DXA reference values and anthropometric screening for visceral obesity in Western Australian adults

BACKGROUND Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, affecting over 30% of the United States population. Early patient identification using a simple method is highly desirable. AIM To create machine learning models for predicting NAFLD in the general United States population. METHODS Using the NHANES 1988-1994. Thirty NAFLD-related factors were included. The dataset was divided into the training (70%) and testing (30%) datasets. Twenty-four machine learning algorithms were applied to the training dataset. The best-performing models and another interpretable model ( i.e. , coarse trees) were tested using the testing dataset. RESULTS There were 3235 participants ( n = 3235) that met the inclusion criteria. In the training phase, the ensemble of random undersampling (RUS) boosted trees had the highest F1 (0.53). In the testing phase, we compared selective machine learning models and NAFLD indices. Based on F1, the ensemble of RUS boosted trees remained the top performer (accuracy 71.1% and F1 0.56) followed by the fatty liver index (accuracy 68.8% and F1 0.52). A simple model (coarse trees) had an accuracy of 74.9% and an F1 of 0.33. CONCLUSION Not every machine learning model is complex. Using a simpler model such as coarse trees, we can create an interpretable model for predicting NAFLD with only two predictors: fasting C-peptide and waist circumference. Although the simpler model does not have the best performance, its simplicity is useful in clinical practice.

show abstract

“…Waist circumference is directly associated with obesity and metabolic syndrome[ 23 , 24 ]. They are also the established risk factors of NAFLD.…”

Section: Discussionmentioning

confidence: 99%

Machine learning models for predicting non-alcoholic fatty liver disease in the general United States population: NHANES database

Atsawarungruangkit¹,

Laoveeravat²,

Promrat³

2021

WJH

View full text Add to dashboard Cite

show abstract

“…However, it is now widely accepted that VAT comprises fat deposits found throughout the body, including the omentum, mesenteric, epiploic, gonadal, epicardia, and retroperitoneal depots, and is frequently accompanied by other ectopic fat deposits. When reviewing the literature, it becomes clear that studies that present normative VAT measurements are scarce [ 63 ]. Recently, Elliot et al [ 64 ] examined the visceral fat area (VFA) in patients with EAC using computer tomography and defined visceral obesity as VFA > 163.8 cm 2 for men and 80.1 cm 2 for women, respectively.…”

Section: Epidemiologymentioning

confidence: 99%

Role of Obesity, Physical Exercise, Adipose Tissue-Skeletal Muscle Crosstalk and Molecular Advances in Barrett’s Esophagus and Esophageal Adenocarcinoma

Bilski

Pinkas

Wójcik

et al. 2022

IJMS

View full text Add to dashboard Cite

Both obesity and esophageal adenocarcinoma (EAC) rates have increased sharply in the United States and Western Europe in recent years. EAC is a classic example of obesity-related cancer where the risk of EAC increases with increasing body mass index. Pathologically altered visceral fat in obesity appears to play a key role in this process. Visceral obesity may promote EAC by directly affecting gastroesophageal reflux disease and Barrett’s esophagus (BE), as well as a less reflux-dependent effect, including the release of pro-inflammatory adipokines and insulin resistance. Deregulation of adipokine production, such as the shift to an increased amount of leptin relative to “protective” adiponectin, has been implicated in the pathogenesis of BE and EAC. This review discusses not only the epidemiology and pathophysiology of obesity in BE and EAC, but also molecular alterations at the level of mRNA and proteins associated with these esophageal pathologies and the potential role of adipokines and myokines in these disorders. Particular attention is given to discussing the possible crosstalk of adipokines and myokines during exercise. It is concluded that lifestyle interventions to increase regular physical activity could be helpful as a promising strategy for preventing the development of BE and EAC.

show abstract

“…Far more accurate measurement of whole body and regional body composition can be provided by the 3-component (fat, lean and bone) model of body composition generated by dual energy x-ray absorptiometry (DEXA). Such 3-component modelling of body composition has provided normative population data 7 , for athletes 8 and for patient specific reference data: e.g., osteoporosis 9 and diabetes 10 .…”

Section: Introductionmentioning

confidence: 99%

Adults with Crohn’s disease exhibit elevated gynoid fat and reduced android fat irrespective of disease relapse or remission

Dowling

Jakeman

Norton

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Crohn’s disease (CD) is a debilitating inflammatory bowel condition of unknown aetiology that is growing in prevalence globally. Large-scale studies have determined associations between female obesity or low body mass index (BMI) with risk of CD at all ages or 8– < 40 years, respectively. For males, low BMI entering adult life is associated with increased incidence of CD or ulcerative colitis up to 40 years later. Body composition analysis has shown that combinations of lean tissue loss and high visceral fat predict poor CD outcomes. Here, we assessed dietary intake, physical activity and whole or regional body composition of patients with CD relapse or remission. This anthropometric approach found people with CD, irrespective of relapse or remission, differed from a large representative healthy population sample in exhibiting elevated gynoid fat and reduced android fat. CD is associated with mesenteric adipose tissue, or “creeping fat”, that envelops affected intestine exclusive of other tissue; that fat is localised to the android region of the body. In this context, CD mesenteric adiposity represents a stark juxtaposition of organ-specific and regional adiposity. Although our study population was relatively small, we suggest tentatively that there is a rationale to refer to Crohn’s disease as a fatty intestine condition, akin to fatty liver conditions. We suggest that our data provide early insight into a subject that potentially warrants further investigation across a larger patient cohort.

show abstract

DXA reference values and anthropometric screening for visceral obesity in Western Australian adults

Cited by 21 publications

References 21 publications

Machine learning models for predicting non-alcoholic fatty liver disease in the general United States population: NHANES database

Machine learning models for predicting non-alcoholic fatty liver disease in the general United States population: NHANES database

Role of Obesity, Physical Exercise, Adipose Tissue-Skeletal Muscle Crosstalk and Molecular Advances in Barrett’s Esophagus and Esophageal Adenocarcinoma

Adults with Crohn’s disease exhibit elevated gynoid fat and reduced android fat irrespective of disease relapse or remission

Contact Info

Product

Resources

About