Metabolic Profiles of Type 2 Diabetes and Their Association With Renal Complications.

CONTEXT: The components of metabolic syndrome (MetS) are interrelated and associated with renal complications in patients with type 2 diabetes (T2D). OBJECTIVE: We aimed to reveal prevalent metabolic profiles in patients with T2D and identify which metabolic profiles were risk markers for renal progression. METHODS: A total of 3556 participants with T2D from a hospital (derivation cohort) and 931 participants with T2D from a community survey (external validation cohort) were included. The primary outcome was the onset of diabetic kidney disease (DKD), and secondary outcomes included estimated glomerular filtration rate (eGFR) decline, macroalbuminuria, and end-stage renal disease (ESRD). In the derivation cohort, clusters were identified using the 5 components of MetS, and their relationships with the outcomes were assessed. To validate the findings, participants in the validation cohort were assigned to clusters. Multivariate odds ratios (ORs) of the primary outcome were evaluated in both cohorts, adjusted for multiple covariates at baseline. RESULTS: In the derivation cohort, 6 clusters were identified as metabolic profiles. Compared with cluster 1, cluster 3 (severe hyperglycemia) had increased risks of DKD (hazard ratio [HR] [95% CI]: 1.72 [1.39-2.12]), macroalbuminuria (2.74 [1.84-4.08]), ESRD (4.31 [1.16-15.99]), and eGFR decline [P < .001]; cluster 4 (moderate dyslipidemia) had increased risks of DKD (1.97 [1.53-2.54]) and macroalbuminuria (2.62 [1.61-4.25]). In the validation cohort, clusters 3 and 4 were replicated to have significantly increased risks of DKD (adjusted ORs: 1.24 [1.07-1.44] and 1.39 [1.03-1.87]). CONCLUSION: We identified 6 prevalent metabolic profiles in patients with T2D. Severe hyperglycemia and moderate dyslipidemia were validated as significant risk markers for DKD.

Dynamic forecasting of severe acute graft-versus-host disease after transplantation.

Forecasting of severe acute graft-versus-host disease (aGVHD) after transplantation is a challenging 'large p, small n' problem that suffers from nonuniform data sampling. We propose a dynamic probabilistic algorithm, daGOAT, that accommodates sampling heterogeneity, integrates multidimensional clinical data and continuously updates the daily risk score for severe aGVHD onset within a two-week moving window. In the studied cohorts, the cross-validated area under the receiver operator characteristic curve (AUROC) of daGOAT rose steadily after transplantation and peaked at ≥0.78 in both the adult and pediatric cohorts, outperforming the two-biomarker MAGIC score, three-biomarker Ann Arbor score, peri-transplantation features-based models and XGBoost. Simulation experiments indicated that the daGOAT algorithm is well suited for short time-series scenarios where the underlying process for event generation is smooth, multidimensional and where there are frequent and irregular data missing. daGOAT's broader utility was demonstrated by performance testing on a remotely different task, that is, prediction of imminent human postural change based on smartphone inertial sensor time-series data.