Prediction of Hepatic Steatosis (Fatty Liver) using Machine Learning

2019 ◽  
Author(s):  
Ridhi Deo ◽  
Suranjan Panigrahi
Keyword(s):  
Machine Learning ◽  
Fatty Liver ◽  
Hepatic Steatosis

scholarly journals Prospective association between adherence to the Mediterranean diet and hepatic steatosis: the Swiss CoLaus cohort study

BMJ Open ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. e040959
Author(s):  
Saman Khalatbari-Soltani ◽  
Pedro Marques-Vidal ◽  
Fumiaki Imamura ◽  
Nita G. Forouhi
Keyword(s):  
Cohort Study ◽  
Fatty Liver ◽  
Hepatic Steatosis ◽  
Mediterranean Diet ◽  
Population Level ◽  
Inverse Association ◽  
Alcoholic Fatty Liver ◽  
The Mediterranean ◽  
Prospective Association

ObjectiveThe Mediterranean diet has been promoted as a healthy dietary pattern, but whether the Mediterranean diet may help to prevent hepatic steatosis is not clear. This study aimed to evaluate the prospective association between adherence to the Mediterranean diet and risk of hepatic steatosis.DesignPopulation-based prospective cohort study.SettingThe Swiss CoLaus Study.ParticipantsWe evaluated 2288 adults (65.4% women, aged 55.8±10.0 years) without hepatic steatosis at first follow-up in 2009–2012. Adherence to the Mediterranean diet was scaled as the Mediterranean diet score (MDS) based on the Mediterranean diet pyramid ascertained with responses to Food Frequency Questionnaires.Outcome measuresNew onset of hepatic steatosis was ascertained by two indices separately: the Fatty Liver Index (FLI, ≥60 points) and the non-alcoholic fatty liver disease (NAFLD) score (≥−0.640 points). Prospective associations between adherence to the Mediterranean diet and risk of hepatic steatosis were quantified using Poisson regression.ResultsDuring a mean 5.3 years of follow-up, hepatic steatosis was ascertained in 153 (6.7%) participants by FLI criteria and in 208 (9.1%) by NAFLD score. After multivariable adjustment, higher adherence to MDS was associated with lower risk of hepatic steatosis based on FLI: risk ratio 0.84 (95% CI 0.73 to 0.96) per 1 SD of MDS; 0.85 (0.73 to 0.99) adjusted for BMI; and 0.85 (0.71 to 1.02) adjusted for both BMI and waist circumference. When using NAFLD score, no significant association was found between MDS and risk of hepatic steatosis (0.95 (0.83 to 1.09)).ConclusionA potential role of the Mediterranean diet in the prevention of hepatic steatosis is suggested by the inverse association observed between adherence to the Mediterranean diet and incidence of hepatic steatosis based on the FLI. The inconsistency of this association when hepatic steatosis was assessed by NAFLD score points to the need for accurate population-level assessment of fatty liver and its physiological markers.

scholarly journals Coupling Machine Learning and Lipidomics as a Tool to Investigate Metabolic Dysfunction-Associated Fatty Liver Disease. A General Overview

Biomolecules ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 473
Author(s):  
Helena Castañé ◽  
Gerard Baiges-Gaya ◽  
Anna Hernández-Aguilera ◽  
Elisabet Rodríguez-Tomàs ◽  
Salvador Fernández-Arroyo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Predictive Biomarkers ◽  
Metabolic Dysfunction ◽  
Complex Situation ◽  
Nonalcoholic Fatty Liver ◽  
General Overview ◽  
Diagnosis Accuracy

Hepatic biopsy is the gold standard for staging nonalcoholic fatty liver disease (NAFLD). Unfortunately, accessing the liver is invasive, requires a multidisciplinary team and is too expensive to be conducted on large segments of the population. NAFLD starts quietly and can progress until liver damage is irreversible. Given this complex situation, the search for noninvasive alternatives is clinically important. A hallmark of NAFLD progression is the dysregulation in lipid metabolism. In this context, recent advances in the area of machine learning have increased the interest in evaluating whether multi-omics data analysis performed on peripheral blood can enhance human interpretation. In the present review, we show how the use of machine learning can identify sets of lipids as predictive biomarkers of NAFLD progression. This approach could potentially help clinicians to improve the diagnosis accuracy and predict the future risk of the disease. While NAFLD has no effective treatment yet, the key to slowing the progression of the disease may lie in predictive robust biomarkers. Hence, to detect this disease as soon as possible, the use of computational science can help us to make a more accurate and reliable diagnosis. We aimed to provide a general overview for all readers interested in implementing these methods.

scholarly journals Dissociation of hepatic insulin resistance from susceptibility of nonalcoholic fatty liver disease induced by a high-fat and high-carbohydrate diet in mice

2014 ◽  
Vol 306 (6) ◽  
pp. G496-G504 ◽  
Author(s):  
Akihiro Asai ◽  
Pauline M. Chou ◽  
Heng-Fu Bu ◽  
Xiao Wang ◽  
M. Sambasiva Rao ◽  
...  
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Nonalcoholic Fatty Liver Disease ◽  
Hepatic Steatosis ◽  
Fatty Liver Disease ◽  
Diet Group ◽  
High Fat ◽  
Nonalcoholic Fatty Liver ◽  
Akt Phosphorylation ◽  
High Carbohydrate

Liver steatosis in nonalcoholic fatty liver disease is affected by genetics and diet. It is associated with insulin resistance (IR) in hepatic and peripheral tissues. Here, we aimed to characterize the severity of diet-induced steatosis, obesity, and IR in two phylogenetically distant mouse strains, C57BL/6J and DBA/2J. To this end, mice (male, 8 wk old) were fed a high-fat and high-carbohydrate (HFHC) or control diet for 16 wk followed by the application of a combination of classic physiological, biochemical, and pathological studies to determine obesity and hepatic steatosis. Peripheral IR was characterized by measuring blood glucose level, serum insulin level, homeostasis model assessment of IR, glucose intolerance, insulin intolerance, and AKT phosphorylation in adipose tissues, whereas the level of hepatic IR was determined by measuring insulin-triggered hepatic AKT phosphorylation. We discovered that both C57BL/6J and DBA/2J mice developed obesity to a similar degree without the feature of liver inflammation after being fed an HFHC diet for 16 wk. C57BL/6J mice in the HFHC diet group exhibited severe pan-lobular steatosis, a marked increase in hepatic triglyceride levels, and profound peripheral IR. In contrast, DBA/2J mice in the HFHC diet group developed only a mild degree of pericentrilobular hepatic steatosis that was associated with moderate changes in peripheral IR. Interestingly, both C57BL/6J and DBA/2J developed severe hepatic IR after HFHC diet treatment. Collectively, these data suggest that the severity of diet-induced hepatic steatosis is correlated to the level of peripheral IR, not with the severity of obesity and hepatic IR. Peripheral rather than hepatic IR is a dominant factor of pathophysiology in nonalcoholic fatty liver disease.

Sign in / Sign up

Export Citation Format

Share Document