Across this week’s diabetes/obesity literature, the AI/ML angle is less about “fancier models” and more about engineering better inputs (composite indices, multimodal biomarker sets) and then shipping them as usable clinical/risk-stratification artifacts. A Diabetes Obesity & Metabolism paper couples machine learning + growth-mixture modelling and explicitly frames a web-based risk prediction tool for worsening renal function in T2DM using a novel cardiometabolic index as a key marker [1]. In parallel, a J Diabetes Metab Disord analysis uses feature-selection style ML (Boruta) to elevate a muscle-quality composite as a practical diabetes risk signal [2]. A scoping review in Advances in Nutrition generalizes the direction of travel: obesity risk prediction increasingly calls for multimodal biomarker bundles interpreted with ML/AI rather than single markers [3].
Why it matters / what changes in tactics
-
Clinicians/teams: If adopting ML risk tools, treat them like any other diagnostic/prognostic instrument: insist on external validation, local calibration checks, and clear “what to do if high-risk” pathways before workflow embedding [1] [2].
-
Researchers: The publishable frontier is shifting toward (a) multimodal feature sets that are feasible in real-world care and (b) reporting that supports implementation—calibration, decision-curve style utility, subgroup performance, and transparent variable definitions [1] [3].
References
-
Zhang Q, Zhou Y, Fu L, et al. Relationship between cardiometabolic index and worsening renal function in T2DM: Insights from machine learning, growth mixture modelling, and development of a web-based risk prediction tool. Diabetes Obes Metab. Published online December 22, 2025. doi: https://doi.org/10.1111/dom.70374.
PubMed: https://pubmed.ncbi.nlm.nih.gov/41424207/ -
Yao X, Xiao K, Oo HK. Protector role of muscle quality against diabetes in non-elderly U.S. adults. J Diabetes Metab Disord. 2025;25(1):14. doi: https://doi.org/10.1007/s40200-025-01828-w.
PubMed: https://pubmed.ncbi.nlm.nih.gov/41451398/ -
Vahid F, Loyola-Leyva A, Tur J, et al. Multimodal (Bio)Markers and Risk of Obesity - A Comprehensive Scoping Review. Adv Nutr. Published online December 24, 2025. doi: https://doi.org/10.1016/j.advnut.2025.100579.
PubMed: https://pubmed.ncbi.nlm.nih.gov/41453658/