Reducing NAFLD-screening time: A comparative study of eight diagnostic methods offering an alternative to ultrasound scans

Association between chitinase-3-like protein 1 and metabolic-associated fatty liver disease in patients with type 2 diabetes mellitus

BACKGROUND AND AIM

Early identification of liver fibrosis is essential for the prognosis of metabolic-associated fatty liver disease (MAFLD), particularly in type 2 diabetes mellitus (T2DM) patients. Here, we explored the association of chitinase-3-like protein 1 (CHI3L1) and liver fibrosis in T2DM-MAFLD patients.

METHODS

Liver fibrosis was staged in T2DM-MAFLD patients, and a liver stiffness measurement (LSM) of ≥ 8 kPa was used to differentiate between non-significant (NSLF) and significant liver fibrosis (SLF) subgroups. The two subgroups were compared for serum CHI3L1 and other parameters. Linear correlation, logistic regression, and restricted cubic spline (RCS) analyses were performed to evaluate the association between CHI3L1 and liver fibrosis. Receiver operating characteristic (ROC) curve analysis was performed to assess the diagnostic accuracy of CHI3L1.

RESULTS

Among T2DM-MAFLD, SLF patients had higher CHI3L1 compared to NSLF patients. CHI3L1 was found to be positively correlated with LSM. Multivariate logistic regression analysis suggested that CHI3L1 may be a potential independent risk factor for SLF. Further stratified analysis indicated that the odds ratios of SLF in the high CHI3L1 group were higher than in the low CHI3L1 group in the subgroups. RCS analysis suggested an increasing trend in the incidence of significant fibrosis with the rising level of CHI3L1. The area under the ROC curve for detecting significant fibrosis was 0.749 (95% CI: 0.668-0.829).

CONCLUSIONS

Serum CHI3L1 demonstrates an association with significant liver fibrosis. High serum levels of CHI3L1 may indicate the existence of significant liver fibrosis in T2DM-MAFLD patients.

Association between body roundness index and non-alcoholic fatty liver disease detected by Fibroscan in America

BACKGROUND

The prevalence of non-alcoholic fatty liver disease (NAFLD) and obesity is worldwide on the rise. Body roundness index (BRI), as a newly developed anthropometric indicator, has been recently reported to identify obesity. However, it is still unclear whether BRI is associated with the prevalence of NAFLD.

METHODS

Data were from the National Health and Nutrition Examination Survey (NHANES) 2017-2018. NAFLD was diagnosed based on hepatic steatosis defined by CAP values ≥274 dB/m. Multivariable logistic regression analysis was performed to detect the association between BRI and the odds of NAFLD. Subgroup analysis stratified by age, gender, BMI, and race was further conducted. To explore the potential ability of BRI in predicting NAFLD, the area under the curve (AUC) of BRI was calculated by receiver operating characteristic (ROC) analysis.

RESULTS

Among the 4467 study participants, 1718 (38.5%) were diagnosed with NAFLD. Compared to the non-NAFLD group, participants with NAFLD had a higher level of BRI. The positive associations between BRI and NAFLD were detected in all three models (mode 1: OR = 1.71, 95% CI: 1.65-1.78, p < 0.0001; mode 2: OR = 1.78, 95% CI: 1.71-1.86, p < 0.0001; mode3: OR = 1.23, 95% CI: 1.11-1.35, p < 0.0001). The positive association steadily existed in different subgroups after stratified by age, gender, and BMI. Moreover, the non-linear association between BRI and NAFLD was detected, presenting inverted U-shaped curves. Furthermore, BRI had a high predictive value (AUC = 0.807) in identifying NAFLD.

CONCLUSIONS

BRI was positively associated with the prevalence of NAFLD among individuals in America, regardless of age, gender, and BMI. Besides, BRI presented a high ability for identifying NAFLD.

Waist to height ratio in nonalcoholic fatty liver disease - Systematic review and meta-analysis

BACKGROUND AND AIMS

Current nonalcoholic fatty liver disease (NAFLD) guidelines do not provide any recommendations regarding the waist-to-height ratio (WHtR), a simple obesity metric calculated by dividing waist circumference by height. Therefore, we performed a systematic review and meta-analysis aiming to evaluate WHtR in NAFLD.

METHODS

We performed a systematic electronic search on PubMed, Embase, and Scopus, identifying observational studies assessing WHtR in NAFLD. QUADAS-2 tool was used to evaluate the quality of included studies. The two main statistical outcomes were the area under the curve (AUC) and the mean difference (MD).

RESULTS

We included a total of 27 studies in our quantitative and qualitative synthesis, with a total population of 93,536 individuals. WHtR was significantly higher in NAFLD patients compared to controls with an MD of 0.073 (95% CI 0.058 - 0.088). This was also confirmed after conducting a subgroup analysis according to the hepatic steatosis diagnosis method, for ultrasound (MD 0.066 [96% CI 0.051 - 0.081]) and transient elastography (MD 0.074 [96% CI 0.053 - 0.094]). Moreover, NAFLD male patients presented significantly lower WHtR compared to female patients (MD -0.022 [95% CI -0.041 - -0.004]). The AUC of WHtR for predicting NAFLD was 0.815 (95% CI 0.780 - 0.849).

CONCLUSIONS

WHtR is considerably higher in NAFLD patients compared to controls. Female NAFLD patients present higher WHtR compared to NAFLD male patients. In comparison to other presently suggested scores and markers, the WHtR's accuracy in predicting NAFLD is considered acceptable.

Diagnostic ability using fatty liver and metabolic markers for metabolic-associated fatty liver disease stratified by metabolic/glycemic abnormalities

AIMS/INTRODUCTION

Although several noninvasive predictive markers for fatty liver and metabolic markers have been used for fatty liver prediction, whether such markers can also predict metabolic-associated fatty liver disease (MAFLD) remains unclear. We aimed to examine the ability of existing fatty liver or metabolic markers to predict MAFLD.

MATERIALS AND METHODS

Participants in a high-volume center in Tokyo were classified into groups with and without MAFLD, based on the presence of metabolic abnormalities and fatty liver diagnosed through abdominal ultrasonography, between 2008 and 2018. The diagnostic abilities of three fatty liver markers: fatty liver index (FLI), hepatic steatosis index (HSI), and lipid accumulation product (LAP), and three common metabolic markers: waist-to-height ratio (WHR), body mass index (BMI), and waist circumference (WC), for predicting MAFLD, were evaluated. Analyses stratified by MAFLD subtypes were performed.

RESULTS

Of 92,374 individuals, 19,392 (36.1%) had MAFLD. The diagnostic performances for MAFLD prediction, measured as c-statistics, for FLI, HSI, LAP, WHR, BMI, and WC were 0.906, 0.892, 0.878, 0.844, 0.877, and 0.878, respectively. Optimal cutoff values for diagnosing MAFLD for FLI, HSI, LAP, WHR, BMI, and WC were 20.3, 32.7, 20.0, 0.49, 22.9, and 82.1, respectively. Analyses stratified by MAFLD subtypes, based on BMI and metabolic/glycemic abnormalities, suggested that FLI and HSI had acceptable (c-statistics >0.700) diagnostic abilities throughout all the analyses.

CONCLUSIONS

All six markers were excellent predictors of MAFLD in diagnosing among the general population, with FLI and HSI particularly useful among all sub-populations.

Artificial intelligence model with deep learning in nonalcoholic fatty liver disease diagnosis: genetic based artificial neural networks

Nonalcoholic fatty liver disease (NAFLD) is one of the most common causes of chronic liver disease in the world. The NAFLD spectrum includes simple steatosis, steatohepatitis, fibrosis, cirrhosis, and hepatocellular carcinoma (HCC). Genetic, nutritional factors, obesity, insulin resistance, gut microbiota are among the risk factors for NAFLD. The genetic variant Patatin-like phospholipase domain-containing protein 3 (PNPLA3) plays an important role in the development of a number of liver diseases ranging from steatosis, chronic hepatitis, cirrhosis and HCC. Due to the increase in the prevalence of NAFLD, new models are being developed with machine learning, deep learning, artificial neural network (ANN) algorithms in the field of artificial intelligence (AI) to determine low-cost, noninvasive diagnostic methods. Models developed with ANN from AI modules are important in order to examine biochemical and genomic information in detail in the diagnosis of NAFLD. The aim of this study is to develop a simple ANN model using biochemical and genotypic parameters in the diagnosis of NAFLD. A total of 300 patients followed up with the diagnosis of NAFLD and 100 controls were included in the study. The data set was divided into two as training and test set. Genotyping of PNPLA3 (CC, CG, GG) as genomic analysis was performed with real time PCR device. The algorithm used for the diagnosis of NAFLD was designed using age, body mass index (BMI), mean platelet volume (MPV), insulin resistance (IR), alanine aminotransferase (ALT), genotype PNPLA3 (CC, CG, GG) parameters. MLP Classifier algorithm from ANN was used in the development of the model. ANN algorithms are used in python programming language. Statistical analyzes were made in SPSS program. Percent accuracy, area under the ROC curve, confusion matrix, Positive (PPV) and Negative Predicted Value (NPV) values, precision, recall, and f1-score results were determined. The accuracy percentage was determined as 0.979 in the train set and 0.970 in the test set. The Log Loss value was set to 0.09. The developed neural network achieved an accuracy percentage of 97.0% during testing, with an area under the ROC curve value of 0.95. We think that the ANN model developed with genomic and biochemical parameters can be used as a cost-effective, noninvasive new predictive diagnostic model in clinical practice in the diagnosis of NAFLD.

Machine-Learning Algorithm for Predicting Fatty Liver Disease in a Taiwanese Population

The rising incidence of fatty liver disease (FLD) poses a health challenge, and is expected to be the leading global cause of liver-related morbidity and mortality in the near future. Early case identification is crucial for disease intervention. A retrospective cross-sectional study was performed on 31,930 Taiwanese subjects (25,544 training and 6386 testing sets) who had received health check-ups and abdominal ultrasounds in Changhua Christian Hospital from January 2009 to January 2019. Clinical and laboratory factors were included for analysis by different machine-learning algorithms. In addition, the performance of the machine-learning algorithms was compared with that of the fatty liver index (FLI). Totally, 6658/25,544 (26.1%) and 1647/6386 (25.8%) subjects had moderate-to-severe liver disease in the training and testing sets, respectively. Five machine-learning models were examined and demonstrated exemplary performance in predicting FLD. Among these models, the xgBoost model revealed the highest area under the receiver operating characteristic (AUROC) (0.882), accuracy (0.833), F1 score (0.829), sensitivity (0.833), and specificity (0.683) compared with those of neural network, logistic regression, random forest, and support vector machine-learning models. The xgBoost, neural network, and logistic regression models had a significantly higher AUROC than that of FLI. Body mass index was the most important feature to predict FLD according to the feature ranking scores. The xgBoost model had the best overall prediction ability for diagnosing FLD in our study. Machine-learning algorithms provide considerable benefits for screening candidates with FLD.

American Association of Clinical Endocrinology Clinical Practice Guideline for the Diagnosis and Management of Nonalcoholic Fatty Liver Disease in Primary Care and Endocrinology Clinical Settings: Co-Sponsored by the American Association for the Study of Liver Diseases (AASLD)

OBJECTIVE

To provide evidence-based recommendations regarding the diagnosis and management of nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH) to endocrinologists, primary care clinicians, health care professionals, and other stakeholders.

METHODS

The American Association of Clinical Endocrinology conducted literature searches for relevant articles published from January 1, 2010, to November 15, 2021. A task force of medical experts developed evidence-based guideline recommendations based on a review of clinical evidence, expertise, and informal consensus, according to established American Association of Clinical Endocrinology protocol for guideline development.

RECOMMENDATION SUMMARY

This guideline includes 34 evidence-based clinical practice recommendations for the diagnosis and management of persons with NAFLD and/or NASH and contains 385 citations that inform the evidence base.

CONCLUSION

NAFLD is a major public health problem that will only worsen in the future, as it is closely linked to the epidemics of obesity and type 2 diabetes mellitus. Given this link, endocrinologists and primary care physicians are in an ideal position to identify persons at risk on to prevent the development of cirrhosis and comorbidities. While no U.S. Food and Drug Administration-approved medications to treat NAFLD are currently available, management can include lifestyle changes that promote an energy deficit leading to weight loss; consideration of weight loss medications, particularly glucagon-like peptide-1 receptor agonists; and bariatric surgery, for persons who have obesity, as well as some diabetes medications, such as pioglitazone and glucagon-like peptide-1 receptor agonists, for those with type 2 diabetes mellitus and NASH. Management should also promote cardiometabolic health and reduce the increased cardiovascular risk associated with this complex disease.

Distinctive clinical and genetic features of lean vs overweight fatty liver disease using the UK Biobank

BACKGROUND

Lean NAFLD may differ from NAFLD found in overweight or obese patients. We used the UK biobank to conduct a cross-sectional study that examined features that distinguish lean NAFLD from overweight or obese NAFLD.

METHODS

MRI-PDFF data were used to identify patients with NAFLD, with NAFLD defined as PDFF ≥ 5%. BMI patient cohorts were identified, with lean defined as a BMI < 25, and overweight or obese defined as a BMI ≥ 25. Variables of interest to fatty liver disease, including single nucleotide polymorphisms, were chosen from the UK biobank data portal. Logistic regression was used to generate models predictive of NAFLD in each cohort.

RESULTS

1007 patients had NAFLD, and of these, 871 had BMI ≥ 25, and 136 BMI < 25. Factors associated with NAFLD in patients with BMI < 25 included male sex, white blood cell count, red blood cell count, triglycerides, ALT, creatinine, visceral adipose tissue, rs58542926 T, and rs738409 G. In contrast, factors associated with NAFLD in patients with BMI ≥ 25 included male sex, waist circumference, HDL cholesterol, triglycerides, serum glucose, ALT, creatinine, urate, visceral adipose tissue, rs1260326 T, rs1044498 C, rs58542926 T, and rs738409 G. For lean patients, our generated prediction score had an AUC of 0.92, sensitivity of 0.90 and specificity of 0.81. For overweight or obese patients, the prediction score had an AUC of 0.86, sensitivity of 0.87 and specificity of 0.70.

CONCLUSIONS

Our analysis suggests that lean and overweight or obese NAFLD are distinct entities. We have developed a risk score incorporating both clinical and genetic factors that accurately classify lean patients with NAFLD, with the potential to serve as a tool for screening purposes.

Waist-to-height ratio, an optimal anthropometric indicator for metabolic dysfunction associated fatty liver disease in the Western Chinese male population

Background

Non-alcoholic fatty liver disease (NAFLD) has been entitled as metabolic-dysfunction associated fatty liver disease (MAFLD). Therefore anthropometric indicators of adiposity may provide a non-invasive predictive and diagnostic tool for this disease. This study intended to validate and compare the MAFLD predictive and diagnostic capability of eight anthropometric indicators.

Methods

The study involved a population-based retrospective cross-sectional design. The Fangchenggang area male health and examination survey (FAMHES) was used to collect data of eight anthropometric indicators, involving body mass index (BMI), waist-to-height ratio (WHtR), waist-hip ratio (WHR), body adiposity index (BAI), cardiometabolic index (CMI), lipid accumulation product (LAP), visceral adiposity index (VAI), and abdominal volume index (AVI). Receiver operating characteristics (ROC) curves and the respective areas under the curves (AUCs) were utilized to compare the diagnostic capacity of each indicator for MAFLD and to determine the optimal cutoff points. Binary logistic regression analysis was applied to identify the odds ratios (OR) with 95% confidence intervals (95% CI) for all anthropometric indicators and MAFLD. The Spearman rank correlation coefficients of anthropometric indicators, sex hormones, and MAFLD were also calculated.

Results

All selected anthropometric indicators were significantly associated with MAFLD (P < 0.001), with an AUC above 0.79. LAP had the highest AUC [0.868 (95% CI, 0.853–0.883)], followed by WHtR [0.863 (95% CI, 0.848–0.879)] and AVI [0.859 (95% CI, 0.843–0.874)]. The cutoff values for WHtR, LAP and AVI were 0.49, 24.29, and 13.61, respectively. WHtR [OR 22.181 (95% CI, 16.216–30.340)] had the strongest association with MAFLD, regardless of potential confounders. Among all the anthropometric indicators, the strongest association was seen between LAP and sex hormones.

Conclusion

All anthropometric indicators were associated with MAFLD. WHtR was identified as the strongest predictor of MAFLD in young Chinese males, followed by LAP and AVI. The strongest association was found between LAP and sex hormones.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12944-021-01568-9.

Development and validation of a neural network for NAFLD diagnosis

Non-Alcoholic Fatty Liver Disease (NAFLD) affects about 20–30% of the adult population in developed countries and is an increasingly important cause of hepatocellular carcinoma. Liver ultrasound (US) is widely used as a noninvasive method to diagnose NAFLD. However, the intensive use of US is not cost-effective and increases the burden on the healthcare system. Electronic medical records facilitate large-scale epidemiological studies and, existing NAFLD scores often require clinical and anthropometric parameters that may not be captured in those databases. Our goal was to develop and validate a simple Neural Network (NN)-based web app that could be used to predict NAFLD particularly its absence. The study included 2970 subjects; training and testing of the neural network using a train–test-split approach was done on 2869 of them. From another population consisting of 2301 subjects, a further 100 subjects were randomly extracted to test the web app. A search was made to find the best parameters for the NN and then this NN was exported for incorporation into a local web app. The percentage of accuracy, area under the ROC curve, confusion matrix, Positive (PPV) and Negative Predicted Value (NPV) values, precision, recall and f1-score were verified. After that, Explainability (XAI) was analyzed to understand the diagnostic reasoning of the NN. Finally, in the local web app, the specificity and sensitivity values were checked. The NN achieved a percentage of accuracy during testing of 77.0%, with an area under the ROC curve value of 0.82. Thus, in the web app the NN evidenced to achieve good results, with a specificity of 1.00 and sensitivity of 0.73. The described approach can be used to support NAFLD diagnosis, reducing healthcare costs. The NN-based web app is easy to apply and the required parameters are easily found in healthcare databases.

The usefulness of obesity and lipid-related indices to predict the presence of Non-alcoholic fatty liver disease

Background

Conicity index, body-shape index, lipid accumulation product (LAP), waist circumference (WC), triglyceride, triglyceride-glucose (TyG) index, hepatic steatosis index (HSI), waist-to-height ratio (WHtR), TyG index-related parameters (TyG-WHtR, TyG-BMI, TyG-WC), body mass index (BMI), visceral adiposity index, triglyceride to high-density lipoprotein cholesterol ratio and body roundness index have been reported as reliable markers of non-alcoholic fatty liver disease (NAFLD). However, there is debate about which of the above obesity and lipid-related indices has the best predictive performance for NAFLD risk.

Methods

This study included 6870 female and 7411 male subjects, and 15 obesity and lipid-related indices were measured and calculated. NAFLD was diagnosed by abdominal ultrasound. The area under the curve (AUC) of 15 obesity and lipid-related indices were calculated by receiver operating characteristic (ROC) analysis.

Results

Among the 15 obesity and lipid-related indices, the TyG index-related parameters had the strongest association with NAFLD. ROC analysis showed that except for ABSI, the other 14 parameters had high predictive value in identifying NAFLD, especially in female and young subjects. Most notably, TyG index-related parameters performed better than other parameters in predicting NAFLD in most populations. In the female population, the AUC of TyG-WC for predicting NAFLD was 0.9045, TyG-BMI was 0.9084, and TyG-WHtR was 0.9071. In the male population, the AUC of TyG-WC was 0.8356, TyG-BMI was 0.8428, and TyG-WHtR was 0.8372. In addition, BMI showed good NAFLD prediction performance in most subgroups (AUC>0.8).

Conclusions

Our data suggest that TyG index-related parameters, LAP, HSI, BMI, and WC appear to be good predictors of NAFLD. Of these parameters, TyG index-related parameters showed the best predictive potential.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12944-021-01561-2.

Performance of Fatty Liver Index in Identifying Non-Alcoholic Fatty Liver Disease in Population Studies. A Meta-Analysis

Background. Fatty liver index (FLI) is a non-invasive tool used to stratify the risk of non-alcoholic fatty liver disease (NAFLD) in population studies; whether it can be used to exclude or diagnose this disorder is unclear. We conducted a meta-analysis to assess the prevalence of NAFLD in each FLI class and the performance of FLI in detecting NAFLD. Methods. Four databases were searched until January 2021 (CRD42021231367). Original articles included were those reporting the performance of FLI and adopting ultrasound, computed tomography, or magnetic resonance as a reference standard. The numbers of subjects with NAFLD in FLI classes <30, 30–60, and ≥60, and the numbers of subjects classified as true/false positive/negative when adopting 30 and 60 as cut-offs were extracted. A random-effects model was used for pooling data. Results. Ten studies were included, evaluating 27,221 subjects without secondary causes of fatty liver disease. The prevalence of NAFLD in the three FLI classes was 14%, 42%, and 67%. Sensitivity, specificity, positive predictive value, negative predictive value, likelihood ratio for positive results, likelihood ratio for negative results, and diagnostic odds ratio were 81%, 65%, 53%, 84%, 2.3, 0.3, and 7.8 for the lower cut-off and 44%, 90%, 67%, 76%, 4.3, 0.6, and 7.3 for the higher cut-off, respectively. A similar performance was generally found in studies adopting ultrasound versus other imaging modalities. Conclusions. FLI showed an adequate performance in stratifying the risk of NAFLD. However, it showed only weak evidence of a discriminatory performance in excluding or diagnosing this disorder.

Composite BMI and Waist-to-Height Ratio Index for Risk Assessment of Non-alcoholic Fatty Liver Disease in Adult Populations

Background: As obesity becomes more prevalent, non-alcoholic fatty liver disease (NAFLD) is also becoming a major worldwide health problem and the most common cause of chronic liver disease. A new obesity classification method based on a composite index which includes both the body mass index (BMI) and the waist-to-height ratio (WHtR) was recently proposed. However, the usefulness of this approach to assess the risk of NAFLD is unclear. Methods: This is a cross-sectional study of 1,276 adult individuals in Dalian, China. The Mann Whitney U test, χ2 test and t-test were used to compare differences between groups. Binary logistic regression analysis was used to identify independent risk factors. Based on BMI and WHtR tertiles, individuals were divided into five new groups. Spearman correlation and receiver operating characteristic curve (ROC) analyses were performed to compare the NAFLD risk factors among groups based on BMI alone, WHtR alone, or the combination of both indexes. Results: BMI, waistline circumference (WC), WHtR, alanine aminotransferase (ALT), weight, triglycerides (TG), γ-glutamyl transpeptidase (GGT), serum uric acid (SUA), red blood cell (RBC) counts, hemoglobin levels (HGB), fasting blood glucose (FBG) and aspartate aminotransferase (AST) levels were identified as high risk factors for NAFLD (all AUC > 0.7). Logistic regression analysis suggested that BMI and WHtR were independent predictors of the appearance of NAFLD (the ORs for BMI and WHtR were 1.595 and 4.060E-11, respectively; all P < 0.001). The combination of BMI and WHtR tertiles significantly improved the correlation coefficient and Area under the receiver operating characteristic curve (AUC) for NAFLD risk factors in subjects classified as overweight or obese when compared with either BMI or WHtR alone. Conclusions: BMI, WC, WHtR, ALT, weight, TG, GGT, SUA, RBC, HGB, FBG, AST were high risk factors for NAFLD. The composite BMI and WHtR index improved body fat classification and the ability to detect individuals with NAFLD risk, offering a more precise method for the early identification of high- and low-risk NAFLD patients.

Relationship between triglyceride glucose index and the incidence of non-alcoholic fatty liver disease in the elderly: a retrospective cohort study in China

OBJECTIVE

Non-alcoholic fatty liver disease (NAFLD) is one of the major causes of liver-related diseases but relationship between triglyceride glucose (TyG) and NAFLD in the elderly is not reported yet. In this study, we investigated the role of TyG index for predicting the incidence of NAFLD in the elderly.

DESIGN AND SETTING

This is a prospective cohort study in Henan, China, from 2011 to 2018.

PARTICIPANTS AND METHODS

In total, 46 693 elderly who participated in a routine physical examination programme from 2011 to 2018 were included in this study. TyG index was calculated as ln (fasting triglyceride (mg/dL)×fasting plasma glucose (mg/dL)/2), while NAFLD was defined as hepatic steatosis after excluding other causes based on the results of abdominal ultrasonography; Cox regression model was performed to explore the relationship between TyG index and NAFLD. Also, mediation effect was used to analyse the role of the TyG index in WHtR (waist-to-height ratio) and NAFLD.

RESULTS

During the 149 041 person-years follow-up, a total of 5660 NAFLD events occurred (3.80/100 person-years). After adjusting for potential confounding factors, quartiles 4 of TyG index significantly increased the incidence of NAFLD compared with quartile 1, the HRs and 95% CI were 1.314 (1.234 to 1.457). In addition, TyG index played a partial mediating role in the relationship between WHtR and NAFLD and indirect effect was 1.009 (1.006 to 1.011).

CONCLUSION

Higher TyG index was associated with higher risk of NAFLD in the aged, and therefore, TyG index may be a novel predictor for incidence of NAFLD. Further, regular examination and evaluation of the TyG index might be useful for controlling the occurrence of NAFLD.

Selecting the best machine learning algorithm to support the diagnosis of Non-Alcoholic Fatty Liver Disease: A meta learner study

Background & aims

Liver ultrasound scan (US) use in diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD) causes costs and waiting lists overloads. We aimed to compare various Machine learning algorithms with a Meta learner approach to find the best of these as a predictor of NAFLD.

Methods

The study included 2970 subjects, 2920 constituting the training set and 50, randomly selected, used in the test phase, performing cross-validation. The best predictors were combined to create three models: 1) FLI plus GLUCOSE plus SEX plus AGE, 2) AVI plus GLUCOSE plus GGT plus SEX plus AGE, 3) BRI plus GLUCOSE plus GGT plus SEX plus AGE. Eight machine learning algorithms were trained with the predictors of each of the three models created. For these algorithms, the percent accuracy, variance and percent weight were compared.

Results

The SVM algorithm performed better with all models. Model 1 had 68% accuracy, with 1% variance and an algorithm weight of 27.35; Model 2 had 68% accuracy, with 1% variance and an algorithm weight of 33.62 and Model 3 had 77% accuracy, with 1% variance and an algorithm weight of 34.70. Model 2 was the most performing, composed of AVI plus GLUCOSE plus GGT plus SEX plus AGE, despite a lower percentage of accuracy.

Conclusion

A Machine Learning approach can support NAFLD diagnosis and reduce health costs. The SVM algorithm is easy to apply and the necessary parameters are easily retrieved in databases.

Which Metabolic Index is Appropriate for Predicting Non-alcoholic Steatohepatitis?

BACKGROUND

There are controversial ideas about the application of metabolic indices for the prediction of nonalcoholic steatohepatitis (NASH). In this study, we evaluated some novel metabolic indices for the screening of NASH.

METHODS

This prospective case-control study was performed in a gastroenterology outpatient clinic. Consecutively selected patients with persistently elevated aminotransferase levels and evidence of fatty liver in ultrasonography were enrolled. Those with other etiologies of aminotransferase elevation were excluded. The remaining was presumed to have NASH. The control group consisted of age and sex-matched subjects with normal liver function tests and liver ultrasound examinations.

RESULTS

Finally, 94 patients with steatohepatitis and 106 controls were included in the project. The mean liver fat content (LFC), aspartate aminotransferase, and alanine aminotransferase levels were significantly lower in the control group than in the NASH group. LFC was independently associated with the presence of NASH in logistic regression analysis. LFC had a good area under the curve for the prediction of NASH in ROC (receiver operating characteristic curve) analysis.

CONCLUSION

LFC seems to be a reliable metabolic index for the detection of patients with NASH.

Non-Alcoholic Fatty Liver Disease is Associated with Higher Metabolic Expenditure in Overweight and Obese Subjects: A Case-Control Study

Non-alcoholic fatty liver disease (NAFLD) is a common condition in Western countries. However, their metabolic characteristics are poorly known even though they could be important. Therefore, the objective of this study was to measure resting metabolic parameters in overweight/obese adults with hepatic steatosis compared to controls, matched for age, sex, and obesity level. Hepatic steatosis was diagnosed with liver ultrasound. Energy metabolism was measured with indirect calorimetry: energy expenditure (REE), predicted REE, the ratio between REE and the predicted REE, and the respiratory quotient (RQ) were reported. We measured some anthropometric, body composition, and bio-humoral parameters; 301 participants with NAFLD were matched for age, sex, and obesity level with 301 participants without NAFLD. People with NAFLD showed significantly higher REE (1523 ± 238 vs. 1464 ± 212 kcal, p = 0.005), REE/REE predicted ratio (98.2 ± 9.4 vs. 95.7 ± 8.1, p = 0.002), and RQ (0.88 ± 0.08 vs. 0.85 ± 0.07, p = 0.03). Moreover, the NAFLD group had significantly higher inflammatory and insulin-resistance parameters compared to controls. In conclusion, NAFLD is associated with a significantly higher metabolic expenditure, as measured with indirect calorimetry, compared to a similar cohort of individuals without this condition. Higher inflammatory levels in patients with NAFLD can probably explain our findings, even if other research is needed on this issue.