Development and application of a novel model to predict the risk of non-alcoholic fatty liver disease among lean pre-diabetics with normal blood lipid levels

Abstract

Background Non-alcoholic fatty liver disease (NAFLD) has been associated with type 2 diabetes, but its relationship with pre-diabetes is still unknown. This study aims to determine whether pre-diabetes is associated with NAFLD, followed by establishing a NAFLD predictive nomogram for lean Chinese pre-diabetics with normal blood lipids. Methods Datasets from 3 previous studies, 1 (2774 pre-diabetics with normal blood lipids for training, 925 for validation), 2 (546 for longitudinal internal validation, post-5-year follow-up), and 3 (501 from another institution for external validation), were used. Kaplan-Meier determined cumulative NAFLD hazard, and least absolute shrinkage and selection operator regression analysis uncovered its risk factors. Multivariate logistic regression analysis constructed the nomogram, followed by validation with receiver operating characteristic curve, calibration plot, and decision curve analyses. Results NAFLD incidence increased with diabetes progression, and pre-diabetics had higher cumulative risk versus non-diabetics, even for lean individuals with normal blood lipids. Six risk factors were identified: body mass index, total cholesterol, alanine aminotransferase:aspartate aminotransferase, triglyceride:high density lipoprotein cholesterol, fasting blood glucose and γ-glutamyl-transferase. The nomogram yielded areas under the curve of 0.808, 0.785, 0.796 and 0.832, for respectively, training, validation, longitudinal internal validation, and external validation, which, along with calibration curve values of p = 0.794, 0.875, 0.854 and 0.810 for those 4 datasets and decision curve analyses, validated its clinical utility. Conclusions Lean pre-diabetic Chinese with normal blood lipids have higher NAFLD risk versus non-diabetics. The nomogram is able to predict NAFLD among such individuals, with high discrimination, enabling its use for early detection and intervention.

Deep learning imaging phenotype can classify metabolic syndrome and is predictive of cardiometabolic disorders

“…The direction of these correlations aligns with the definition of metabolic syndrome, with the strongest correlations observed for waist circumference and lipid levels. Many studies have previously shown the associations between waist circumference and lipid levels with liver diseases [ 39 – 41 ].…”

Acute decompensated heart failure in patients with prediabetes: relationship with risk factors and comorbidities

“…более высокая концентрация АЛТ в крови. Предполагается, что в данном случае имеет место взаимосвязь НАЖБП и АЛТ не столько с ОДСН (NT-proBNP), сколько более высоким ИМТ и большей ОТ [13]. Но полученные результаты требуют подтверждения на большей выборке больных.…”

A dynamic machine learning model for prediction of NAFLD in a health checkup population: A longitudinal study

“…Compared to existing studies on prognosis prediction models, the predictive performance of the model developed in our study demonstrates certain advantages. In a study by Zhu et al, multivariate LR model was constructed to predict the risk of NAFLD among lean pre-diabetics with normal blood lipid levels, achieving an AUC of 0.796 in the longitudinal internal validation with a 5-year follow-up period [ 21 ]. Abeysekera et al utilized variables measured at the participants' adolescence to predict the incidence risk of NAFLD at the age of 24 using LR, yielding the highest AUROC of 0.79 [ 22 ].…”