External validation and comparison of simple tools to screen for nonalcoholic fatty liver disease in Chinese community population

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

Introduction

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.

Methods

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.

Results

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.

Conclusions

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.

Development and validation of a nomogram for nonalcoholic fatty liver disease in Western Xinjiang, China

OBJECTIVE

The aim of this study was to establish a simple, nonalcoholic fatty liver disease (NAFLD) screening model using readily available variables to identify high-risk individuals in Western Xinjiang, China.

METHODS

A total of 40 033 patients from the National Health Examination were divided into a training group (70%) and a validation group (30%). Univariate regression and least absolute shrinkage and selection operator models optimized feature selection, while a multivariate logistic regression analysis constructed the prediction model. The model's performance was evaluated using the area under the receiver operating characteristic curve, and its clinical utility was assessed through decision curve analysis.

RESULTS

The nomogram assessed NAFLD risk based on factors such as sex, age, diastolic blood pressure, waist circumference, BMI, fasting plasma glucose, alanine aminotransferase, platelet count, total cholesterol, triglycerides, low-density lipoprotein-cholesterol, and high-density lipoprotein-cholesterol. The area under the receiver operating characteristic curves were 0.829 for men and 0.859 for women in the development group, and 0.817 for men and 0.865 for women in the validation group. The decision curve analysis confirmed the nomogram's clinical usefulness, with consistent findings in the validation set.

CONCLUSION

A user-friendly nomogram prediction model for NAFLD risk was successfully developed and validated for Western Xinjiang, China.

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.

Non-alcoholic fatty liver disease and socioeconomic determinants in an Iranian cohort study

BACKGROUND

Non-alcoholic fatty liver disease (NAFLD) is widespread worldwide. On the other hand, social inequality and socioeconomic status (SES) can affect all aspects of health. Therefore, this study aimed to investigate the relationship between SES indicators and NAFLD.

METHODS

This was a cross-sectional study using data from the registration phase of the Hoveyzeh Cohort Study, which included 10,009 individuals aged 35-70 years from May 2016 to August 2018. Fatty liver disease was determined based on Fatty Liver Index (FLI). The crude and adjusted odds ratios were calculated by logistic regression analysis to estimate associations between the fatty liver index and SES after controlling the potential confounders.

RESULTS

According to the FLI index, there were 2,006 people with fatty liver (28%) and 5,246 people without fatty liver (72%). Several 4496 people (62%) were women. The chi-square test showed significant relationships between the educational level and skill level (P < 0.001), the wealth index (P < 0.001), and Townsend Index (P < 0.001) with fatty liver index. In multivariable analysis, after adjustment for age, sex, physical activity, smoking, type of residence, calorie intake, dyslipidemia, skill level, and diabetes, the wealth index (p < 0.001) was positively associated with the fatty liver index. Besides, a reverse and significant association was seen between the Townsend index and the fatty liver index(p < 0.001). In contrast, no significant associations were seen between gender and educational level with the fatty liver index.

CONCLUSIONS

A more vulnerable SES is associated with NAFLD. Fatty liver index and socioeconomic indicators can be powerful monitoring tools to monitor health differences in diagnosing NAFLD.

Comparison of the diagnostic performance of twelve noninvasive scores of metabolic dysfunction-associated fatty liver disease

BACKGROUND

The absence of distinct symptoms in the majority of individuals with metabolic dysfunction-associated fatty liver disease (MAFLD) poses challenges in identifying those at high risk, so we need simple, efficient and cost-effective noninvasive scores to aid healthcare professionals in patient identification. While most noninvasive scores were developed for the diagnosis of nonalcoholic fatty liver disease (NAFLD), consequently, the objective of this study was to systematically assess the diagnostic ability of 12 noninvasive scores (METS-IR/TyG/TyG-WC/TyG-BMI/TyG-WtHR/VAI/HSI/FLI/ZJU/FSI/K-NAFLD) for MAFLD.

METHODS

The study recruited eligible participants from two sources: the National Health and Nutrition Examination Survey (NHANES) 2017-2020.3 cycle and the database of the West China Hospital Health Management Center. The performance of the model was assessed using various metrics, including area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and subgroup analysis.

RESULTS

A total of 7398 participants from the NHANES cohort and 4880 patients from the Western China cohort were included. TyG-WC had the best predictive power for MAFLD risk in the NHANES cohort (AUC 0.863, 95% CI 0.855-0.871), while TyG-BMI had the best predictive ability in the Western China cohort (AUC 0.903, 95% CI 0.895-0.911), outperforming other models, and in terms of IDI, NRI, DCA, and subgroup analysis combined, TyG-WC remained superior in the NAHANES cohort and TyG-BMI in the Western China cohort.

CONCLUSIONS

TyG-BMI demonstrated satisfactory diagnostic efficacy in identifying individuals at a heightened risk of MAFLD in Western China. Conversely, TyG-WC exhibited the best diagnostic performance for MAFLD risk recognition in the United States population. These findings suggest the necessity of selecting the most suitable predictive models based on regional and ethnic variations.

Validation of nonalcoholic fatty liver disease (NAFLD) related steatosis indices in metabolic associated fatty liver disease (MAFLD) and comparison of the diagnostic accuracy between NAFLD and MAFLD

BACKGROUND

Metabolic-associated fatty liver disease (MAFLD) is a new term of nonalcoholic fatty liver disease (NAFLD), with newly proposed diagnostic criteria. The applicability of common noninvasive testing for screening NAFLD is unclear for the detection of MAFLD and requires reevaluation. We aimed to validate the effectiveness of traditional NAFLD-related steatosis indices for diagnosing MAFLD and to determine the optimal cutoff values as well as compare their accuracy between NAFLD and MAFLD diagnosis.

METHODS

This study enrolled 1866 participants from the National Health and Nutrition Examination Survey (NHANES) database (2017-2018). The diagnostic performances of fatty liver index (FLI), Framingham Steatosis Index (FSI), Zhejiang University index (ZJU), lipid accumulation product (LAP), hepatitis steatosis index (HSI) and visceral adiposity index (VAI) were evaluated using the area under the receiver operator characteristic (AUROC) curve and the optimal cutoff points were calculated according to maximum Youden's index.

RESULTS

FLI had the highest AUROC (0.840) for predicting MAFLD in the whole population, with a cutoff value of 56.93. The AUROCs of FLI, FSI, ZJU, LAP, HSI and VAI for predicting MAFLD/NAFLD were 0.840/0.812, 0.833/0.811, 0.826/0.811, 0.826/0.799, 0.814/0.803 and 0.747/0.729, respectively. The AUROC values of all indices decreased in the subgroup of the population with overweight or diabetes.

CONCLUSION

The NAFLD-related scores would be equally useful to screen MAFLD and seemed to be more compatible with MAFLD. The FLI was optimal in both MAFLD and NAFLD diagnoses. However, a new predictive indicator suitable for various characteristics of the population is worth further development in the future.

Assessing the clinical utility of major indices for nonalcoholic fatty liver disease in East Asian populations

Nonalcoholic fatty liver disease (NAFLD) is currently the most common form of chronic liver disease. The growing prevalence of NAFLD is strongly associated with the high incidence of metabolic syndrome. NAFLD affects as much as 19% of the US population with a disproportionate impact on minority racial groups such as Asian Americans. If not promptly managed, NAFLD may progress to more feared complications. Liver indices for NAFLD screening have been proposed but were often developed using study populations with different anthropometrics than patients of East Asian descent. This review compares the accuracy of five indices for NAFLD screening in Asian cohorts. The Fatty Liver Index performed well in multiple large-scale community studies, although other indices may be more suited for specific patient cohorts. This is important, as the utilization of liver indices could accelerate screening for NAFLD for early management and to reduce liver disease-related health disparities among Asian Americans.

Lipid accumulation product (LAP) index for the diagnosis of nonalcoholic fatty liver disease (NAFLD): a systematic review and meta-analysis

BACKGROUND

Lipid accumulation product (LAP) is an index calculated by waist circumference (WC) and triglyceride (TG), which reflects lipid toxicity. This study aims to investigate the association between the LAP index and nonalcoholic fatty liver disease (NAFLD) in a systematic review and meta-analysis.

METHODS AND RESULTS

PubMed, Scopus, and Web of Science online databases were searched for eligible studies that investigated the association of the LAP index and NAFLD. Sixteen observational studies with 96,101 participants, including four cohort studies, one case‒control study and 11 cross-sectional studies with baseline data, were entered into this analysis. Fourteen studies reported a significant association between the LAP index and NAFLD, and two reported that this relation was not significant; two different meta-analyses (1- mean difference (MD) and 2- bivariate diagnostic test accuracy [DTA]) were conducted using Stata version 14. The LAP index was compared in subjects with and without NAFLD, and the difference was significant with 34.90 units (CI 95: 30.59-39.31, P < 0.001) of the LAP index. The DTA meta-analysis was conducted and showed that the LAP index pooled sensitivity and specificity for screening of NAFLD were 94% (CI95: 72%-99%, I2 = 99%, P < 0.001) and 85% (CI95: 62%-96%, I2 = 99%, P < 0.001), respectively.

CONCLUSION

The LAP Index is an inexpensive, sensitive, and specific method to evaluate NAFLD and may be valuable for NAFLD screening.

Comparison of the Diagnostic Performance of Steatosis Indices for Discrimination of CT-Diagnosed Metabolic Dysfunction-Associated Fatty Liver Disease

Non-alcoholic fatty liver disease (NAFLD) was redefined as metabolic dysfunction-associated fatty liver disease (MAFLD) in 2020. Due to this, further validation of the non-invasive tests used in NAFLD diagnosis is required for MAFLD. There are five known steatosis indices for computed tomography (CT)-diagnosed MAFLD. These indices include the fatty liver index (FLI), the hepatic steatosis index (HSI), the lipid accumulation product (LAP), the visceral adiposity index (VAI), and the Zhejiang University index (ZJU). We aimed to analyze the diagnostic abilities of these five widely known steatosis indices for CT-diagnosed MAFLD. From March 2012 to October 2019, we retrospectively analyzed the clinical information and images of 1300 adults aged ≥19 years who underwent CT scans at our institution. To compare differences, the Chi-square test and independent t-test were used for categorical and continuous variables, respectively. The area under the receiver operating characteristic (AUROC) curve was used to validate the diagnostic accuracy of MAFLD. Of the five indices, FLI was the best at predicting MAFLD, with the highest AUROC (0.791). The sensitivity and specificity of FLI for diagnosing MAFLD were both 70.9%. The optimal cut-off value was 29.9. FLI is a useful surrogate index for screening MAFLD in clinical practice.