Predictor Of Nonalcoholic Fatty Liver Disease Research Articles

Elevated non-HDL-C to HDL-C ratio as a marker for NAFLD and liver fibrosis risk: a cross-sectional analysis.

Dyslipidemia is a known independent risk factor for Nonalcoholic fatty liver disease (NAFLD). However, the relationship between NAFLD and the serum non-high-density lipoprotein cholesterol (non-HDL-C) to high-density lipoprotein cholesterol (HDL-C) ratio remains unclear. This study examined the association between the non-HDL-C to HDL-C ratio and NAFLD prevalence, including liver steatosis and fibrosis levels in the population. We conducted a cross-sectional study using data from the National Health and Nutrition Examination Survey (NHANES) 2017-2018, including 4798 participants. Liver ultrasound and Transient Elastography (TE) were used to assess fibrosis and steatosis. Adjusted multivariable regression analyses, subgroup analyses based on BMI and sex, and a generalized additive model were employed to investigate the relationship between the non-HDL-C/HDL-C ratio and NAFLD. Among the 4798 participants, 39.27% (n = 1,884) had NAFLD. Significant positive correlations between non-HDL-C/HDL-C and NAFLD risk were found across all models, with sex-stratified analyses indicating higher risk in men. Liver fibrosis was also associated with non-HDL-C/HDL-C ratios. The Receiver operating characteristic (ROC) analysis shows non-HDL-C/HDL-C as a better predictor for NAFLD than non-HDL-C or HDL-C alone. Elevated non-HDL-C/HDL-C levels are independently associated with increased NAFLD and liver fibrosis risk in the American population, suggesting its utility in predicting NAFLD and related liver fibrosis.

Advancing non-alcoholic fatty liver disease prediction: a comprehensive machine learning approach integrating SHAP interpretability and multi-cohort validation.

Non-alcoholic fatty liver disease (NAFLD) represents a major global health challenge, often undiagnosed because of suboptimal screening tools. Advances in machine learning (ML) offer potential improvements in predictive diagnostics, leveraging complex clinical datasets. We utilized a comprehensive dataset from the Dryad database for model development and training and performed external validation using data from the National Health and Nutrition Examination Survey (NHANES) 2017-2020 cycles. Seven distinct ML models were developed and rigorously evaluated. Additionally, we employed the SHapley Additive exPlanations (SHAP) method to enhance the interpretability of the models, allowing for a detailed understanding of how each variable contributes to predictive outcomes. A total of 14,913 participants were eligible for this study. Among the seven constructed models, the light gradient boosting machine achieved the highest performance, with an area under the receiver operating characteristic curve of 0.90 in the internal validation set and 0.81 in the external NHANES validation cohort. In detailed performance metrics, it maintained an accuracy of 87%, a sensitivity of 92.9%, and an F1 score of 0.92. Key predictive variables identified included alanine aminotransferase, gammaglutamyl transpeptidase, triglyceride glucose-waist circumference, metabolic score for insulin resistance, and HbA1c, which are strongly associated with metabolic dysfunctions integral to NAFLD progression. The integration of ML with SHAP interpretability provides a robust predictive tool for NAFLD, enhancing the early identification and potential management of the disease. The model's high accuracy and generalizability across diverse populations highlight its clinical utility, though future enhancements should include longitudinal data and lifestyle factors to refine risk assessments further.

Remission of Nonalcoholic Fatty Liver Disease After Radical Surgery in Patients with Colorectal Cancer: A Single-Center Retrospective Study.

Purpose: The purpose of this study was to investigate the relationship between remission of nonalcoholic fatty liver disease (NAFLD) and radical surgery for colorectal cancer (CRC) patients. Methods: From January 2014 to December 2021, data of patients with concurrent CRC and NAFLD who underwent radical surgery in a single-center hospital were retrospectively collected. NAFLD was defined as a mean computed tomography (CT) liver attenuation value of <40 Hounsfield units (HUs). Comparison of preoperative and 1-year postoperative CT images was performed to evaluate the change of NAFLD. Multivariate logistic regression analysis was performed to identify independent predictive factors for NAFLD remission. The Kaplan-Meier method was used to estimate overall survival (OS) and disease-free survival (DFS) between the remission group and no remission group. Results: In this study, a total of 55 eligible patients were included. The remission group had 33 (60.0%) patients and the no remission group had 22 (40.0%) patients. The mean preoperative weight was 66.1 ± 9.9 kg. The mean preoperative body mass index (BMI) was 25.4 ± 2.5 kg/m2. We found that the average weight was significantly decreased (P < 0.01), average BMI was significantly decreased (P < 0.01), and HU score was significantly increased (P < 0.01). By comparing baseline characteristics between the remission group and no remission group, we found that the remission group exhibited larger tumor sizes (P = 0.036) than the no remission group. In the multivariate logistic regression analysis, we found that weight change was a predictor for NAFLD (odds ratio = 0.764, 95% confidence interval = 0.618-0.944, P = 0.013). We did not find any statistically significant differences in OS (P = 0.182) or DFS (P = 0.248) between the remission group and no remission group. Conclusions: The NAFLD remission rate reached 60.0% for CRC patients 1 year after radical surgery. In addition, we found that weight change was a predictor of NAFLD remission.

Development and Validation of a Risk Prediction Model for NAFLD: A Study Based on a Physical Examination Population.

To construct and validate a precise and personalized predictive model for non-alcoholic fatty liver disease (NAFLD) to enhance NAFLD screening and healthcare administration. A total of 730 participants' clinical information and outcome measurements were gathered and randomly divided into training and validation sets in a ratio of 3:7. Using the least absolute shrinkage and selection operator (LASSO) regression and multiple logistic regression, a nomogram was established to select risk predictor variables. The NAFLD prediction model was validated through the receiver operating characteristic (ROC) curve, calibration plot, and decision curve analysis (DCA). After random grouping, the cohort comprised 517 in the training set and 213 in the validation set. The prediction model employed nine of the 20 selected variables, namely gender, hypertension, waist circumference, body mass index, blood platelet, triglycerides, high-density lipoprotein cholesterol, plasma glucose, and alanine aminotransferase. ROC curve analysis yielded an area under the curve values of 0.877 (95% Confidence Interval [CI]: 0.848-0.907) for the training set and 0.871 (95% CI: 0.825-0.917) for the validation set. Optimal critical values were determined as 0.472 (0.786, 0.825) in the training set and 0.457 (0.743, 0.839) in the validation set. Calibration curves for both sets showed proximity to the ideal diagonal, with P-values of 0.972 and 0.370 for the training and validation sets, respectively (P > 0.05). DCA indicated favorable clinical applicability of the model. We constructed a nomogram model that could complement traditional NAFLD detection methods, aiding in individualized risk assessment for NAFLD.

Improving nonalcoholic fatty liver disease classification performance with latent diffusion models

Integrating deep learning with clinical expertise holds great potential for addressing healthcare challenges and empowering medical professionals with improved diagnostic tools. However, the need for annotated medical images is often an obstacle to leveraging the full power of machine learning models. Our research demonstrates that by combining synthetic images, generated using diffusion models, with real images, we can enhance nonalcoholic fatty liver disease (NAFLD) classification performance even in low-data regime settings. We evaluate the quality of the synthetic images by comparing two metrics: Inception Score (IS) and Fréchet Inception Distance (FID), computed on diffusion- and generative adversarial network (GAN)-generated images. Our results show superior performance for the diffusion-generated images, with a maximum IS score of 1.90 compared to 1.67 for GANs, and a minimum FID score of 69.45 compared to 100.05 for GANs. Utilizing a partially frozen CNN backbone (EfficientNet v1), our synthetic augmentation method achieves a maximum image-level ROC AUC of 0.904 on a NAFLD prediction task.

Prevalence of Nonalcoholic Fatty Liver Disease at a Tertiary Care Center in Saudi Arabia.

To determine the prevalence of nonalcoholic fatty liver disease (NAFLD) in patients who received abdominal imaging and to assess the clinical and metabolic characteristics of NAFLD. This is a retrospective study of 500 family medicine patients (aged 18 years and older) who completed abdominal imaging at King Faisal Specialist Hospital & Research Centre, Riyadh, Saudi Arabia, from January 2016 through June 2020. The patients enrolled had a mean age of 49.41 ± 14.80 years, with 300 females and 349 of Saudi nationality. The mean body mass index (BMI) was 29.43 ± 6.61 kg/m2, while 373 of the enrolled subjects were either overweight or obese. Half of our patients had some form of fatty liver in the imaging results. Regarding chronic medical conditions, 33.4%, 31.4%, and 29.4% had a history of hypertension, type 2 diabetes mellitus (DM2), and dyslipidemia, respectively. The mean Fibrosis-4 (FIB-4) index was 0.94 ± 0.72. Body mass index was higher among fatty liver patients (p = 0.001). Hypertension, coronary artery disease, dyslipidemia, and DM2 were more common in the fatty liver group. Our findings reiterate the significance of obesity and the coexistence of cardiovascular risk factors in NAFLD. Further studies are needed to corroborate and expand our findings, enabling more refined strategies for the prevention, risk prediction, early detection, and management of NAFLD.

Fatty liver biomarkers and insulin resistance indices in the prediction of non-alcoholic fatty liver disease in Ghanaian patients.

Scant West African data on non-alcoholic fatty liver disease (NAFLD) means there is little representation of this population in the modelling used to derive biomarkers and predictive indices for risk stratification of patients for the presence of hepatic steatosis. This study evaluates the performance of the fatty liver index (FLI), hepatic steatosis index (HSI) and triglyceride-glucose (TyG) index and its derivatives in predicting ultrasound detected NAFLD in a locally resident population of Ghanaian participants. A post hoc analysis of data from a cross sectional assessment of NAFLD and cardiovascular risk was performed. Data from 210 participants without significant alcohol intake, or secondary causes of fatty liver and not on steatogenic drugs was evaluated. A structured questionnaire had been used to collect demographic data, medical and drug history. Anthropometry, blood sampling for liver chemistry and fasting lipids were performed. Hepatic steatosis was detected by ultrasonography. A retrospective analysis involving multivariate binary logistic regression assessed FLI, HIS, TyG (and its derivatives) as predictors of NAFLD with p < .05 considered statistically significant. Sensitivity, specificity, predictive values, likelihood ratios were calculated and accuracy of the proxies evaluated from area under the receiver operating characteristics curve (AUROC). All the biomarkers and indices were significantly associated with NAFLD (p ≤ .001). All the lipid and fatty liver indices assessed performed acceptably as predictors of NAFLD. FLI (AUC = 0.8, 95% CI [0.74-0.87]), TyG-WC (AUC = 0.81, 95% CI [0.75-0.88]) and TyG-WHtR (AUC = 0.81, 95% CI [0.74-0.88]) performed best at predicting NAFLD. Whilst in all cases the markers had good specificity (>90%) they lacked sufficient sensitivity with FLI having the highest sensitivity of 36.7%. Their overall accuracy was greater than 70% in each case. The overall accuracy of HSI, FLI, TyG index and its derivatives (TyG WHtR, TyG BMI, TyG WC) was acceptable for predicting NAFLD in this population. Given their performance in this study and in light of their low cost, accessibility, easy interpretation and non-invasive nature; they are suitable tools for screening in the Ghanaian population.

SAT356 Predicting Nonalcoholic Fatty Liver Disease in Adolescent Girls with Polycystic Ovary Syndrome and Obesity

Abstract Disclosure: J.S. Lo: None. F. Bril: None. A. Taylor: None. N. Morelli: None. M.A. Ware: None. Y. Garcia-Reyes: None. M.J. McPhaul: Employee; Self; Quest Diagnostics. M.G. Cree: Consulting Fee; Self; Pollie, Inc. Research Investigator; Self; Amino Corp. Adolescents with obesity and polycystic ovary syndrome (PCOS) have significant insulin resistance and are at high risk of nonalcoholic fatty liver disease (NAFLD). This risk may be related to increased growth hormone and insulin resistance associated with puberty, in addition to excess testosterone. NAFLD is difficult to diagnose in obese individuals. Intact insulin (II), as measured by mass spectrometry, multiplied by alanine aminotransferase (ALT; II*ALT) has emerged as a strong predictor for NAFLD in adults (ROC 0.94 [0.89-0.99]). However, II*ALT has not been used in predict NAFLD in adolescents with PCOS. To assess the utility of II*ALT measurements in predicting NAFLD in the context of pubertal timing in a high-risk population of adolescents with PCOS and obesity. Participants were screened to confirm PCOS status per 2018 international guidelines. Liver fat fraction was measured with MRI Dixon, and fasting laboratory assessments were performed including traditional insulin (TI) and insulin growth factor-1 (IGF-1), measured with ELISA and ALT, AST. NAFLD was defined as a liver fat ≥5.0%. Mass spectrometry was used to measure intact molecules of II and C-peptide. Seventy-seven adolescent girls with PCOS and obesity who were Tanner 5 and at least 1-year post-menarche were enrolled (age 16.3 ± 1.7 years, BMI 34.9 ± 5.0 kg/m2). There was no difference in the prediction of NAFLD between II and TI (AUROC 0.72 [0.59-0.85] vs. 0.66 [0.53-0.79], p=0.39). Of note, the combination of II*ALT (ROC 0.83 [0.72-0.95], sensitivity 77%, specificity 65%) performed better in predicting NAFLD than II alone (ROC 0.72 [0.59-0.85]), ALT alone (ROC 0.81 [0.71-0.91]), and better than TI*ALT (ROC 0.75 [0.63-0.86]) for the entire cohort (p&amp;lt;0.01 for overall comparison). Patients were divided into 2 groups based on age as a surrogate for pubertal duration (Age &amp;lt;15: n=22, age 13.9 ± 0.8, BMI 32.7 ± 4.9 kg/m2, and Age &amp;gt;15: n=55, age 17.3 ± 0.9, BMI 35.8 ± 4.8 kg/m2). II*ALT had a higher ROC to predict NAFLD in the &amp;gt;15 group (ROC 0.90 [0.81-0.98], sensitivity 97%, specificity 60%) compared to the &amp;lt;15 group (ROC 0.71 [0.41-0.99] sensitivity 81%, specificity 83%), although it did not reach statistical significance. There was no effect of race and ethnicity on these relationships. The II*ALT index performs better than II and ALT alone for the detection of NAFLD and outperforms TI*ALT as well. It is a strong predictor for NAFLD in adolescents &amp;gt;15 years old with PCOS and obesity, with results very similar to those published in adults. However, it is not as robust in adolescents younger than 15 years old, perhaps due to the effect of pubertal hormones altering the relationship between liver fat and insulin concentrations. Presentation Date: Saturday, June 17, 2023

Comparison of Obesity-Related Indicators for Nonalcoholic Fatty Liver Disease Diagnosed by Transient Elastography.

This study aimed to assess obesity-related indices in predicting nonalcoholic fatty liver disease (NAFLD) in the United States. These indices were analyzed separately in previous studies, but evidence comparing them together was still lacking. We analyzed data from 8126 individuals in the National Health and Nutrition Examination Survey (NHANES) database and measured their body mass index (BMI), body roundness index (BRI), a body shape index, conicity index, body adiposity index, abdominal volume index (AVI), and waist-hip ratio. We used logistic analyses with odds ratios to evaluate the association between obesity-related indices and NAFLD and compared their diagnostic ability by receiver operating characteristic (ROC) curves, areas under the curve (AUCs), and net reclassification improvement (NRI). The AVI had the highest AUC (0.835 at controlled attenuation parameter [CAP] scores 263 dB/m and 0.831 at CAP scores 285 dB/m) in the ROC curve analysis. The AVI also showed better discriminatory ability than BMI (NRI = 0.0331 at CAP scores 263 dB/m and 0.0328 at CAP scores 285 dB/m), the same as BRI (NRI = 0.0283 at CAP scores 263 dB/m and 0.0272 at CAP scores 285 dB/m). In males, AVI (AUC = 0.8501 at CAP scores 263 dB/m and 0.8466 at CAP scores 285 dB/m) and BRI (AUC = 0.8517 at CAP scores 263 dB/m and 0.8497 at CAP scores 285 dB/m) had better predictive ability than BMI and similar to females. This was consistent across different age and race groups. AVI and BRI were better predictors of NAFLD than BMI.

Identification and validation of disulfidptosis-associated molecular clusters in non-alcoholic fatty liver disease.

Objective: Non-alcoholic fatty liver disease (NAFLD) is the most prevalent liver disease in the world, and its pathogenesis is not fully understood. Disulfidptosis is the most recently reported form of cell death and may be associated with NAFLD progression. Our study aimed to explore the molecular clusters associated with disulfidptosis in NAFLD and to construct a predictive model. Methods: First, we analyzed the expression profile of the disulfidptosis regulators and immune characteristics in NAFLD. Using 104 NAFLD samples, we investigated molecular clusters based on differentially expressed disulfidptosis-related genes, along with the related immune cell infiltration. Cluster-specific differentially expressed genes were then identified by using the WGCNA method. We also evaluated the performance of four machine learning models before choosing the optimal machine model for diagnosis. Nomogram, calibration curves, decision curve analysis, and external datasets were used to confirm the prediction effectiveness. Finally, the expression levels of the biomarkers were assessed in a mouse model of a high-fat diet. Results: Two differentially expressed DRGs were identified between healthy and NAFLD patients. We revealed the expression profile of DRGs in NAFLD and the correlation with 22 immune cells. In NAFLD, two clusters of molecules connected to disulfidptosis were defined. Significant immunological heterogeneity was shown by immune infiltration analysis among the various clusters. A significant amount of immunological infiltration was seen in Cluster 1. Functional analysis revealed that Cluster 1 differentially expressed genes were strongly linked to energy metabolism and immune control. The highest discriminatory performance was demonstrated by the SVM model, which had a higher area under the curve, relatively small residual and root mean square errors. Nomograms, calibration curves, and decision curve analyses were used to show how accurate the prediction of NAFLD was. Further analysis revealed that the expression of three model-related genes was significantly associated with the level of multiple immune cells. In animal experiments, the expression trends of DDO, FRK and TMEM19 were consistent with the results of bioinformatics analysis. Conclusion: This study systematically elucidated the complex relationship between disulfidptosis and NAFLD and developed a promising predictive model to assess the risk of disease in patients with disulfidptosis subtypes and NAFLD.

Utility of Indices Obtained During Medical Checkups for Predicting Fatty Liver Disease in Non-obese People.

Objective To predict fatty liver disease (FLD), including nonalcoholic FLD (NAFLD) and metabolic dysfunction-associated FLD (MAFLD), from blood tests and anthropometric measurements, the fatty liver index (FLI) and triglyceride glucose-body mass index (TyG-BMI) have been reported as promising indicators. We evaluated the predictive ability of several indices, including the waist circumference, BMI, FLI and TyG-BMI, that might predict FLD in non-obese individuals undergoing health checkups. Methods This retrospective observational study enrolled non-obese subjects who underwent abdominal ultrasonography between May 1, 2015, and June 30, 2021. Obesity was defined as a BMI <25 kg/m2. FLD was diagnosed by abdominal ultrasonography. Using a receiver operating characteristic analysis, we examined the predictive validity of indices for NAFLD and MAFLD by calculating the area under the curve (AUC). Results Of the 24,825 subjects (mean age 44.3±10.0 years old; 54% men) enrolled in this examination of the association of indices, including FLI and TyG-BMI, with NAFLD, NAFLD was diagnosed in 3,619 (27%) men and 733 (6%) women. In both men and women, the FLI and TyG-BMI had significantly higher AUC values for NAFLD prediction than the other indicators (FLI: 0.786 for men and 0.875 for women, TyG-BMI: 0.783 for men and 0.868 for women). In analyses of subjects with a BMI <23 kg/m2, the superiority of the FLI and TyG-BMI remained unchanged. The FLI and TyG-BMI also had significantly higher AUC values for MAFLD prediction than the other indicators. Conclusion The FLI and TyG-BMI had a particularly high predictive ability for NAFLD and MAFLD in non-obese subjects.

SERUM FERRITIN; A STRONG NON-INVASIVE PREDICTOR FOR NAFLD PROGRESSION

Objective: To determine and compare serum ferritin in non-alcoholic fatty liver disease (NAFLD) patients of our ethnicity and to find a predictive value of serum ferritin in designating the progression of the disease. Study Design: Cross-sectional diagnostic study Place and Duration of Study: Shalamar Hospital and Combined Military Hospital Lahore Pakistan, from Mar to Jul 2019. Methodology: On abdominal ultrasonography and raised LFTs, age, gender and BMI matched 129 subjects were classified as cases and controls. After that NAFLD fibrosis score (NFS) was calculated in the cases who had hyper-echoic liver margins and later subjects were divided into 43 healthy controls (group A), 66 subject with steatosis (group B) and 20 subjects with steatohepatitis (group C). Fasting serum ferritin, insulin, glucose levels were measured and HOMA-IR was calculated using {Glucose (mg/dl) × insulin (μlU/ml) / 405} formula. Data was entered and analysed on SPSS version 21. For group compari...... Results: There was a significant difference between the serum ferritin among all the groups. Area under the curve of serum ferritin for group B and group C were 0.603 and 0.885 and serum ferritin levels of ≥40.75 ng/ml with sensitivity of 94% and specificity of 69% were declared to be of the best diagnostic value. While the value of ≥67.55ng/ml of serum ferritin is the best predictor ......... ... Conclusion: Serum ferritin has a good positive predictive value.

262-LB: Fasting Intact Insulin by Liquid Chromatography–Tandem Mass Spectrometry (LC-MS/MS) as a Predictor of Nonalcoholic Fatty Liver Disease in Pediatric Patients

Background: Recent research in adults has shown fasting intact insulin levels measured by mass spectrometry can predict nonalcoholic fatty liver disease (NAFLD) in patients without diabetes; however, there is limited research in children. This study aimed to evaluate fasting intact insulin by LC-MS/MS as a predictive biomarker of NAFLD in adolescents. Methods: This retrospective, cross-sectional study was based on data from four previously conducted studies. Existing clinical laboratory values included fasting intact insulin, alanine aminotransferase (ALT), aspartate aminotransferase (AST), C-peptide, and the insulin resistance (IR) score. Hepatic fat was assessed by magnetic resonance imaging proton density fat fraction (MRI-PDFF) or MR spectroscopy (MRS). NAFLD was defined as intrahepatic fat of ≥5%. Results: A total of 73 children were included in the analysis (64% male; 13.9 ± 2.8 years of age; body mass index (BMI) 29.1 ± 8.5 kg/m2; 56% with NAFLD). Intact fasting insulin, C-peptide, AST, ALT, and IR scores were higher in children with NAFLD compared to non-NAFLD children (P&amp;lt;0.05). Fasting intact insulin measurements predicted NAFLD (area under the receiver operating characteristic curve [AUROC] of 0.83 [95%CI, 0.73-0.93]). When combined with ALT (intact insulin (μU/mL) × ALT (× U/L)), the combined biomarker slightly improved the prediction of NAFLD (AUROC 0.89 [0.81-0.96]), with positive and negative predictive values of 79% and 100%, respectively. Based on maximizing Youden's index, the optimal cutoff points to predict NAFLD were 13.0 μU/mL for intact insulin and 380 μU/mL × U/L for intact insulin × ALT. Conclusion: Our findings support that fasting intact insulin alone, or combined with ALT (intact insulin × ALT), show promise as predictive biomarkers for pediatric NAFLD with high positive and negative predictive values. Additional studies are needed to validate these findings in other pediatric populations. Disclosure H. Huneault: None. D. Ayinde: None. Z. He: None. C. C. Cohen: None. M. J. McPhaul: Employee; Quest Diagnostics. M. B. Vos: Consultant; Boehringer Ingelheim International GmbH, BMS, Intercept Pharmaceuticals, Inc., Novo Nordisk, ProSciento, Eli Lilly and Company. Research Support; Quest Diagnostics, TARGET PharmaSolutions, Inc. Funding National Institutes of Health (R01DK125701); Georgia Clinical Translational Science Alliance (UL1TR002378)

Liver Fat Scores for Noninvasive Diagnosis and Monitoring of Nonalcoholic Fatty Liver Disease in Epidemiological and Clinical Studies.

Nonalcoholic fatty liver disease (NAFLD) is strongly associated with the metabolic syndrome and type 2 diabetes and independently contributes to long-term complications. Being often asymptomatic but reversible, it would require population-wide screening, but direct diagnostics are either too invasive (liver biopsy), costly (MRI) or depending on the examiner's expertise (ultrasonography). Hepatosteatosis is usually accommodated by features of the metabolic syndrome (e.g. obesity, disturbances in triglyceride and glucose metabolism), and signs of hepatocellular damage, all of which are reflected by biomarkers, which poorly predict NAFLD as single item, but provide a cheap diagnostic alternative when integrated into composite liver fat indices. Fatty liver index, NAFLD LFS, and hepatic steatosis index are common and accurate indices for NAFLD prediction, but show limited accuracy for liver fat quantification. Other indices are rarely used. Hepatic fibrosis scores are commonly used in clinical practice, but their mandatory reflection of fibrotic reorganization, hepatic injury or systemic sequelae reduces sensitivity for the diagnosis of simple steatosis. Diet-induced liver fat changes are poorly reflected by liver fat indices, depending on the intervention and its specific impact of weight loss on NAFLD. This limited validity in longitudinal settings stimulates research for new equations. Adipokines, hepatokines, markers of cellular integrity, genetic variants but also simple and inexpensive routine parameters might be potential components. Currently, liver fat indices lack precision for NAFLD prediction or monitoring in individual patients, but in large cohorts they may substitute nonexistent imaging data and serve as a compound biomarker of metabolic syndrome and its cardiometabolic sequelae.

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.

Prediction of MAFLD and NAFLD using different screening indexes: A cross-sectional study in U.S. adults.

Metabolic dysfunction-associated fatty liver disease (MAFLD), formerly known as non-alcoholic fatty liver disease (NAFLD), has become the most common chronic liver disease worldwide. We aimed to explore the gender-related association between nine indexes (BMI/WC/VAI/LAP/WHtR/TyG/TyG-BMI/TyG-WC/TyG-WHtR) and MAFLD/NAFLD and examine their diagnostic utility for these conditions. Eligible participants were screened from the 2017-2018 cycle data of National Health and Nutrition Examination Survey (NHANES). Logistic regression and receiver operating characteristic (ROC) curve were used to assess the predictive performance of 9 indexes for MAFLD/NAFLD. Among the 809 eligible individuals, 478 had MAFLD and 499 had NAFLD. After adjusting for gender, age, ethnicity, FIPR and education level, positive associations with the risk of MAFLD/NAFLD were found for all the nine indexes. For female, TyG-WHtR presented the best performance in identifying MAFLD/NAFLD, with AUC of 0.845 (95% CI = 0.806-0.879) and 0.831 (95% CI = 0.791-0.867) respectively. For male, TyG-WC presented the best performance in identifying MAFLD/NAFLD, with AUC of 0.900 (95% CI = 0.867-0.927) and 0.855 (95% CI = 0.817-0.888) respectively. BMI/WC/VAI/LAP/WHtR/TyG/TyG-BMI/TyG-WC/TyG-WHtR are important indexes to identify the risk of MAFLD and NAFLD.

Prevalence of Non-Alcoholic Fatty Liver Disease in Urban Adult Population in a Tertiary Care Center, Chennai.

Non-alcoholic fatty liver disease (NAFLD) is becoming one of the most common liver diseases among the Indian population. The predisposing factors for NAFLD are diet, lifestyle modifications, and lack of exercise. There is a paucity of research on NAFLD in the South Indian population. Hence, the present study aimed to assess the prevalence of NAFLD among the urban adult population in Chennai. This analytical cross-sectional study was conducted in General Medicine outpatient departments at a tertiary care center in Chennai. The study included 510 non-alcoholic adults (both male and female) aged between 21 and 40 years. Ultrasonography was performed to rule out fatty liver in all participants. All the results obtained were statistically analyzed using SPSS software version 22.0. The frequency was given in percentage. The proportion of participants who screened positive for NAFLD was 61.5%. The participants with higher body mass index (BMI) were found to be significantly 23.09 times higher risk of developing NAFLD. An increase in age was also found to be a predictor of NAFLD. This study also supports that males are more prone to develop NAFLD and are at a 1.59% higher risk of developing the disease than females. Fatty liver has become one of the common non-communicable diseases in India, the high prevalence of NAFLD in the present study supports it. Therefore, people should have regular screening and diagnosis to rule out fatty liver disease. Proper diet patterns and exercise must be followed to prevent fatty liver.

Burden of non-alcoholic fatty liver disease in subclinical hypothyroidism

Abstract Background: The objective of the study was to investigate the burden and predictors of non-alcoholic fatty liver disease (NAFLD) in subclinical hypothyroidism (SCH) patients. Methods: A cross-sectional study was undertaken from January 2017 to December 2017 in 69 patients with SCH, visiting our tertiary care centre. Data collected included the demographic features, physical examination findings, laboratory investigations (free triiodothyronine [T3], free thyroxine (T4), serum thyroid-stimulating hormone (TSH), thyroid peroxidase antibodies, fasting plasma glucose, liver function test, fasting lipid profile and total serum cholesterol) and findings from the abdomen ultrasound and the electrocardiogram. Results: SCH was evident in 60.9% patients with SCH studied. Males showed a significantly high burden of NAFLD than females (52.4% Vs 47.61%; P = 0.005). Aspartate aminotransferase (AST), alanine aminotransferase (ALT), body weight, waist circumference (WC) and waist–hip ratio (WHR) showed a positive association with NAFLD in subclinical hypothyroidism. Conclusions: Our study provides significant evidence of a positive association between subclinical hypothyroidism and NAFLD. AST, ALT, WC and WHR may be considered the predictors of NAFLD in SCH.

The role of platelet-related parameters for the prediction of NAFLD in OSAHS patients

PurposeAs the detection of non-alcoholic fatty liver disease (NAFLD) is imperative for the prevention of its complications, we aimed to explore the predictive value of platelet to lymphocyte count ratio (PLR) and white blood cell count to mean platelet volume ratio (WBC/MPV) in relation to the occurrence of NAFLD among patients with obstructive sleep apnea–hypopnea syndrome (OSAHS).MethodsThis was a cross-sectional study consisting of 351 patients with OSAHS (279 with and 72 without NAFLD). The logistic regression analysis was performed to estimate associations between PLR, WBC/MPV, and NAFLD. Finally, the receiver operating characteristic curve (ROC curve) was used to analyze the efficacy of PLR and WBC/MPV in NAFLD prediction.ResultsCompared to the OSAHS-only group, there was a rising trend in AHI and TS90% in the OSAHS + NAFLD group. And the logistic regression analysis identified average oxygen saturation (MaSO2), WBC/MPV and PLR as predicted factors (odds ratio [OR] = 1.134, P = 0.031; OR = 7.559, P = 0.018, OR = 0.980, P < 0.001, respectively) for NAFLD in OSAHS patients. Moreover, compared with WBC/MPV, PLR, FLI, and APRI, a combination of WBC/MPV and PLR presented the largest AUC for the detection of NAFLD in BMI < 28 kg/m2 (0.753, 95% CI 0.684–0.822), and in age ≥ 60 years subgroup (0.786, 95% CI 0.692–0.880) in ROC analysis. Meanwhile, a combination of WBC/MPV and PLR presented the second largest AUC for the detection of NAFLD in all subjects (0.743, 95% CI 0.708–0.831), as well as in the age < 60 years subgroup (0.729, 95% CI 0.652–0.806), only ranked after FLI, suggesting the combination of WBC/MPV and PLR has a good predictive value for NAFLD in OSAHS patients.ConclusionWe confirmed that the levels of WBC/MPV, PLR, and MaSO2 were closely related to the occurrence of NAFLD among OSAHS patients. Furthermore, our results highlighted the clinical combination of WBC/MPV and PLR levels could act as a simple and effective biomarker for screening NAFLD in patients with OSAHS.

Association between iron metabolism and non-alcoholic fatty liver disease: results from the National Health and Nutrition Examination Survey (NHANES 2017–2018) and a controlled animal study

BackgroundIron metabolism may be involved in the pathogenesis of the non-alcoholic fatty liver disease (NAFLD). The relationship between iron metabolism and NAFLD has not been clearly established. This study aimed to clarify the relationship between biomarkers of iron metabolism and NAFLD.MethodsBased on the National Health and Nutrition Examination Survey (NHANES), restricted cubic spline models and multivariable logistic regression were used to examine the association between iron metabolism [serum iron (SI), serum ferritin (SF), transferrin saturation (TSAT), and soluble transferrin receptor (sTfR)] and the risk for NAFLD. In addition, stratified subgroup analysis was performed for the association between TSAT and NAFLD. Moreover, serum TSAT levels were determined in male mice with NAFLD. The expression of hepcidin and ferroportin, vital regulators of iron metabolism, were analyzed in the livers of mice by quantitative real-time PCR (qRT-PCR) and patients with NAFLD by microarray collected from the GEO data repository.ResultsPatients with NAFLD showed decreased SI, SF, and TSAT levels and increased STfR levels based on the NHANES. After adjusting for confounding factors, TSAT was significantly negatively correlated with NAFLD. Of note, the relationship between TSAT and NAFLD differed in the four subgroups of age, sex, race, and BMI (P for interaction < 0.05). Consistently, mice with NAFLD exhibited decreased serum TSAT levels. Decreased hepcidin and increased ferroportin gene expression were observed in the livers of patients and mice with NAFLD.ConclusionSerum TSAT levels and hepatic hepcidin expression were decreased in both patients and mice with NAFLD. Among multiple biomarkers of iron metabolism, lower TSAT levels were significantly associated with a higher risk of NAFLD in the U.S. general population. These findings might provide new ideas for the prediction, diagnosis, and mechanistic exploration of NAFLD.