scholarly journals Predicting and elucidating the etiology of fatty liver disease using a machine learning-based approach: an IMI DIRECT study

2020 ◽  
Author(s):  
Naeimeh Atabaki-Pasdar ◽  
Mattias Ohlsson ◽  
Ana Viñuela ◽  
Francesca Frau ◽  
Hugo Pomares-Millan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Prediction Models ◽  
Cell Function ◽  
Area Under The Curve ◽  
Liver Fat ◽  
Irreversible Damage ◽  
Alcoholic Fatty Liver

ABSTRACTBackgroundNon-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in type 2 diabetes (T2D) and beyond. Early diagnosis of NAFLD is important, as this can help prevent irreversible damage to the liver and ultimately hepatocellular carcinomas.Methods and FindingsUtilizing the baseline data from the IMI DIRECT participants (n=1514) we sought to expand etiological understanding and develop a diagnostic tool for NAFLD using machine learning. Multi-omic (genetic, transcriptomic, proteomic, and metabolomic) and clinical (liver enzymes and other serological biomarkers, anthropometry, and measures of beta-cell function, insulin sensitivity, and lifestyle) data comprised the key input variables. The models were trained on MRI image-derived liver fat content (<5% or ≥5%). We applied LASSO (least absolute shrinkage and selection operator) to select features from the different layers of omics data and Random Forest analysis to develop the models. The prediction models included clinical and omics variables separately or in combination. A model including all omics and clinical variables yielded a cross-validated receiver operator characteristic area under the curve (ROCAUC) of 0.84 (95% confidence interval (CI)=0.82, 0.86), which compared with a ROCAUC of 0.82 (95% CI=0.81, 0.83) for a model including nine clinically-accessible variables. The IMI DIRECT prediction models out-performed existing non-invasive NAFLD prediction tools.ConclusionsWe have developed clinically useful liver fat prediction models (see: www.predictliverfat.org) and identified biological features that appear to affect liver fat accumulation.

scholarly journals Relationship between Muscle Mass and Non-Alcoholic Fatty Liver Disease

Biology ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 122
Author(s):  
Jun-Hyuk Lee ◽  
Hye-Sun Lee ◽  
Byoung-Kwon Lee ◽  
Yu-Jin Kwon ◽  
Ji-Won Lee
Keyword(s):  
Skeletal Muscle ◽  
Risk Factor ◽  
Liver Disease ◽  
Fatty Liver ◽  
Muscle Mass ◽  
Fatty Liver Disease ◽  
Skeletal Muscle Mass ◽  
Liver Fat ◽  
Alcoholic Fatty Liver ◽  
Alcoholic Fatty Liver Disease

Although sarcopenia is known to be a risk factor for non-alcoholic fatty liver disease (NAFLD), whether NAFLD is a risk factor for the development of sarcopenia is not clear. We investigated relationships between NAFLD and low skeletal muscle mass index (LSMI) using three different datasets. Participants were classified into LSMI and normal groups. LSMI was defined as a body mass index (BMI)-adjusted appendicular skeletal muscle mass <0.789 in men and <0.512 in women or as the sex-specific lowest quintile of BMI-adjusted total skeletal muscle mass. NAFLD was determined according to NAFLD liver fat score or abdominal ultrasonography. The NAFLD groups showed a higher hazard ratios (HRs) with 95% confidence intervals (CIs) for LSMI than the normal groups (HRs = 1.21, 95% CIs = 1.05–1.40). The LSMI groups also showed a higher HRs with 95% CIs for NAFLD than normal groups (HRs = 1.56, 95% CIs = 1.38–1.78). Participants with NAFLD had consistently less skeletal muscle mass over 12 years of follow-up. In conclusion, LSMI and NAFLD showed a relationship. Maintaining muscle mass should be emphasized in the management of NAFLD.

Is liver fat detrimental to vessels?: intersections in the pathogenesis of NAFLD and atherosclerosis

2008 ◽  
Vol 115 (1) ◽  
pp. 1-12 ◽  
Author(s):  
Paola Loria ◽  
Amedeo Lonardo ◽  
Giovanni Targher
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Molecular Mechanisms ◽  
Treatment Strategies ◽  
Liver Fat ◽  
Cvd Risk ◽  
Alcoholic Fatty Liver ◽  
Insulin Resistant ◽  
Major Player

NAFLD (non-alcoholic fatty liver disease) encompasses the spectrum of fatty liver disease in insulin-resistant individuals who often display T2DM (Type 2 diabetes mellitus) and obesity. The present review highlights the pathophysiological basis and clinical evidence for a possible causal linkage between NAFLD and CVD (cardiovascular disease). The role of traditional and non-traditional CVD risk factors in the pathophysiology of NAFLD is considered in the first part of the review, with the basic science shared by atherogenesis and hepatic steatogenesis discussed in depth in the second part. In conclusion, NAFLD is not an innocent bystander, but a major player in the development and progression of CVD. NAFLD and CVD also share similar molecular mechanisms and targeted treatment strategies. On the research side, studies should focus on interventions aimed at restoring energy homoeostasis in lipotoxic tissues and at improving hepatic (micro)vascular blood supply.

scholarly journals Coffee prevents fatty liver disease induced by a high-fat diet by modulating pathways of the gut–liver axis

2019 ◽  
Vol 8 ◽  
Author(s):  
Paola Vitaglione ◽  
Giovanna Mazzone ◽  
Vincenzo Lembo ◽  
Giuseppe D'Argenio ◽  
Antonella Rossi ◽  
...  
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
High Fat Diet ◽  
Fatty Liver Disease ◽  
Coffee Consumption ◽  
Liver Fat ◽  
Standard Diet ◽  
High Fat ◽  
Metabolic Derangement ◽  
Alcoholic Fatty Liver

AbstractCoffee consumption is inversely associated with the risk of non-alcoholic fatty liver disease (NAFLD). A gap in the literature still exists concerning the intestinal mechanisms that are involved in the protective effect of coffee consumption towards NAFLD. In this study, twenty-four C57BL/6J mice were divided into three groups each receiving a standard diet, a high-fat diet (HFD) or an HFD plus decaffeinated coffee (HFD+COFFEE) for 12 weeks. Coffee supplementation reduced HFD-induced liver macrovesicular steatosis (P < 0·01) and serum cholesterol (P < 0·001), alanine aminotransferase and glucose (P < 0·05). Accordingly, liver PPAR- α (P < 0·05) and acyl-CoA oxidase-1 (P < 0·05) as well as duodenal ATP-binding cassette (ABC) subfamily A1 (ABCA1) and subfamily G1 (ABCG1) (P < 0·05) mRNA expressions increased with coffee consumption. Compared with HFD animals, HFD+COFFEE mice had more undigested lipids in the caecal content and higher free fatty acid receptor-1 mRNA expression in the duodenum and colon. Furthermore, they showed an up-regulation of duodenal and colonic zonulin-1 (P < 0·05), duodenal claudin (P < 0·05) and duodenal peptide YY (P < 0·05) mRNA as well as a higher abundance of Alcaligenaceae in the faeces (P < 0·05). HFD+COFFEE mice had an energy intake comparable with HFD-fed mice but starting from the eighth intervention week they gained significantly less weight over time. Data altogether showed that coffee supplementation prevented HFD-induced NAFLD in mice by reducing hepatic fat deposition and metabolic derangement through modification of pathways underpinning liver fat oxidation, intestinal cholesterol efflux, energy metabolism and gut permeability. The hepatic and metabolic benefits induced by coffee were accompanied by changes in the gut microbiota.

scholarly journals Magnesium Intake Is Inversely Associated with the Risk of Non-Alcoholic Fatty Liver Disease Among American Young adults

2020 ◽  
Vol 4 (Supplement_2) ◽  
pp. 1446-1446
Author(s):  
Liping Lu ◽  
Cheng Chen ◽  
Yuexia Li ◽  
Lisa Vanwagner ◽  
Wenzhi Guo ◽  
...  
Keyword(s):  
Young Adults ◽  
Liver Disease ◽  
Coronary Artery ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Lower Risk ◽  
Liver Fat ◽  
Inverse Association ◽  
Alcoholic Fatty Liver ◽  
Alcoholic Fatty Liver Disease

Abstract Objectives To examine magnesium (Mg) intake from diet and supplements during young adulthood in relation to risk of non-alcoholic fatty liver disease (NAFLD) in midlife. Methods A total of 2712 black and white American adults aged 18 to 30 years were recruited in the Coronary Artery Risk Development in Young Adult (CARDIA) study in 1985–1986 (baseline) with 8 additional examinations during 25 years thereafter. Mg intake was assessed at baseline and exam years 7 and 20 using the CARDIA diet history questionnaires. Computed tomography (CT) scanning was performed at exam year 25 (2010–2011) to ascertain NAFLD cases, which was defined as liver attenuation (LA) ≤51 Hounsfield units after exclusion for other causes of liver fat. Logistic regression was used to examine the association between cumulative average Mg intake and the risk of NAFLD. Results At exam year 25, 638 NAFLD cases were documented. An inverse association between total Mg intake (from diet and supplements) and NAFLD risk was observed after adjustment sociodemographics, major lifestyle factors, dietary quality, and clinical measurements (body mass index, blood pressure, lipid profiles, and fasting insulin). Compared with participants in the lowest quintile of Mg intake, those in the highest quintile had a 54% lower risk of NAFLD [multivariable-adjusted odds ratio = 0.46, 95% confidence interval = (0.25, 0.87), P for trend = 0.0498]. Consistently, there was an inverse association between whole grain consumption (a major food source of magnesium) and NAFLD risk. Conclusions This study suggests that higher intake of Mg throughout adulthood is associated with a lower risk of NAFLD in middle age. Funding Sources The Coronary Artery Risk Development in Young Adults Study is supported by grants from the National Heart, Lung, and Blood Institute (NHLBI) in collaboration with the University of Alabama at Birmingham, Northwestern University, University of Minnesota, and Kaiser Foundation Research Institute.This study is also partially supported by the NIH grants and NHLBI.

Sign in / Sign up

Export Citation Format

Share Document