Anomaly Detection for Prolongation of Health

Abstract

Chronic diseases, such as diabetes, and cardiovascular diseases, are some of the most pressing global health challenges. These diseases typically develop over time, often with few or no symptoms in the early stages, which makes early detection difficult. As a result, they are usually diagnosed at more advanced stages, when treatment options become more limited, less effective, and far more costly.   Hence, we propose a novel AI-driven anomaly detection approach that goes beyond detecting single instances of abnormality. Instead, we study the personal health trajectory of individuals, how their health metrics evolve, and identify significant deviations, or "intersections" along this path. These intersections represent points where health parameters begin to deviate from their normal trajectory, signalling potential risks for disease progression. We can detect early warning signs by continuously monitoring these trajectories and providing gradual, corrective adjustments that maintain health stability. The concept of personal health trajectories recognizes that health is not static but rather dynamic, influenced by many factors that interact over time. A key advantage of this approach is that it allows for the detection of subtle shifts in health long before they manifest as overt disease symptoms.   The integration of EHRs, wearable devices, and lifestyle data, combined with AI-driven anomaly detection represents a significant opportunity to shift healthcare from a treatment-based model to a prevention-focused approach. This project aims to harness the power of AI to continuously monitor health data, detect early signs of chronic disease, and implement personalized interventions that maintain health and prevent disease progression.