Ultrasound, anthropometry and bioimpedance: a comparison in predicting fat deposition in non-alcoholic fatty liver disease

Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices

Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, which can progress from simple steatosis to advanced cirrhosis and hepatocellular carcinoma. Clinical diagnosis of NAFLD is crucial in the early stages of the disease. The main aim of this study was to apply machine learning (ML) methods to identify significant classifiers of NAFLD using body composition and anthropometric variables. A cross-sectional study was carried out among 513 individuals aged 13 years old or above in Iran. Anthropometric and body composition measurements were performed manually using body composition analyzer InBody 270. Hepatic steatosis and fibrosis were determined using a Fibroscan. ML methods including k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Radial Basis Function (RBF) SVM, Gaussian Process (GP), Random Forest (RF), Neural Network (NN), Adaboost and Naïve Bayes were examined for model performance and to identify anthropometric and body composition predictors of fatty liver disease. RF generated the most accurate model for fatty liver (presence of any stage), steatosis stages and fibrosis stages with 82%, 52% and 57% accuracy, respectively. Abdomen circumference, waist circumference, chest circumference, trunk fat and body mass index were among the most important variables contributing to fatty liver disease. ML-based prediction of NAFLD using anthropometric and body composition data can assist clinicians in decision making. ML-based systems provide opportunities for NAFLD screening and early diagnosis, especially in population-level and remote areas.

Nutritional ultrasound®: Conceptualisation, technical considerations and standardisation

Nutritional ultrasound® is a new concept that uses ultrasound to assess body composition. It is composed of the evaluation of fat-free mass and fat mass. It is an emerging, economical, portable, non-invasive technique that evaluates the musculoskeletal area with linear, broadband, multifrequency probes, with a depth field of 20-100mm. It quantifies muscle modifications in malnutrition and provides information on functional changes (echogenicity). Although there are no validated specific cut-off points, the anterior rectum area of the quadriceps can be used as a criterion for malnutrition. The distribution of adipose tissue provides information on the energy reserve and the inflammatory pattern. It is important to integrate nutritional ultrasound® measures in clinical practice adapted to different settings and pathologies. It is necessary to establish training plans in nutritional ultrasound® for use by Endocrinology and Nutrition Specialists, with the aim of improving the diagnosis and treatment of their patients.

The Perirenal Fat Thickness Was Associated with Nonalcoholic Fatty Liver Disease in Patients with Type 2 Diabetes Mellitus

PURPOSE

Obesity is an important risk factor for nonalcoholic fatty liver disease (NAFLD). Perirenal fat and paranephric fat were seldom studied in NAFLD. We aimed to explore the relationship between perirenal fat thickness (PrFT) and paranephric fat thickness (PnFT) and NAFLD in patients with type 2 diabetes mellitus (T2DM).

PATIENTS AND METHODS

A total of 493 diabetic patients including 231 NAFLD patients were enrolled in our study from September 2019 to December 2020. Patients with NAFLD were categorized into three subgroups according to the severity and fibrosis risk of NAFLD. Anthropometric indices and clinical characteristics were collected from clinical records. PrFT and PnFT were measured via ultrasound. Multivariate logistic regression analysis was used to assess the association between PrFT, PnFT and presence, severity and advanced fibrosis risk of NAFLD.

RESULTS

Compared with non-NAFLD patients, those with NAFLD had significantly higher PrFT and PnFT. The PrFT and PnFT were independently associated with presence of NAFLD and the PrFT was independently associated with the advanced fibrosis risk of NAFLD after adjusting confounding factors.

CONCLUSION

The PrFT was independently associated with the presence and advanced fibrosis risk of NAFLD in patients with T2DM.

Comparison of bioelectrical impedance analysis, mass index, and waist circumference in assessing risk for non-alcoholic steatohepatitis

OBJECTIVE

Non-alcoholic fatty liver disease is a leading cause of liver disease worldwide and includes nonalcoholic steatohepatitis (NASH), which can progress to cirrhosis. Because NASH is associated with obesity severity, routine evaluation of obesity/body fat in clinical settings may help detect patients at risk. The aim of this study was to determine whether assessing body fat by bioelectrical impedance analysis (BIA) is superior to body mass index (BMI) and waist circumference (WC) in assessing the risk for NASH.

METHODS

In this cross-sectional study, patients were recruited and gave consent from a local hospital. All had a liver biopsy. Measurements before the biopsy included BMI, WC, and BIA. BIA was used to measure percentage body fat and fat mass (kg). Based on histology, patients were grouped into one of three categories: simple steatosis (SS), NASH, or normal liver (NL).

RESULTS

Of the 139 participants who participated, 39 were classified as SS, 53 as NASH, and 47 as NL. Regardless of sex, patients with NASH had significantly higher BMI, WC, percentage body fat and fat mass than those with NL or SS. These four parameters were significantly positively correlated with liver histology measurements. In all patients, when controlling for sex and age we found that BMI, WC, and BIA were equal at predicting the presence of NASH (P = 0.0571).

CONCLUSION

All three methods, BIA, BMI, and WC, were comparable in assessing the risk for NASH. For practical purpose in clinical settings, using BMI is acceptable.

Beverage consumption and paediatric NAFLD

Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease in children and adolescents, due to the increased worldwide incidence of obesity among children. It is now clear enough that of diet high in carbohydrates and simple sugars are associated with hepatic steatosis and non-alcoholic steatohepatitis (NASH). Several studies have shown that an increased consumption of simple sugars is also positively associated with overweight and obesity, and related co-morbidities, such as type 2 diabetes, metabolic syndrome and NAFLD. It is difficult to define the role of the various components of soft drinks and energy drinks in the pathogenesis of NAFLD and its progression in NASH, but the major role is played by high calorie and high sugar consumption, mainly fructose. In addition, other components of these beverages (e.g. xanthine) seem to have an important role in the pathogenesis of metabolic disorders, crucial pathways involved in NAFLD/NASH. The drastic reduction in the consumption of energy drinks and soft drinks is an appropriate intervention for the prevention of obesity and NAFLD in young people.