Phenotypes of non-alcoholic fatty liver disease (NAFLD) and all-cause mortality: unsupervised machine learning analysis of NHANES III

Abstract

ObjectivesNon-alcoholic fatty liver disease (NAFLD) is a non-communicable disease with a rising prevalence worldwide and with large burden for patients and health systems. To date, the presence of unique phenotypes in patients with NAFLD has not been studied, and their identification could inform precision medicine and public health with pragmatic implications in personalised management and care for patients with NAFLD.DesignCross-sectional and prospective (up to 31 December 2019) analysis of National Health and Nutrition Examination Survey III (1988–1994).Primary and secondary outcomes measuresNAFLD diagnosis was based on liver ultrasound. The following predictors informed an unsupervised machine learning algorithm (k-means): body mass index, waist circumference, systolic blood pressure (SBP), plasma glucose, total cholesterol, triglycerides, liver enzymes alanine aminotransferase, aspartate aminotransferase and gamma glutamyl transferase. We summarised (means) and compared the predictors across clusters. We used Cox proportional hazard models to quantify the all-cause mortality risk associated with each cluster.Results1652 patients with NAFLD (mean age 47.2 years and 51.5% women) were grouped into 3 clusters: anthro-SBP-glucose (6.36%; highest levels of anthropometrics, SBP and glucose), lipid-liver (10.35%; highest levels of lipid and liver enzymes) and average (83.29%; predictors at average levels). Compared with the average phenotype, the anthro-SBP-glucose phenotype had higher all-cause mortality risk (aHR=2.88; 95% CI: 2.26 to 3.67); the lipid-liver phenotype was not associated with higher all-cause mortality risk (aHR=1.11; 95% CI: 0.86 to 1.42).ConclusionsThere is heterogeneity in patients with NAFLD, whom can be divided into three phenotypes with different mortality risk. These phenotypes could guide specific interventions and management plans, thus advancing precision medicine and public health for patients with NAFLD.

The Impact and Burden of Dietary Sugars on the Liver

“…The majority of subjects fell into the average NAFLD phenotype, whereas 6% and 10% of the remaining subjects fell into phenotypes characterized by (1) high levels of anthropometrics, systolic blood pressure, and glucose (highest all-cause mortality), or (2) high levels of liver biomarkers and cholesterol, respectively. 152 Furthermore, recent studies have demonstrated that diet and lifestyle modifications, including sugar reduction, are more effective in decreasing intrahepatic fat in NAFLD patients who are carriers of the PNPLA3 I148M gene polymorphism versus noncarriers. 153 , 154 A tailored dietary approach that accounts for differences in clinical, genetic, and metabolic characteristics between responders and nonresponders to nutrition therapies for NAFLD, including sugar reduction, may be more effective than traditional lifestyle recommendations.…”

Network pharmacological analysis on the mechanism of Linggui Zhugan decoction for nonalcoholic fatty liver disease

“…Nonalcoholic fatty liver disease (NAFLD) is a liver disorder characterized by hepatic steatosis exceeding 5%, without secondary causes. [ 1 ] NAFLD prevalence is rising worldwide, with a prevalence of 30% in China and 25% in the world. [ 2 , 3 ] NAFLD is a major cause of hepatic sclerosis, liver cancer, and other liver diseases, burdening patients and the health system.…”

Linear age-course association between non-alcoholic fatty liver disease, components of metabolic syndrome, and mortality

“…NAFLD may increase the risk of cardiovascular disease, chronic kidney disease, and some specific cancers 2,3 . However, its impact on mortality is still controversial due to the difference in the study population's characteristics and the diagnosis method of NAFLD [4][5][6][7][8] . Most NAFLD-related mortality studies were based on western people or limited by highly selected patient populations 4,5,9,10 .…”