Digital Twin-Enabled Personalized Nutrition Improves Metabolic Dysfunction-Associated Fatty Liver Disease in Type 2 Diabetes: Results of a 1-Year Randomized Controlled Study

ObjectivePostprandial hyperglycemia drives insulin resistance and inflammation, leading to metabolic dysfunction-associated fatty liver disease (MAFLD). Prediction of postprandial glycemic responses (PPGR) by digital twin (DT) technology can fashion a personalized nutrition, activity and sleep to treat type 2 diabetes (T2D) and MAFLD. This study examines the effects of DT-enabled personalized nutrition, activity and sleep on glycemic status, surrogate markers of MAFLD, and MRI-derived proton density fat fraction (MRI-PDFF) in patients with T2D.MethodsOpen-label, trial randomized (2:1) eligible 319 people with type 2 diabetes to intervention (DT) or standard care (SC). DT patients followed personalized meal plans with foods suggested by artificial intelligence with least predicted PPGR. Primary endpoint was to compare change in HbA1c and medicine reduction between the DT and SC group. Key secondary endpoints included remission, to compare liver function test scores and Visceral Adiposity using MRI.ResultsHbA1C was significantly better for DT than SC (-2.9 [1.8] vs. -0.3 [1.2]; p <0.001) at one year with 72.7% remission of T2D. In patients with abnormal baseline values, significant improvements were seen in DT vs. SC patients from baseline to one year in NAFLD liver fat score (mean [SD]; -2.5 [2.0] vs. -0.1 [1.5]; p<0.001) and NAFLD liver fibrosis score (-1.20 [0.9] vs. -0.1 [1.0]; p<0.001), respectively. Improvements are seen with DT compared with SC in other liver fat, fibrosis score and %liver fat by MRI-PDFF.ConclusionsAt one year, DT-enabled personalized treatment significantly improved hyperglycemia and surrogate markers of MAFLD and MRI-PDFF.