Machine learning reveals the contribution of lipoproteins to liver triglyceride content and inflammation.

CONTEXT: Metabolic dysfunction-associated steatotic liver disease (MASLD) is currently the most common chronic liver disease worldwide and is strongly associated with metabolic comorbidities, including dyslipidemia. OBJECTIVE: Herein, we aim to estimate the prevalence of MASLD and metabolic dysfunction-associated steatohepatitis (MASH) in Europeans with isolated hypercholesterolemia and isolated hypertriglyceridemia in the UK Biobank and to estimate the independent contribution of lipoproteins to liver triglyceride content. METHODS: We selected 218,732 Europeans from the UK Biobank without chronic viral hepatitis and other causes of liver disease, of whom 14,937 with liver magnetic resonance imaging (MRI) data available. Next, to examine the relationships between traits in predicting liver triglyceride content, we compared the predictive performance of several machine learning methods and selected the best performing algorithms based on the minimum cross-validated mean squared error (MSE). RESULTS: There was an approximately 3-fold and 4-fold enrichment of MASLD and MASH in individuals with isolated hypertriglyceridemia (p=1.23E-41 and p=1.29E-10, respectively), whereas individuals with isolated hypercholesterolemia had a marginal higher rate of MASLD and no difference in MASH rate compared to control group (p=0.019 and p=0.97, respectively). Among machine learning methods, feed-forward neural network had the best cross-validation MSE on the validation set. Circulating triglycerides, after body mass index (BMI), were the second strongest independent predictor of liver proton density fat fraction (PDFF) with the largest absolute mean Shapley additive explanation (SHAP) value. CONCLUSION: Isolated hypertriglyceridemia is the second strongest, after obesity, independent predictor of MASLD/MASH. Individuals with hypertriglyceridemia, but not with hypercholesterolemia, should be screened for liver disease.

A new breakfast brioche containing bergamot fiber prevents insulin and glucose increase in healthy volunteers: a pilot study.

BACKGROUND: Despite the abundance of studies on the beneficial effects of a fiber rich diet as well as polyphenols deriving from Citrus fruits on postprandial serum glucose and insulin, clinical evidence on their synergic effects on healthy subjects have never been published. We aimed to investigate the feasibility of a new dietary approach in controlling glucose and insulin response at breakfast time by testing a brioche enriched with wheat bran and bergamot fiber. METHODS: We enrolled 11 healthy volunteers in a cross-over study. Participants consumed a classic brioche at breakfast and our functional brioche, containing wheat bran and bergamot fiber, on another day. Vital functions, biochemical parameters (including glucose and insulin), anthropometric measurements as well as resting energy expenditure and fat oxidation were evaluated before and after the intake of both meals. RESULTS: The mean age was ~25 years. The mean BMI was 23.5 kg/m2. The consumption of the functional brioche reduced the glucose Cmax(0-120 min) by ~6% and prevented the insulin increase over time by 30%, finally demonstrating insulin Cmax(0-120 min) and iAUC(0-120 min) values significantly lower compared to classic brioche (respectively P value =0.04 and 0.03). The stepwise multivariable analysis confirmed the association between the consumption of the functional brioche containing bran and bergamot fiber and glucose Cmax(0-120 min) (B=-0.45; P=0.034), and insulin iAUC(0-120 min) (B=-764 P=0.036). CONCLUSIONS: The association of wheat bran and bergamot fiber significantly influences glucose metabolism and may exert insulin-like effects on healthy volunteers. If confirmed, berga-brioche would be a useful tool in preventing diabetes and controlling the glycometabolic status of type 2 diabetic patients.