Abstract

In healthcare organizations, a great problem is faced by healthcare providers to know the ART adherence and status of HIV/AIDS patients. In this research, a predictive model using supervised learning is developed to let clinicians and healthcare providers know the ART adherence of PLHIV using features of the patients� treatment history. The methodology used was CRISP-DM data mining process. The research used easily measurable baseline demographic and clinical variables such as body weight, ART regimen, patients enrolled in care, and phenotype. Data preprocessing and transformation was done to ensure the dataset collected was clean. The dataset was split into training and test set i.e., 80% for training and 20% for testing. The baseline results from the benchmark and performance evaluation showed that random forest model performed the best with accuracy of 81% and AUC of 79.3% compared to other binary algorithms and classification error rate of 0.333. The model that performed poorly was Na�ve Bayes with an accuracy score of 20.0%. The model that performed poorly was Na�ve Bayes with an accuracy score of 20.0%. The researcher retrospectively followed 21551 records of patients who were seeking care at county health facilities.

Description