AI in drug therapy optimization: A comparative study of machine learning models for guideline adherant therapy personalization in hyperlipidemia

Hyperlipidemia is a key contributor to cardiovascular diseases. While guideline-based treatment strategies exist, real-world implementation varies due to patient-specific complexities, clinician subjectivity, and evolving clinical evidence. This study evaluates Random Forest (RF) Classifier and XG-Boost models for personalizing hyperlipidemia treatment based on AHA and ACC guidelines with factors like eGFR, Baseline_LDL_C, Age, ASCVD_Risk_Score, Cost_Sensitivity, ASCVD, Diabetes, Triglycerides, BMI, and Smoking_Status, with an emphasis on guideline adherence and performance metrics. This E-Poster was presented at Kerala Pharmaceutical Congress 2025, held at Caritas College of Pharmacy, Kottayam, Kerala, India and won the "Best Paper Award" in the General stream.