporating disease prediction and individualized treatment instructions. A comprehensive analysis of the research performed in the past has shown that ML models, including Random Forest (RF) and XGBoost (XG), can often report predictive accuracies of approximately 97%. But none of the studies have compared these algorithms (systematically and in an experimental setting). To overcome this problem, the current research experimentally assesses the performance of RF, XG, and LightGBM using three different datasets, including a self-generated training dataset, a schedule dataset, and a publicly accessible Kaggle dataset on heart diseases. Although RF first provided the best performance, with large amounts of hyperparameter tuning, LightGBM was able to outperform all other models, reaching an accuracy of close to 98 percent, and a 2.1-2.5 percent score enhancement in a variety of main evaluation indicators, such as recall.
Keywords	Machine learning, Healthcare, Decision trees, Ensemble learning, medical diagnosis, Recommendation systems, Gradient boosting, Boosting algorithms, Comparative analysis
Field	Medical / Pharmacy
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-02
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.76895

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research