HIV Progression and Outcome Prediction to Enhance Patient Matching for Clinical Trials

In this study, we explore the application of machine learning (ML) models for predicting human immunodeficiency virus (HIV) progression and patient outcomes, aiming to enhance patient-trial matching in clinical trials. We evaluate several ML algorithms, including Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Naïve Bayes (NB), Gradient Boosting Methods (XGBoost), and Logistic Regression, to determine their suitability for the task. Our rigorous analysis reveals that Random Forest and XGBoost outperform other models, achieving accuracy rates of 87.85% and 89.02%, respectively, in predicting HIV progression.Additionally, we delve into precision, recall, and F1-score metrics, providing a comprehensive assessment of each model’s performance. The results show the potential of ML in accurately classifying individuals living with HIV into distinct outcome categories. This research marks a significant stride toward optimizing patient-trial matching processes, ultimately improving the efficiency of clinical trials, and enhancing patient care. Future work will focus on fine-tuning these ML models to improve their predictive capabilities and advance personalized healthcare in the context of HIV clinical trials.