Machine learning algorithm outperforms fibrosis markers in predicting significant fibrosis in biopsy-confirmed NAFLD

Non-invasive Scores and Serum Biomarkers for Fatty Liver in the Era of Metabolic Dysfunction-associated Steatotic Liver Disease (MASLD): A Comprehensive Review From NAFLD to MAFLD and MASLD

PURPOSE OF REVIEW

The prevalence of non-alcoholic fatty liver disease (NAFLD) is rapidly increasing worldwide, making it the leading cause of liver related morbidity and mortality. Currently, liver biopsy is the gold standard for assessing individuals with steatohepatitis and fibrosis. However, its invasiveness, sampling variability, and impracticality for large-scale screening has driven the search for non-invasive methods for early diagnosis and staging. In this review, we comprehensively summarise the evidence on the diagnostic performance and limitations of existing non-invasive serum biomarkers and scores in the diagnosis and evaluation of steatosis, steatohepatitis, and fibrosis.

RECENT FINDINGS

Several non-invasive serum biomarkers and scores have been developed over the last decade, although none has successfully been able to replace liver biopsy. The introduction of new NAFLD terminology, namely metabolic dysfunction-associated fatty liver disease (MAFLD) and more recently metabolic dysfunction-associated steatotic liver disease (MASLD), has initiated a debate on the interchangeability of these terminologies. Indeed, there is a need for more research on the variability of the performance of non-invasive serum biomarkers and scores across the diagnostic entities of NAFLD, MAFLD and MASLD. There remains a significant need for finding valid and reliable non-invasive methods for early diagnosis and assessment of steatohepatitis and fibrosis to facilitate prompt risk stratification and management to prevent disease progression and complications. Further exploration of the landscape of MASLD under the newly defined disease subtypes is warranted, with the need for more robust evidence to support the use of commonly used serum scores against the new MASLD criteria and validation of previously developed scores.

Links between gut microbiome, metabolome, clinical variables and non-alcoholic fatty liver disease severity in bariatric patients

BACKGROUND AND AIMS

Bacterial species and microbial pathways along with metabolites and clinical parameters may interact to contribute to non-alcoholic fatty liver disease (NAFLD) and disease severity. We used integrated machine learning models and a cross-validation approach to assess this interaction in bariatric patients.

METHODS

113 patients undergoing bariatric surgery had clinical and biochemical parameters, blood and stool metabolite measurements as well as faecal shotgun metagenome sequencing to profile the intestinal microbiome. Liver histology was classified as normal liver obese (NLO; n = 30), simple steatosis (SS; n = 41) or non-alcoholic steatohepatitis (NASH; n = 42); fibrosis was graded F0 to F4.

RESULTS

We found that those with NASH versus NLO had an increase in potentially harmful E. coli, a reduction of potentially beneficial Alistipes putredinis and an increase in ALT and AST. There was higher serum glucose, faecal 3-(3-hydroxyphenyl)-3-hydroxypropionic acid and faecal cholic acid and lower serum glycerophospholipids. In NAFLD, those with severe fibrosis (F3-F4) versus F0 had lower abundance of anti-inflammatory species (Eubacterium ventriosum, Alistipes finegoldii and Bacteroides dorei) and higher AST, serum glucose, faecal acylcarnitines, serum isoleucine and homocysteine as well as lower serum glycerophospholipids. Pathways involved with amino acid biosynthesis and degradation were significantly more represented in those with NASH compared to NLO, with severe fibrosis having an overall stronger significant association with Superpathway of menaquinol-10 biosynthesis and Peptidoglycan biosynthesis IV.

CONCLUSIONS

In bariatric patients, NASH and severe fibrosis were associated with specific bacterial species, metabolic pathways and metabolites that may contribute to NAFLD pathogenesis and disease severity.

Non-invasive diagnosis of non-alcoholic fatty liver disease: Current status and future perspective

Non-alcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease throughout the world. Hepatocellular carcinoma (HCC) and liver cirrhosis can result from nonalcoholic steatohepatitis (NASH), the severe stage of NAFLD progression. By some estimates, NAFLD affects almost one-third of the world's population, which is completely new and serious public health issue. Unfortunately, NAFLD is diagnosed by exclusion, and the gold standard for identifying NAFLD/NASH and reliably measuring liver fibrosis remains liver biopsy, which is an invasive, costly, time-consuming procedure and involves variable inter-observer diagnosis. With the progress of omics and imaging techniques, numerous non-invasive serological assays have been generated and developed. On the basis of these developments, non-invasive biomarkers and imaging techniques have been combined to increase diagnostic accuracy. This review provides information for the diagnosis and assessment of NAFLD/NASH in clinical practice going forward and may assist the clinician in making an early and accurate diagnosis and in proposing a cost-effective patient surveillance. We discuss newly identified and validated non-invasive diagnostic methods from biopsy-confirmed NAFLD patient studies and their implementation in clinical practice, encompassing NAFLD/NASH diagnosis and differentiation, fibrosis assessment, and disease progression monitoring. A series of tests, including 20-carboxy arachidonic acid (20-COOH AA) and 13,14-dihydro-15-keto prostaglandin D2 (dhk PGD2), were found to be potentially the most accurate non-invasive tests for diagnosing NAFLD. Additionally, the Three-dimensional magnetic resonance imaging (3D-MRE), combination of the FM-fibro index and Liver stiffness measurement (FM-fibro LSM index) and the machine learning algorithm (MLA) tests are more accurate than other tests in assessing liver fibrosis. However, it is essential to use bigger cohort studies to corroborate a number of non-invasive diagnostic tests with extremely elevated diagnostic values.

Application of artificial intelligence techniques for non-alcoholic fatty liver disease diagnosis: A systematic review (2005-2023)

BACKGROUND AND OBJECTIVES

Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data.

METHODS

We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information".

RESULTS

We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches.

CONCLUSION

AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.

Limitations of Noninvasive Tests-Based Population-Level Risk Stratification Strategy for Nonalcoholic Fatty Liver Disease

BACKGROUND

Nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH) are highly prevalent but underdiagnosed.

AIMS

We used an electronic health record data network to test a population-level risk stratification strategy using noninvasive tests (NITs) of liver fibrosis.

METHODS

Data were obtained from PCORnet® sites in the East, Midwest, Southwest, and Southeast United States from patients aged [Formula: see text] 18 with or without ICD-10-CM diagnosis codes for NAFLD, NASH, and NASH-cirrhosis between 9/1/2017 and 8/31/2020. Average and standard deviations (SD) for Fibrosis-4 index (FIB-4), NAFLD fibrosis score (NFS), and Hepatic Steatosis Index (HSI) were estimated by site for each patient cohort. Sample-wide estimates were calculated as weighted averages across study sites.

RESULTS

Of 11,875,959 patients, 0.8% and 0.1% were coded with NAFLD and NASH, respectively. NAFLD diagnosis rates in White, Black, and Hispanic patients were 0.93%, 0.50%, and 1.25%, respectively, and for NASH 0.19%, 0.04%, and 0.16%, respectively. Among undiagnosed patients, insufficient EHR data for estimating NITs ranged from 68% (FIB-4) to 76% (NFS). Predicted prevalence of NAFLD by HSI was 60%, with estimated prevalence of advanced fibrosis of 13% by NFS and 7% by FIB-4. Approximately, 15% and 23% of patients were classified in the intermediate range by FIB-4 and NFS, respectively. Among NAFLD-cirrhosis patients, a third had FIB-4 scores in the low or intermediate range.

CONCLUSIONS

We identified several potential barriers to a population-level NIT-based screening strategy. HSI-based NAFLD screening appears unrealistic. Further research is needed to define merits of NFS- versus FIB-4-based strategies, which may identify different high-risk groups.

Application and impact of Lasso regression in gastroenterology: A systematic review

Least absolute shrinkage and selection operator (Lasso) regression is a statistical technique that can be used to study the effects of clinical variables in outcome prediction. In this study, we aimed at systematically reviewing the application of Lasso regression in gastroenterology for developing predictive models and providing a method of performing Lasso regression. A comprehensive search strategy was conducted in PubMed, Embase and Cochrane CENTRAL databases (Keywords: lasso regression; gastrointestinal tract/diseases) following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were screened for eligibility based on pre-defined selection criteria and the data was extracted using a standardized form. Total 16 studies were included, comprising a diverse range of gastroenterological disease-related outcomes. Sample sizes ranged from 134 to 8861 subjects. Eleven studies reported liver disease-related prediction models, while five focused on non-hepatic etiology models. Lasso regression was applied for variable selection, risk prediction and model development, with various validation methods and performance metrics used. Model performance metrics included Area Under the Receiver Operating Characteristics (AUROC), C-index and calibration plots. In gastroenterology, Lasso regression has been used in various diseases such as inflammatory bowel disease, liver disease and esophageal cancer. It is valuable for complex scenarios with many predictors. However, its effectiveness depends on high-quality and complete data. While it identifies important variables, it doesn't provide causal interpretations. Therefore, cautious interpretation is necessary considering the study design and data quality.

Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study

BACKGROUND AND AIMS

Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD.

APPROACH AND RESULTS

Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82).

CONCLUSIONS

Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

Serological indices and ultrasound variables in predicting the staging of hepatitis B liver fibrosis: A comparative study based on random forest algorithm and traditional methods

Objective

To compare the diagnostic efficacy of serological indices and ultrasound (US) variables in hepatitis B virus (HBV) liver fibrosis staging using random forest algorithm (RFA) and traditional methods.

Methods

The demographic and serological indices and US variables of patients with HBV liver fibrosis were retrospectively collected and divided into serology group, US group, and serology + US group according to the research content. RFA was used for training and validation. The diagnostic efficacy was compared to logistic regression analysis (LRA) and APRI and FIB-4 indices.

Results

For the serology group, the diagnostic performance of RFA was significantly higher than that of APRI and FIB-4 indices. The diagnostic accuracy of RFA in the four classifications (S0S1/S2/S3/S4) of the hepatic fibrosis stage was 79.17%. The diagnostic accuracy for significant fibrosis (≥S2), advanced fibrosis (≥S3), and cirrhosis (S4) was 87.99%, 90.69%, and 92.40%, respectively. The area under the curve (AUC) values were 0.945, 0.959, and 0.951, respectively. For the US group, there was no significant difference in diagnostic performance between RFA and LRA. The diagnostic performance of RFA in the serology + US group was significantly better than that of LRA. The diagnostic accuracy of the four classifications (S0S1/S2/S3/S4) of the hepatic fibrosis stage was 77.21%. The diagnostic accuracy for significant fibrosis (≥S2), advanced fibrosis (≥S3), and cirrhosis (S4) was 87.50%, 90.93%, and 93.38%, respectively. The AUC values were 0.948, 0.959, and 0.962, respectively.

Conclusion

RFA can significantly improve the diagnostic performance of HBV liver fibrosis staging. RFA based on serological indices has a good ability to predict liver fibrosis staging. RFA can help clinicians accurately judge liver fibrosis staging and reduce unnecessary biopsies.

Machine learning algorithms based on proteomic data mining accurately predicting the recurrence of hepatitis B-related hepatocellular carcinoma

BACKGROUND AND AIM

Over 10% of hepatocellular carcinoma (HCC) cases recur each year, even after surgical resection. Currently, there is a lack of knowledge about the causes of recurrence and the effective prevention. Prediction of HCC recurrence requires diagnostic markers endowed with high sensitivity and specificity. This study aims to identify new key proteins for HCC recurrence and to build machine learning algorithms for predicting HCC recurrence.

METHODS

The proteomics data for analysis in this study were obtained from the Clinical Proteomics Tumor Analysis Consortium (CPTAC) database. We analyzed different proteins based on cases with or without recurrence of HCC. Survival analysis, Cox regression analysis, and area under the ROC curves (AUROC > 0.7) were used to screen for more significant differential proteins. Predictive models for HCC recurrence were developed using four machine learning algorithms.

RESULTS

A total of 690 differentially expressed proteins between 50 relapsed and 77 non-relapsed hepatitis B-related HCC patients were identified. Seven of these proteins had an AUROC > 0.7 for 5-year survival in HCC, including BAHCC1, ESF1, RAP1GAP, RUFY1, SCAMP3, STK3, and TMEM230. Among the machine learning algorithms, the random forest algorithm showed the highest AUROC values (AUROC: 0.991, 95% CI 0.962-0.999) for identifying HCC recurrence, followed by the support vector machine (AUROC: 0.893, 95% Cl 0.824-0.956), the logistic regression (AUROC: 0.774, 95% Cl 0.672-0.868), and the multi-layer perceptron algorithm (AUROC: 0.571, 95% Cl 0.459-0.682).

CONCLUSIONS

Our study identifies seven novel proteins for predicting HCC recurrence and the random forest algorithm as the most suitable predictive model for HCC recurrence.

Applications of artificial intelligence (AI) in researches on non-alcoholic fatty liver disease(NAFLD) : A systematic review

Non-alcoholic fatty liver disease (NAFLD) is one of the most important causes of chronic liver disease in the world, it has been found that cardiovascular and renal risks and diseases are also highly prevalent in adults with NAFLD. Diagnosis and treatment of NAFLD face many challenges, although the medical science has been very developed. Efficiency, accuracy and individualization are the main goals to be solved. Evaluation of the severity of NAFLD involves a variety of clinical parameters, how to optimize non-invasive evaluation methods is a necessary issue that needs to be discussed in this field. Artificial intelligence (AI) has become increasingly widespread in healthcare applications, and it has been also brought many new insights into better analyzing chronic liver disease, including NAFLD. This paper reviewed AI related researches in NAFLD field published recently, summarized diagnostic models based on electronic health record and lab test, ultrasound and radio imaging, and liver histopathological data, described the application of therapeutic models in personalized lifestyle guidance and the development of drugs for NAFLD. In addition, we also analyzed present AI models in distinguishing healthy VS NAFLD/NASH, and fibrosis VS non-fibrosis in the evaluation of NAFLD progression. We hope to provide alternative directions for the future research.

Radiomics analysis of contrast-enhanced CT for staging liver fibrosis: an update for image biomarker

BACKGROUND

To establish and validate a radiomics-based model for staging liver fibrosis at contrast-enhanced CT images.

MATERIALS AND METHODS

This retrospective study developed two radiomics-based models (R-score: radiomics signature; R-fibrosis: integrate radiomic and serum variables) in a training cohort of 332 patients (median age, 59 years; interquartile range, 51-67 years; 256 men) with biopsy-proven liver fibrosis who underwent contrast-enhanced CT between January 2017 and December 2020. Radiomic features were extracted from non-contrast, arterial and portal phase CT images and selected using the least absolute shrinkage and selection operator (LASSO) logistic regression to differentiate stage F3-F4 from stage F0-F2. Optimal cutoffs to diagnose significant fibrosis (stage F2-F4), advanced fibrosis (stage F3-F4) and cirrhosis (stage F4) were determined by receiver operating characteristic curve analysis. Diagnostic performance was evaluated by area under the curve, Obuchowski index, calibrations and decision curve analysis. An internal validation was conducted in 111 randomly assigned patients (median age, 58 years; interquartile range, 49-66 years; 89 men).

RESULTS

In the validation cohort, R-score and R-fibrosis (Obuchowski index, 0.843 and 0.846, respectively) significantly outperformed aspartate transaminase-to-platelet ratio (APRI) (Obuchowski index, 0.651; p < .001) and fibrosis-4 index (FIB-4) (Obuchowski index, 0.676; p < .001) for staging liver fibrosis. Using the cutoffs, R-fibrosis and R-score had a sensitivity range of 70-87%, specificity range of 71-97%, and accuracy range of 82-86% in diagnosing significant fibrosis, advanced fibrosis and cirrhosis.

CONCLUSION

Radiomic analysis of contrast-enhanced CT images can reach great diagnostic performance of liver fibrosis.

Malaysian Society of Gastroenterology and Hepatology consensus statement on metabolic dysfunction-associated fatty liver disease

The Malaysian Society of Gastroenterology and Hepatology saw the need for a consensus statement on metabolic dysfunction-associated fatty liver disease (MAFLD). The consensus panel consisted of experts in the field of gastroenterology/hepatology, endocrinology, bariatric surgery, family medicine, and public health. A modified Delphi process was used to prepare the consensus statements. The panel recognized the high and increasing prevalence of the disease and the consequent anticipated increase in liver-related complications and mortality. Cardiovascular disease is the leading cause of mortality in MAFLD patients; therefore, cardiovascular disease risk assessment and management is important. A simple and clear liver assessment and referral pathway was agreed upon, so that patients with more severe MAFLD can be linked to gastroenterology/hepatology care, while patients with less severe MAFLD can remain in primary care or endocrinology, where they are best managed. Lifestyle intervention is the cornerstone in the management of MAFLD. The panel provided a consensus on the use of statin, angiotensin-converting enzyme inhibitor or angiotensin receptor blocker, sodium-glucose cotransporter-2 inhibitor, glucagon-like peptide-1 agonist, pioglitazone, vitamin E, and metformin, as well as recommendations on bariatric surgery, screening for gastroesophageal varices and hepatocellular carcinoma, and liver transplantation in MAFLD patients. Increasing the awareness and knowledge of the various stakeholders on MAFLD and incorporating MAFLD into existing noncommunicable disease-related programs and activities are important steps to tackle the disease. These consensus statements will serve as a guide on MAFLD for clinicians and other stakeholders.

Non-invasive tests of non-alcoholic fatty liver disease

ABSTRACT

For the detection of steatosis, quantitative ultrasound imaging techniques have achieved great progress in past years. Magnetic resonance imaging proton density fat fraction is currently the most accurate test to detect hepatic steatosis. Some blood biomarkers correlate with non-alcoholic steatohepatitis, but the accuracy is modest. Regarding liver fibrosis, liver stiffness measurement by transient elastography (TE) has high accuracy and is widely used across the world. Magnetic resonance elastography is marginally better than TE but is limited by its cost and availability. Several blood biomarkers of fibrosis have been used in clinical trials and hold promise for selecting patients for treatment and monitoring treatment response. This article reviews new developments in the non-invasive assessment of non-alcoholic fatty liver disease (NAFLD). Accumulating evidence suggests that various non-invasive tests can be used to diagnose NAFLD, assess its severity, and predict the prognosis. Further studies are needed to determine the role of the tests as monitoring tools. We cannot overemphasize the importance of context in selecting appropriate tests.

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.