Optimizing Antiretroviral Therapy (ART) Adherence Through Predictive Analytics Using Machine Learning Techniques

Abstract

HIV and AIDS remain prominent global health concerns and antiretroviral medication (ART) plays a crucial role in treating infected individuals, preventing disease progression, and improving overall health outcomes. However, missed appointments in ART programs pose significant challenges by causing treatment interruptions, unsuppressed viral load, and increased HIV transmission rates. This research employs the CRISP-DM methodology and aims to develop a predictive model that effectively reduces missed appointments among people living with HIV. A comprehensive analysis of patient data, including demographics, clinical information, and appointment history, was conducted to determine the key factors influencing missed appointments. The prediction model was developed using decision trees, random forests, and support vector machines. The study found that decision trees produced the best results, having lower square errors and greater R squared. The findings contribute to the advancement of predictive analytics in healthcare, particularly in the context of chronic conditions such as HIV/AIDS.