Machine learning classifiers for screening nonalcoholic fatty liver disease in general adults

Mitochondrial mt12361A>G increased risk of metabolic dysfunction-associated steatotic liver disease among non-diabetes

BACKGROUND

Insulin resistance, lipotoxicity, and mitochondrial dysfunction contribute to the pathogenesis of metabolic dysfunction-associated steatotic liver disease (MASLD). Mitochondrial dysfunction impairs oxidative phosphorylation and increases reactive oxygen species production, leading to steatohepatitis and hepatic fibrosis. Artificial intelligence (AI) is a potent tool for disease diagnosis and risk stratification.

AIM

To investigate mitochondrial DNA polymorphisms in susceptibility to MASLD and establish an AI model for MASLD screening.

METHODS

Multiplex polymerase chain reaction was performed to comprehensively genotype 82 mitochondrial DNA variants in the screening dataset (n = 264). The significant mitochondrial single nucleotide polymorphism was validated in an independent cohort (n = 1046) using the Taqman® allelic discrimination assay. Random forest, eXtreme gradient boosting, Naive Bayes, and logistic regression algorithms were employed to construct an AI model for MASLD.

RESULTS

In the screening dataset, only mt12361A>G was significantly associated with MASLD. mt12361A>G showed borderline significance in MASLD patients with 2-3 cardiometabolic traits compared with controls in the validation dataset (P = 0.055). Multivariate regression analysis confirmed that mt12361A>G was an independent risk factor of MASLD [odds ratio (OR) = 2.54, 95% confidence interval (CI): 1.19-5.43, P = 0.016]. The genetic effect of mt12361A>G was significant in the non-diabetic group but not in the diabetic group. mt12361G carriers had a 2.8-fold higher risk than A carriers in the non-diabetic group (OR = 2.80, 95%CI: 1.22-6.41, P = 0.015). By integrating clinical features and mt12361A>G, random forest outperformed other algorithms in detecting MASLD [training area under the receiver operating characteristic curve (AUROC) = 1.000, validation AUROC = 0.876].

CONCLUSION

The mt12361A>G variant increased the severity of MASLD in non-diabetic patients. AI supports the screening and management of MASLD in primary care settings.

Metabolic dysfunction-associated steatotic liver disease: The question of long-term high-normal alanine aminotransferase as a screening test

The growing prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) is being driven by the obesity epidemic. The quest for solutions continues particularly with regard to early detection. This editorial comments on the utility of long-term high-normal alanine aminotransferase (ALT) in screening for MASLD. Chen et al found that new onset MASLD can be detected by repetitively high normal ALT. Implicit in this concept is the question of what should be the accepted upper limit of normal (ULN) for ALT. It was previously set at 40 IU/L based on studies that included people with subclinical liver disease but the new consensus is 30/19 U/L in healthy males/females. Thus, when Chen et al defines the ULN as 40 U/L, others may view it as excessively high. It is important to recognize the variables affecting ULN e.g. instrumentation, diurnal variations, exercise and ageing. These variables matter when the distinctions are subtle e.g. normal vs high-normal. In this regard, the utility of long-term high normal ALT as a disease marker could be enhanced by combining it with other biomarkers, imaging and MASLD genetics to create machine learning classifiers. All in all, Chen et al's work on long-term high normal ALT as a marker of new-onset MASLD deserves merit.

Validation of a screening panel for pediatric metabolic dysfunction-associated steatotic liver disease using metabolomics

BACKGROUND

Metabolic dysfunction-associated steatotic liver disease (MASLD), formerly known as NAFLD, is the most common liver disease in children. Liver biopsy remains the gold standard for diagnosis, although more efficient screening methods are needed. We previously developed a novel NAFLD screening panel in youth using machine learning applied to high-resolution metabolomics and clinical phenotype data. Our objective was to validate this panel in a separate cohort, which consisted of a combined cross-sectional sample of 161 children with stored frozen samples (75% male, 12.8±2.6 years of age, body mass index 31.0±7.0 kg/m2, 81% with MASLD, 58% Hispanic race/ethnicity).

METHODS

Clinical data were collected from all children, and high-resolution metabolomics was performed using their fasting serum samples. MASLD was assessed by MRI-proton density fat fraction or liver biopsy and cardiometabolic factors. Our previously developed panel included waist circumference, triglycerides, whole-body insulin sensitivity index, 3 amino acids, 2 phospholipids, dihydrothymine, and 2 unknowns. To improve feasibility, a simplified version without the unknowns was utilized in the present study. Since the panel was modified, the data were split into training (67%) and test (33%) sets to assess the validity of the panel.

RESULTS

Our present highest-performing modified model, with 4 clinical variables and 8 metabolomics features, achieved an AUROC of 0.92, 95% sensitivity, and 80% specificity for detecting MASLD in the test set.

CONCLUSIONS

Therefore, this panel has promising potential for use as a screening tool for MASLD in youth.

Effects of intermittent fasting regimens on glycemic, hepatic, anthropometric, and clinical markers in patients with non-alcoholic fatty liver disease: Systematic review and meta-analysis of randomized controlled trials

OBJECTIVES

Intermittent fasting (IF) regimens have been hypothesized to influence several markers of cardiometabolic and liver function. The objective of our meta-analysis was to investigate the impact of IF regimens on cardiometabolic and liver markers in subjects diagnosed with non-alcoholic fatty liver disease (NAFLD).

METHODS

We searched several online databases (PubMed/Medline, Web of Science, Scopus and Embase) in order to identify suitable publications for inclusion in the meta-analysis. Results were expressed as weighted mean differences (WMD).

RESULTS

From 12343 articles identified in different databases, a total of 7 RCT arms were entered into the quantitative synthesis. The manuscripts were published between 2019 and 2023. IF regimens (the 5:2 diet, 16/8 time-restricting feeding, and alternate day fasting) varied from 2 months to 3 months. IF regimens reduced steatosis scores (WMD: -33.22 CAP dB/m, 95 % CI: -50.72 to -15.72), anthropometric characteristics of obesity (WMD: -0.77 kg/m2, 95 % CI: -1.38 to -0.17 for body mass index; WMD: -3.16 kg, 95 % CI: -4.71 to -1.61 for body weight; WMD: -1.90 kg, 95 % CI: -3.51 to -0.29 for waist circumference), as well as ALT (WMD: -9.10 U/L, 95 % CI: -12.45 to -5.75), triglyceride (WMD: -20.83 mg/dl, 95 % CI: -39.01 to -2.66), total cholesterol (WMD: -7.80 mg/dl, 95 % CI: -15.18), HbA1c (WMD: -0.14 %, 95 % CI: -0.20 to -0.08) and HOMA-IR (WMD: -1.21, 95 % CI: -2.08 to -0.34) levels versus controls. Nevertheless, no between-group differences were detected for other biomarkers, e.g., fasting blood glucose, insulin, AST, HDL-C or LDL-C values, and fibrosis scores.

CONCLUSION

IF regimens can improve some markers of cardiometabolic and liver function in patients with NAFLD. However, the available evidence to support the benefits of IF regimens is limited and derived from a small number of studies, thus further research is needed to clarify the impact of IF on the cardiometabolic health of NAFLD patients.

Automated machine learning models for nonalcoholic fatty liver disease assessed by controlled attenuation parameter from the NHANES 2017-2020

Background

Nonalcoholic fatty liver disease (NAFLD) is recognized as one of the most common chronic liver diseases worldwide. This study aims to assess the efficacy of automated machine learning (AutoML) in the identification of NAFLD using a population-based cross-sectional database.

Methods

All data, including laboratory examinations, anthropometric measurements, and demographic variables, were obtained from the National Health and Nutrition Examination Survey (NHANES). NAFLD was defined by controlled attenuation parameter (CAP) in liver transient ultrasound elastography. The least absolute shrinkage and selection operator (LASSO) regression analysis was employed for feature selection. Six algorithms were utilized on the H2O-automated machine learning platform: Gradient Boosting Machine (GBM), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), eXtreme Gradient Boosting (XGBoost), and Deep Learning (DL). These algorithms were selected for their diverse strengths, including their ability to handle complex, non-linear relationships, provide high predictive accuracy, and ensure interpretability. The models were evaluated by area under receiver operating characteristic curves (AUC) and interpreted by the calibration curve, the decision curve analysis, variable importance plot, SHapley Additive exPlanation plot, partial dependence plots, and local interpretable model agnostic explanation plot.

Results

A total of 4177 participants (non-NAFLD 3167 vs NAFLD 1010) were included to develop and validate the AutoML models. The model developed by XGBoost performed better than other models in AutoML, achieving an AUC of 0.859, an accuracy of 0.795, a sensitivity of 0.773, and a specificity of 0.802 on the validation set.

Conclusions

We developed an XGBoost model to better evaluate the presence of NAFLD. Based on the XGBoost model, we created an R Shiny web-based application named Shiny NAFLD (http://39.101.122.171:3838/App2/). This application demonstrates the potential of AutoML in clinical research and practice, offering a promising tool for the real-world identification of NAFLD.

Characterization of gut microbiome composition in Iranian patients with nonalcoholic fatty liver disease and nonalcoholic steatohepatitis

Gut microbiota dysbiosis is intimately associated with development of non-alcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH). Nevertheless, the gut microbial community during the course of NAFLD and NASH is yet to be comprehensively profiled. This study evaluated alterations in fecal microbiota composition in Iranian patients with NAFLD and NASH compared with healthy individuals. This cross-sectional study enrolled 15 NAFLD, 15 NASH patients, and 20 healthy controls, and their clinical parameters were examined. The taxonomic composition of the fecal microbiota was determined by sequencing the V3-V4 region of 16S rRNA genes of stool samples. Compared to the healthy controls, NAFLD and NASH patients presented reduced bacterial diversity and richness. We noticed a reduction in the relative abundance of Bacteroidota and a promotion in the relative abundance of Proteobacteria in NAFLD and NASH patients. L-histidine degradation I pathway, pyridoxal 5'-phosphate biosynthesis I pathway, and superpathway of pyridoxal 5'-phosphate biosynthesis and salvage were more abundant in NAFLD patients than in healthy individuals. This study examined fecal microbiota dysbiosis in NAFLD and NASH patients and presented consistent results to European countries. These condition- and ethnicity-specific data could provide different diagnostic signatures and therapeutic targets.

A dynamic machine learning model for prediction of NAFLD in a health checkup population: A longitudinal study

Background

Non-alcoholic fatty liver disease (NAFLD) is one of the most common liver diseases worldwide. Currently, most NAFLD prediction models are diagnostic models based on cross-sectional data, which failed to provide early identification or clarify causal relationships. We aimed to use time-series deep learning models with longitudinal health checkup records to predict the onset of NAFLD in the future, and update the model stepwise by incorporating new checkup records to achieve dynamic prediction.

Methods

10,493 participants with over 6 health checkup records from Beijing MJ Health Screening Center were included to conduct a retrospective cohort study, in which the constantly updated initial 5 checkup data were incorporated stepwise to predict the risk of NAFLD at and after their sixth health checkups. A total of 33 variables were considered, consisting of demographic characteristics, medical history, lifestyle, physical examinations, and laboratory tests. L1-penalized logistic regression (LR) was used for feature selection. The long short-term memory (LSTM) algorithm was introduced for model development, and five-fold cross-validation was conducted to tune and choose optimal hyperparameters. Both internal validation and external validation were conducted, using the 20% randomly divided holdout test dataset and previously unseen data from Shanghai MJ Health Screening Center, respectively, to evaluate model performance. The evaluation metrics included area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, Brier score, and decision curve. Bootstrap sampling was implemented to generate 95% confidence intervals of all the metrics. Finally, the Shapley additive explanations (SHAP) algorithm was applied in the holdout test dataset for model interpretability to obtain time-specific and sample-specific contributions of each feature.

Results

Among the 10,493 participants, 1662 (15.84%) were diagnosed with NAFLD at and after their sixth health checkups. The predictive performance of the deep learning model in the internal validation dataset improved over the incorporation of the checkups, with AUROC increasing from 0.729 (95% CI: 0.698,0.760) at baseline to 0.818 (95% CI: 0.798,0.844) when consecutive 5 checkups were included. The external validation dataset, containing 1728 participants, was used to verify the results, in which AUROC increased from 0.700 (95% CI: 0.657,0.740) with only the first checkups to 0.792 (95% CI: 0.758,0.825) with all five. The results of feature significance showed that body fat percentage, alanine transaminase (ALT), and uric acid owned the greatest impact on the outcome, time-specific, individual-specific and dynamic feature contributions were also produced for model interpretability.

Conclusion

A dynamic prediction model was successfully established in our study, and the prediction capability kept improving with the renewal of the latest checkup records. In addition, we identified key features associated with the onset of NAFLD, making it possible to optimize the prevention and control strategies of the disease in the general population.