Machine Learning Algorithms for Predicting Fatty Liver Disease.

BACKGROUND: Fatty liver disease (FLD) has become a rampant condition. It is associated with a high rate of morbidity and mortality in a population. The condition is commonly referred as FLD. Early prediction of FLD would allow patients to take necessary preventive, diagnosis, and treatment. The main objective of this research is to develop a machine learning (ML) model to predict FLD that can help medics to classify individuals at high risk of FLD, make novel diagnosis, management, and prevention for FLD. METHODS: Total of 3,419 subjects were recruited with 845 having been screened for FLD. Classification models were used in the detection of the disease. These models include logistic regression (LR), random forest (RF), artificial neural networks (ANNs), k-nearest neighbors (KNNs), extreme gradient boosting (XGBoost), and linear discriminant analysis (LDA). Predictive accuracy was assessed by area under curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS: We demonstrated that ML models give more accurate predictions, the best accuracy reached to 0.9415 in the XGBoost model. Feature importance analysis not only confirmed some well-known FLD risk factors, but also demonstrated several novel features for predicting the risk of FLD, such as hemoglobin. CONCLUSION: By implementing the XGBoost model, physicians can efficiently identify FLD in general patients; this would help in prevention, early treatment, and management of FLD.

Adding vitamin D3 to the dipeptidyl peptidase-4 inhibitor saxagliptin has the potential to protect ß-cell function in LADA patients: A 1-year pilot study.

AIMS: This trial was conducted to explore the protective effect on ß-cell function of adding vitamin D3 to DPP-4 inhibitors to treat patients with latent autoimmune diabetes in adults (LADA). METHODS: 60 LADA patients were randomized to group A (n = 21) - conventional therapy with metformin (1-1.7 g/day) and/or insulin treatment; group B (n = 20) - saxagliptin (5 mg/day) plus conventional therapy; and group C (n = 19) - vitamin D3 (2000 IU/day) plus saxagliptin and conventional therapy for 12 months. Fasting and 2-hour postprandial blood samples were collected to measure blood glucose, glycosylated hemoglobin and C-peptide levels at baseline and after 3, 6 and 12 months of treatment. RESULTS: During the 12 months of follow-up, the levels of fasting C-peptide (FCP), 2-hour postprandial C-peptide (PCP) and the C-peptide index (CPI, serum C-peptide-to-plasma glucose level ratio) were maintained in group C. In contrast to those in group A and group B, FCP levels decreased significantly in group B, and CPI levels declined significantly in group A during the 1-year treatment (P < .05). Additionally, the levels of GADA titers in group C significantly decreased compared with those at baseline (P < .05), but no significant differences in GADA titers levels were detected in group A and group B. No significant differences were found among the three groups in the levels of FCP, PCP, the CPI or GADA titers. CONCLUSIONS: The data suggested that adding 2000 IU/day vitamin D3 to saxagliptin might preserve ß-cell function in patients with LADA.