Prospective evaluation of the prevalence of non-alcoholic fatty liver disease and steatohepatitis in a large middle-aged US cohort

Harrison, Stephen A.; Gawrieh, Samer; Roberts, K.; Lisanti, Christopher J.; Schwope, Ryan B.; Cebe, Katherine; Paradis, Valérie; Bédossa, Pierre; Whitehead, Jennifer; Labourdette, Aymeric; Miette, Véronique; Neubauer, Stefan; Fournier, C.; Paredes, Angelo H.; Alkhouri, Naim

doi:10.1016/j.jhep.2021.02.034

Cited by 141 publications

(128 citation statements)

References 39 publications

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…Although the prevalence identified here is relevant to this cohort, we do not know their true importance for other populations. For instance, a recent work established that the prevalence of NAFLD in a middle-aged population in the United States was 38%, with a NASH prevalence of 14% [ 61 ].…”

Section: Discussionmentioning

confidence: 99%

Assessment of Classification Models and Relevant Features on Nonalcoholic Steatohepatitis Using Random Forest

García-Carretero

Holgado-Cuadrado

Barquero-Pérez

2021

Entropy

View full text Add to dashboard Cite

Nonalcoholic fatty liver disease (NAFLD) is the hepatic manifestation of metabolic syndrome and is the most common cause of chronic liver disease in developed countries. Certain conditions, including mild inflammation biomarkers, dyslipidemia, and insulin resistance, can trigger a progression to nonalcoholic steatohepatitis (NASH), a condition characterized by inflammation and liver cell damage. We demonstrate the usefulness of machine learning with a case study to analyze the most important features in random forest (RF) models for predicting patients at risk of developing NASH. We collected data from patients who attended the Cardiovascular Risk Unit of Mostoles University Hospital (Madrid, Spain) from 2005 to 2021. We reviewed electronic health records to assess the presence of NASH, which was used as the outcome. We chose RF as the algorithm to develop six models using different pre-processing strategies. The performance metrics was evaluated to choose an optimized model. Finally, several interpretability techniques, such as feature importance, contribution of each feature to predictions, and partial dependence plots, were used to understand and explain the model to help obtain a better understanding of machine learning-based predictions. In total, 1525 patients met the inclusion criteria. The mean age was 57.3 years, and 507 patients had NASH (prevalence of 33.2%). Filter methods (the chi-square and Mann–Whitney–Wilcoxon tests) did not produce additional insight in terms of interactions, contributions, or relationships among variables and their outcomes. The random forest model correctly classified patients with NASH to an accuracy of 0.87 in the best model and to 0.79 in the worst one. Four features were the most relevant: insulin resistance, ferritin, serum levels of insulin, and triglycerides. The contribution of each feature was assessed via partial dependence plots. Random forest-based modeling demonstrated that machine learning can be used to improve interpretability, produce understanding of the modeled behavior, and demonstrate how far certain features can contribute to predictions.

show abstract

Section: Discussionmentioning

confidence: 99%

Assessment of Classification Models and Relevant Features on Nonalcoholic Steatohepatitis Using Random Forest

García-Carretero

Holgado-Cuadrado

Barquero-Pérez

2021

Entropy

View full text Add to dashboard Cite

show abstract

“…A pproximately 37% of adults in the United States, and as many as 70% of individuals with type 2 diabetes (T2D), have nonalcoholic fatty liver disease (NAFLD). [1][2][3] Nonalcoholic steatohepatitis (NASH), a subtype of NAFLD characterized by inflammation, ballooning, and Mallory's hyaline on liver biopsy, can lead to hepatic fibrosis, cirrhosis, and hepatocellular cancer (HCC). Both NAFLD and NASH are also associated with an increased risk of cardiovascular disease, 4 cardiovascular and liver-related mortality, and impaired health-related quality of life.…”

mentioning

confidence: 99%

Clinical Care Pathway for the Risk Stratification and Management of Patients With Nonalcoholic Fatty Liver Disease

et al. 2021

Self Cite

View full text Add to dashboard Cite

“…The term NAFLD is given to the presence of hepatic steatosis, either by imaging or histology, in the absence of secondary factors such as alcohol abuse, medications, or other causes for fatty liver disease ( 6 , 7 ). It is the most common chronic liver disease in Westernized societies, with about 50% to 60% of adults with obesity having steatosis ( 8 , 9 ). The presence of obesity, in particular when associated with T2D, increases the risk of developing the more severe form associated with hepatocyte necrosis and predominantly lobular inflammation, and risk of cirrhosis, known as nonalcoholic steatohepatitis (NASH) ( 5 ).…”

mentioning

confidence: 99%

The Emerging Role of Glucagon-like Peptide-1 Receptor Agonists for the Management of NAFLD

Chavez

Cusi

Kadiyala

2021

The Journal of Clinical Endocrinology &Amp; Metabolism

View full text Add to dashboard Cite

Context The burden of cirrhosis from NAFLD is reaching epidemic proportions in the United States. This calls for greater awareness among endocrinologists, who often see but may miss the diagnosis in adults with obesity or type 2 diabetes mellitus (T2D) who are at the highest risk. At the same time, recent studies suggest that GLP-1RAs are beneficial versus steatohepatitis (NASH) in this population. This minireview aims to assist endocrinologists to recognize the condition and recent work on the role of GLP-1RAs in NAFLD/NASH. Evidence acquisition Evidence from observational studies, randomized controlled trials, and meta-analyses. Evidence Synthesis Endocrinologists should lead multidisciplinary teams to implement recent consensus statements on NAFLD that call for screening and treatment of clinically significant fibrosis to prevent cirrhosis, especially in the high-risk groups (i.e., people with obesity, prediabetes or T2D). With no FDA-approved agents, weight loss is central to their successful management, with pharmacological treatment options limited today to vitamin E (in people without T2D) and diabetes medications that reverse steatohepatitis, such as pioglitazone or GLP-1RA. Recently the benefit of GLP-1RAs in NAFLD, suggested from earlier trials, has been confirmed in adults with biopsy-proven NASH. In 2021, the FDA also approved semaglutide for obesity management. Conclusion A paradigm change is developing between the endocrinologist’s greater awareness about their critical role to curve the epidemic of NAFLD and new clinical care pathways that include a broader use of GLP-1RAs in the management of these complex patients.

show abstract

Prospective evaluation of the prevalence of non-alcoholic fatty liver disease and steatohepatitis in a large middle-aged US cohort

Cited by 141 publications

References 39 publications

Assessment of Classification Models and Relevant Features on Nonalcoholic Steatohepatitis Using Random Forest

Assessment of Classification Models and Relevant Features on Nonalcoholic Steatohepatitis Using Random Forest

Clinical Care Pathway for the Risk Stratification and Management of Patients With Nonalcoholic Fatty Liver Disease

The Emerging Role of Glucagon-like Peptide-1 Receptor Agonists for the Management of NAFLD

Contact Info

Product

Resources

About