User-Centric AI Analytics for Chronic Health Conditions Management
Aladdin Ayesh
TL;DR
The paper addresses the challenge of managing chronic health conditions through AI by advocating a user-centric, personalized approach that leverages wearable sensing and multi-modal data. It surveys nutrition-, physiology-, and mental-health–related CHCs and illustrates how educational settings and smart-city contexts can serve as constraint environments for developing integrated AI solutions. Key contributions include highlighting the need for validation, personalization, explainability, and responsible AI in health analytics, as well as proposing an integrated mental-physical health framework. The work emphasizes that tailoring AI to individual factors can improve relevance, acceptance, and outcomes in health care and education, with practical implications for deployment and evaluation in real-world settings.
Abstract
The use of AI analytics in health informatics has seen a rapid growth in recent years. In this talk, we look at AI analytics use in managing chronic health conditions such as diabetes, obesity, etc. We focus on the challenges in managing these conditions especially with drug-free approaches due to the variations in individual circumstances. These variations directed the research into user-centric approach leading to variety of research questions. In this short paper, we give examples from recent and current research work and conclude with what, in our opinion, to be the next steps and some remaining open research questions.