IoT and AI-Based Decision Support System for HIV: Integrated Risk Assessment, Monitoring, and Treatment Optimization

Abstract

The management of Human Immunodeficiency Virus (HIV) remains a global healthcare concern, especially in areas with scarce resources, where constant monitoring, behavioral risk evaluation, and improvement in treatment protocols are often restricted. This paper proposes a novel integrated approach to a decision support system, incorporating Internet of Things-based physiological monitoring, Artificial Intelligence-based behavioral risk evaluation, and Machine Learning-based treatment prediction for improved HIV management. The proposed system includes a mechanism to obtain physiological data from patients, a behavioral risk evaluation mechanism through a mobile app, and a mechanism to predict antiretroviral drug resistance using clinical and mutation data. The proposed approach aims to provide a platform for constant monitoring and improvement in patient care, along with providing accurate and reliable information to both patients and healthcare providers, thereby ensuring improved healthcare management and patient outcomes through a proactive approach to healthcare management. In addition, this system has also been designed to be adaptable to different healthcare scenarios, ensuring its applicability in both urban and rural areas. The use of multiple data points also helps improve accuracy and predict potential complications, if any, during patient management, thus providing a platform for proactive management and improved healthcare outcomes.