Artificial Intelligence and Big Data in Predicting and Managing Obesity‑Associated Diabetes

Mwende Muthoni D.

Faculty of Medicine Kampala International University Uganda

ABSTRACT

Artificial intelligence (AI) and big data are reshaping how we understand, predict, and manage obesity‑associated type 2 diabetes (T2D). The diabesity phenotype arises from heterogeneous interactions among genes, behaviors, environments, and health‑care systems. At scale, routinely collected data electronic health records (EHRs), pharmacy claims, continuous glucose monitoring (CGM), wearables, meal logs, imaging, multi‑omics, and social determinants of health (SDOH) capture this complexity but are noisy, incomplete, and biased. Modern machine‑learning (ML) methods can transform these substrates into actionable insights: predicting incident T2D and complications; detecting subclinical trajectories; stratifying patients into mechanistic endotypes; recommending individualized nutrition, activity, and pharmacotherapy; and monitoring for relapse or adverse events. Time‑series deep learning, survival modeling, graph neural networks, and causal inference frameworks enable robust forecasting and counterfactual reasoning, while reinforcement learning (RL) personalizes dynamic regimens. However, translation hinges on trustworthy data engineering, external validation, calibration, explainability, privacy, and equity. Federated learning and differential privacy protect data; fairness auditing and participatory design mitigate bias; and MLOps governs monitoring, drift detection, and post‑deployment updates. Integrating AI into clinical workflows requires human‑in‑the‑loop decision support, interoperable standards, and pragmatic evaluation focused on outcomes that matter to patients and systems. This review synthesizes the data foundations, predictive analytics, digital phenotyping, and decision‑support paradigms relevant to diabesity; outlines implementation, safety, and governance requirements; and maps a path toward multimodal, foundation‑model–enabled “digital twins” that couple physiology with behavior to modify disease trajectories. Done well, AI augments not replaces clinicians and patients, enabling earlier intervention, precise therapy matching, and durable cardiometabolic risk reduction.

Keywords: machine learning; continuous glucose monitoring; digital phenotypes; federated learning; precision diabetes care

 

CITE AS: Mwende Muthoni D. (2026). Artificial Intelligence and Big Data in Predicting and Managing Obesity Associated Diabetes. IDOSR JOURNAL OF BIOLOGY, CHEMISTRY AND PHARMACY 11(1):15-21. https://doi.org/10.59298/IDOSR/JBCP/26/102.1521