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.

Noninvasive assessment of liver disease severity in patients with nonalcoholic fatty liver disease (NAFLD) and type 2 diabetes.

BACKGROUND AND AIMS: We evaluated the diagnostic accuracy of simple, noninvasive tests (NITs) in NAFLD patients with type 2 diabetes (T2D). METHODS AND RESULTS: This was an individual patient data meta-analysis of 1780 patients with biopsy-proven NAFLD and T2D. The index tests of interest were FIB-4, NAFLD Fibrosis Score (NFS), aspartate aminotransferase-to-platelet ratio index, liver stiffness measurement (LSM) by vibration-controlled transient elastography, and AGILE 3+. The target conditions were advanced fibrosis, NASH, and fibrotic NASH(NASH plus F2-F4 fibrosis). The diagnostic performance of noninvasive tests. individually or in sequential combination, was assessed by area under the receiver operating characteristic curve and by decision curve analysis. Comparison with 2278 NAFLD patients without T2D was also made. In NAFLD with T2D LSM and AGILE 3+ outperformed, both NFS and FIB-4 for advanced fibrosis (area under the receiver operating characteristic curve:LSM 0.82, AGILE 3+ 0.82, NFS 0.72, FIB-4 0.75, aspartate aminotransferase-to-platelet ratio index 0.68; p < 0.001 of LSM-based versus simple serum tests), with an uncertainty area of 12%-20%. The combination of serum-based with LSM-based tests for advanced fibrosis led to a reduction of 40%-60% in necessary LSM tests. Decision curve analysis showed that all scores had a modest net benefit for ruling out advanced fibrosis at the risk threshold of 5%-10% of missing advanced fibrosis. LSM and AGILE 3+ outperformed both NFS and FIB-4 for fibrotic NASH (area under the receiver operating characteristic curve:LSM 0.79, AGILE 3+ 0.77, NFS 0.71, FIB-4 0.71; p < 0.001 of LSM-based versus simple serum tests). All noninvasive scores were suboptimal for diagnosing NASH. CONCLUSIONS: LSM and AGILE 3+ individually or in low availability settings in sequential combination after FIB-4 or NFS have a similar good diagnostic accuracy for advanced fibrosis and an acceptable diagnostic accuracy for fibrotic NASH in NAFLD patients with T2D.

Health-related Quality of Life in Patients With Nonalcoholic Fatty Liver Disease: A Prospective Multi-center UK Study.

BACKGROUND & AIMS: It is unclear whether health-related quality of life (HRQoL) is impaired in patients with nonalcoholic fatty liver disease (NAFLD) without advanced fibrosis and how this compares with the general population. We aimed to assess HRQoL in patients with NAFLD in comparison to the general population and any associations of fibrosis severity and metabolic comorbidities with impairments in HRQoL. METHODS: We prospectively enrolled 513 consecutive patients with NAFLD who completed the EuroQol 5-dimensional questionnaire (EQ-5D) and Chronic Liver Disease Questionnaires (CLDQ). Demographic and clinical information, liver biopsy results, and/or liver stiffness (LS) by transient elastography were recorded. A general population sub-cohort of the Health Survey for England 2018 was used as a comparator (n = 5483), and a 1:1 propensity-score (PS) matching was performed, according to age, sex, body mass index, and type 2 diabetes mellitus (T2DM). RESULTS: EQ-5D-5L utility was significantly lower in 466 PS-matched patients with NAFLD compared with PS-matched controls (0.77 ± 0.27 vs 0.84 ± 0.19; P < .001), even in those without advanced fibrosis (F ≤2 or LS <8kPa) (0.80 ± 0.24 vs 0.84 ± 0.19; P = .024). HRQoL measures (EQ-5D-5L, EQ-VAS, CLDQ) did not differ between patients with NAFLD with and without advanced fibrosis. LS was independently associated with lower EQ-5D-5L in all patients with NAFLD but not in those without advanced fibrosis. In the latter, lower EQ-5D-5L was associated with female sex, T2DM, and depression. CONCLUSIONS: Patients with NAFLD, even those without advanced fibrosis, have worse HRQoL compared with the general population. In patients with NAFLD without advanced fibrosis, HRQoL is independently associated with non-liver comorbidities but not LS. Multi-disciplinary management is therefore required in NAFLD, irrespective of fibrosis severity.

Diagnostic accuracy of non-invasive tests for advanced fibrosis in patients with NAFLD: an individual patient data meta-analysis.

OBJECTIVE: Liver biopsy is still needed for fibrosis staging in many patients with non-alcoholic fatty liver disease. The aims of this study were to evaluate the individual diagnostic performance of liver stiffness measurement by vibration controlled transient elastography (LSM-VCTE), Fibrosis-4 Index (FIB-4) and NAFLD (non-alcoholic fatty liver disease) Fibrosis Score (NFS) and to derive diagnostic strategies that could reduce the need for liver biopsies. DESIGN: Individual patient data meta-analysis of studies evaluating LSM-VCTE against liver histology was conducted. FIB-4 and NFS were computed where possible. Sensitivity, specificity and area under the receiver operating curve (AUROC) were calculated. Biomarkers were assessed individually and in sequential combinations. RESULTS: Data were included from 37 primary studies (n=5735; 45% women; median age: 54 years; median body mass index: 30 kg/m2; 33% had type 2 diabetes; 30% had advanced fibrosis). AUROCs of individual LSM-VCTE, FIB-4 and NFS for advanced fibrosis were 0.85, 0.76 and 0.73. Sequential combination of FIB-4 cut-offs (<1.3; ≥2.67) followed by LSM-VCTE cut-offs (<8.0; ≥10.0 kPa) to rule-in or rule-out advanced fibrosis had sensitivity and specificity (95% CI) of 66% (63-68) and 86% (84-87) with 33% needing a biopsy to establish a final diagnosis. FIB-4 cut-offs (<1.3; ≥3.48) followed by LSM cut-offs (<8.0; ≥20.0 kPa) to rule out advanced fibrosis or rule in cirrhosis had a sensitivity of 38% (37-39) and specificity of 90% (89-91) with 19% needing biopsy. CONCLUSION: Sequential combinations of markers with a lower cut-off to rule-out advanced fibrosis and a higher cut-off to rule-in cirrhosis can reduce the need for liver biopsies.

Association of Weight Changes With Changes in Histological Features and Blood Markers in Nonalcoholic Steatohepatitis.

BACKGROUND AND AIMS: Weight loss is recommended for patients with non-alcoholic steatohepatitis (NASH) but the impact of weight change on disease activity remains unclear. We examined the association between weight change (gain/loss) and changes in biochemical and histological features of NASH. METHODS: This was an analysis of the PIVENS and FLINT trials in adults with NASH who had liver biopsies at baseline and at either 1.5 years or 2 years. Multivariable regression models examined how weight change was associated with changes in (a) blood liver markers, (b) NASH resolution with no fibrosis worsening, (c) fibrosis improving with no NASH worsening, and (d) individual histological features. RESULTS: The BMI of the 421 participants was 34.3 kg/m2 (SD:6.5) and their mean weight change was +0.5 kg (SD:6.5). Weight change was independently and positively associated with changes in liver enzymes and the Fibrosis-4 score (all P < .001). Each kg of weight loss was associated with 7% (95% CI, 3%-10%; P < .001) increase in odds of achieving NASH resolution with no fibrosis worsening and with 5% (95% CI, 1%-8%; P = .01) increase in odds of achieving fibrosis improvement with no NASH worsening. Weight gain was associated with worsening of disease activity. For every kg of weight lost, the odds of fibrosis improving were 5% (95% CI, 2%-8%; P = .001). There was no evidence that the association between weight change and outcome depended upon pharmacological treatment, trial, body mass index, and baseline fibrosis. CONCLUSIONS: Weight change was independently and monotonically associated with changes in biochemical and histological features of NASH. Guidelines for NASH management should incorporate recommendations for both avoidance of weight gain and support to lose weight.

Accuracy of FibroScan Controlled Attenuation Parameter and Liver Stiffness Measurement in Assessing Steatosis and Fibrosis in Patients With Nonalcoholic Fatty Liver Disease.

BACKGROUND & AIMS: We estimated the accuracy of FibroScan vibration-controlled transient elastography controlled attenuation parameter (CAP) and liver stiffness measurement (LSMs) in assessing steatosis and fibrosis in patients with suspected nonalcoholic liver disease (NAFLD). METHODS: We collected data from 450 consecutive adults who underwent liver biopsy analysis for suspected NAFLD at 7 centers in the United Kingdom from March 2014 through January 2017. FibroScan examinations with M or XL probe were completed within the 2 weeks of the biopsy analysis (404 had a valid examination). The biopsies were scored by 2 blinded expert pathologists according to nonalcoholic steatohepatitis clinical research network criteria. Diagnostic accuracy was estimated using the area under the receiver operating characteristic curves (AUROCs) for the categories of steatosis and fibrosis. We assessed effects of disease prevalence on positive and negative predictive values. For LSM, the effects of histological parameters and probe type were appraised using multivariable analysis. RESULTS: Using biopsy analysis as the reference standard, we found that CAP identified patients with steatosis with an AUROC of 0.87 (95% confidence interval [CI] 0.82-0.92) for S≥S1, 0.77 (95% CI 0.71-0.82) for S≥S2, and 0.70 (95% CI 0.64-0.75) for S=S3. Youden cutoff values for S≥S1, S≥S2, and S≥S3 were 302 dB/m, 331 dB/m, and 337 dB/m, respectively. LSM identified patients with fibrosis with AUROCs of 0.77 (95% CI 0.72-0.82) for F≥F2, 0.80 (95% CI 0.75-0.84) for F≥F3, and 0.89 (95% CI 0.84-0.93) for F=F4. Youden cutoff values for F≥F2, F≥F3, and F=F4 were 8.2 kPa, 9.7 kPa, and 13.6 kPa, respectively. Applying the optimal cutoff values, determined from this cohort, to populations of lower fibrosis prevalence increased negative predictive values and reduced positive predictive values. Multivariable analysis found that the only parameter that significantly affected LSMs was fibrosis stage (P<10-16); we found no association with steatosis or probe type. CONCLUSIONS: In a prospective analysis of patients with NAFLD, we found CAP and LSM by FibroScan to assess liver steatosis and fibrosis, respectively, with AUROC values ranging from 0.70 to 0.89. Probe type and steatosis did not affect LSM. STUDY REGISTRATION: ClinicalTrials.gov Identifier: NCT01985009.

Prognostic value of multiparametric magnetic resonance imaging, transient elastography and blood-based fibrosis markers in patients with chronic liver disease.

BACKGROUND & AIMS: Liver cT1 , liver T1 , transient elastography (TE) and blood-based biomarkers have independently been shown to predict clinical outcomes but have not been directly compared in a single cohort of patients. Our aim was to compare these tests' prognostic value in a cohort of patients with compensated chronic liver disease. METHODS: Patients with unselected compensated liver disease aetiologies had baseline assessments and were followed up for development of clinical outcomes, blinded to the imaging results. The prognostic value of non-invasive liver tests at prespecified thresholds was assessed for a combined clinical endpoint comprising ascites, variceal bleeding, hepatic encephalopathy, hepatocellular carcinoma, liver transplantation and mortality. RESULTS: One hundred and ninety-seven patients (61% male) with median age of 54 years were followed up for 693 patient-years (median (IQR) 43 (26-58) months). The main diagnoses were NAFLD (41%), viral hepatitis (VH, 25%) and alcohol-related liver disease (ArLD; 14%). During follow-up 14 new clinical events, and 11 deaths occurred. Clinical outcomes were predicted by liver cT1  > 825ms with HR 9.9 (95% CI: 1.29-76.4, P = .007), TE > 8kPa with HR 7.8 (95% CI: 0.97-62.3, P = .02) and FIB-4 > 1.45 with HR 4.09 (95% CI: 0.90-18.4, P = .05). In analysis taking into account technical failure and unreliability, liver cT1  > 825 ms could predict clinical outcomes (P = .03), but TE > 8kPa could not (P = .4). CONCLUSIONS: We provide further evidence that liver cT1 , TE and serum-based biomarkers can predict clinical outcomes, but when taking into account technical failure/unreliability, TE cut-offs perform worse than those of cT1 and blood biomarkers.

Liver biochemical abnormalities in Turner syndrome: A comprehensive characterization of an adult population.

OBJECTIVE: Abnormal liver function tests (LFTs) are frequent in Turner syndrome (TS). The causes and clinical significance are unclear. AIMS: To investigate the prevalence of elevated LFTs in adult TS; secondly, to analyse the associations between elevated LFTs, TS-karyotypes and TS-related conditions; and thirdly, to evaluate liver stiffness and histological assessment. METHODS: A total of 125 TS women were retrospectively studied. Karyotypes, clinical and biochemical details and aortic measurements were recorded. Fibroscan and liver biopsy results were noted. RESULTS: Elevated LFTs were found in 49.6%: gamma-glutamyltransferase (GGT) in 88.7%, ALK in 45.2%, ALT in 40.3% and AST in 29%. A FIB-4 index >1.3 was found in 11.8%. Women with isochromosome of the X long arm, iso[X](q), had a higher prevalence of elevated LFTs. A lower prevalence of abnormal GGT was found in patients with 45,X/46,XX, 45,X/47,XXX or 45,X/46,XX/47,XXX. Subjects with raised GGT were older, shorter and more likely to have higher triglyceride levels. There was no association with HRT duration after adjusting for age. Among patients with elevated aminotransferases, no differences were noted, except for higher HDL-cholesterol levels. The sinuses and ascending aorta diameter were greater in the elevated LFTs group. Fibroscan was suggestive of significant liver fibrosis in 38.1%. Among 11 biopsies, liver architectural changes were reported in 45.4%, including two with cirrhosis. CONCLUSIONS: Elevated LFTs in TS are common and important to detect given the possible progression towards severe liver disease. An association between raised LFTs and karyotype iso[X]q was demonstrated. We have also shown a new association between abnormal LFTs and aortic dilatation.

Hepatic iron is the major determinant of serum ferritin in NAFLD patients.

BACKGROUND AND AIMS: Elevated serum ferritin is common in NAFLD, and is associated with more advanced disease and increased mortality. Hyperferritinaemia in NAFLD is often attributed to inflammation, while in other conditions ferritin closely reflects body iron stores. The aim of this study was to clarify the underlying cause of hyperferritinaemia in NAFLD. METHODS: Ferritin levels were examined with markers of iron status, inflammation and liver injury across the clinical spectrum of NAFLD using blood, tissue and magnetic resonance (MR) imaging. A separate larger group of NAFLD patients with hepatic iron staining and quantification were used for validation. RESULTS: Serum ferritin correlated closely with the iron regulatory hormone hepcidin, and liver iron levels determined by MR. Furthermore, ferritin levels reflected lower serum adiponectin, a marker of insulin resistance, and liver fat, but not cytokine or CRP levels. Ferritin levels differed according to fibrosis stage, increasing from early to moderate disease, and declining in cirrhosis. A similar pattern was found in the validation cohort of NAFLD patients, where ferritin levels were highest in those with macrophage iron deposition. Multivariate analysis revealed liver iron and hepcidin levels as the major determinants of serum ferritin. CONCLUSIONS: While hyperferritinaemia is associated with markers of liver injury and insulin resistance, serum hepcidin and hepatic iron are the strongest predictors of ferritin levels. These findings highlight the role of disordered iron homeostasis in the pathogenesis of NAFLD, suggesting that therapies aimed at correcting iron metabolism may be beneficial.

Rifaximin in non-alcoholic steatohepatitis: An open-label pilot study.

AIM: Gut microbial dysbiosis is implicated in the pathogenesis of non-alcoholic steatohepatitis (NASH). We investigated downstream effects of gut microbiota modulation on markers of hepatic inflammation, steatosis, and hepatic and peripheral insulin sensitivity in patients with NASH using rifaximin therapy. METHODS: Patients with biopsy-proven NASH and elevated aminotransferase values were included in this open-label pilot study, all receiving 6 weeks rifaximin 400 mg twice daily, followed by a 6-week observation period. The primary endpoint was change in alanine aminotransferase (ALT) after 6 weeks of rifaximin. Secondary endpoints were change in hepatic lipid content and insulin sensitivity measured with a hyperinsulinemic-euglycemic clamp. RESULTS: Fifteen patients (13 men and 2 women) with a median (range) age of 46 (32-63) years were included. Seven had diabetes on oral hypoglycemic medications and 8 had no diabetes. After 6 weeks of therapy, no differences were seen in ALT (55 [33-191] vs. 63 [41-218] IU/L, P = 0.41), peripheral glucose uptake (28.9 [19.4-48.3] to 25.5 [17.7-47.9] µmol/kg/min, P = 0.30), hepatic insulin sensitivity (35.2 [15.3-51.7]% vs. 30.0 [10.8-50.5]%, P = 0.47), or hepatic lipid content (21.6 [2.2-46.2]% vs. 24.8 [1.7-59.3]%, P = 0.59) before and after rifaximin treatment. After 12 weeks from baseline, serum ALT increased to 83 (30-217) IU/L, P = 0.02. There was a significant increase in the homeostasis model assessment-estimated insulin resistance index (P = 0.05). The urinary metabolic profile indicated a significant reduction in urinary hippurate with treatment, which reverted to baseline after cessation of rifaximin, although there was no consistent difference in relative abundance of fecal microbiota with treatment. CONCLUSION: These data do not indicate a beneficial effect of rifaximin in patients with NASH.

Phosphodiester content measured in human liver by in vivo 31 P MR spectroscopy at 7 tesla.

PURPOSE: Phosphorus (31 P) metabolites are emerging liver disease biomarkers. Of particular interest are phosphomonoester and phosphodiester (PDE) "peaks" that comprise multiple overlapping resonances in 31 P spectra. This study investigates the effect of improved spectral resolution at 7 Tesla (T) on quantifying hepatic metabolites in cirrhosis. METHODS: Five volunteers were scanned to determine metabolite T1 s. Ten volunteers and 11 patients with liver cirrhosis were scanned at 7T. Liver spectra were acquired in 28 min using a 16-channel 31 P array and 3D chemical shift imaging. Concentrations were calculated using γ-adenosine-triphosphate (γ-ATP) = 2.65 mmol/L wet tissue. RESULTS: T1 means ± standard deviations: phosphatidylcholine 1.05 ± 0.28 s, nicotinamide-adenine-dinucleotide (NAD+ ) 2.0 ± 1.0 s, uridine-diphosphoglucose (UDPG) 3.3 ± 1.4 s. Concentrations in healthy volunteers: α-ATP 2.74 ± 0.11 mmol/L wet tissue, inorganic phosphate 2.23 ± 0.20 mmol/L wet tissue, glycerophosphocholine 2.34 ± 0.46 mmol/L wet tissue, glycerophosphoethanolamine 1.50 ± 0.28 mmol/L wet tissue, phosphocholine 1.06 ± 0.16 mmol/L wet tissue, phosphoethanolamine 0.77 ± 0.14 mmol/L wet tissue, NAD+ 2.37 ± 0.14 mmol/L wet tissue, UDPG 2.00 ± 0.22 mmol/L wet tissue, phosphatidylcholine 1.38 ±â€Š0.31 mmol/L wet tissue. Inorganic phosphate and phosphatidylcholine concentrations were significantly lower in patients; glycerophosphoethanolamine concentrations were significantly higher (P < 0.05). CONCLUSION: We report human in vivo hepatic T1 s for phosphatidylcholine, NAD+ , and UDPG for the first time at 7T. Our protocol allows high signal-to-noise, repeatable measurement of metabolite concentrations in human liver. The splitting of PDE into its constituent peaks at 7T may allow more insight into changes in metabolism. Magn Reson Med 78:2095-2105, 2017. © 2017 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Multiparametric magnetic resonance imaging for the assessment of non-alcoholic fatty liver disease severity.

BACKGROUND & AIMS: The diagnosis of non-alcoholic steatohepatitis and fibrosis staging are central to non-alcoholic fatty liver disease assessment. We evaluated multiparametric magnetic resonance in the assessment of non-alcoholic steatohepatitis and fibrosis using histology as standard in non-alcoholic fatty liver disease. METHODS: Seventy-one patients with suspected non-alcoholic fatty liver disease were recruited within 1 month of liver biopsy. Magnetic resonance data were used to define the liver inflammation and fibrosis score (LIF 0-4). Biopsies were assessed for steatosis, lobular inflammation, ballooning and fibrosis and classified as non-alcoholic steatohepatitis or simple steatosis, and mild or significant (Activity ≥2 and/or Fibrosis ≥2 as defined by the Fatty Liver Inhibition of Progression consortium) non-alcoholic fatty liver disease. Transient elastography was also performed. RESULTS: Magnetic resonance success rate was 95% vs 59% for transient elastography (P<.0001). Fibrosis stage on biopsy correlated with liver inflammation and fibrosis (rs =.51, P<.0001). The area under the receiver operating curve using liver inflammation and fibrosis for the diagnosis of cirrhosis was 0.85. Liver inflammation and fibrosis score for ballooning grades 0, 1 and 2 was 1.2, 2.7 and 3.5 respectively (P<.05) with an area under the receiver operating characteristic curve of 0.83 for the diagnosis of ballooning. Patients with steatosis had lower liver inflammation and fibrosis (1.3) compared to patients with non-alcoholic steatohepatitis (3.0) (P<.0001); area under the receiver operating characteristic curve for the diagnosis of non-alcoholic steatohepatitis was 0.80. Liver inflammation and fibrosis scores for patients with mild and significant non-alcoholic fatty liver disease were 1.2 and 2.9 respectively (P<.0001). The area under the receiver operating characteristic curve of liver inflammation and fibrosis for the diagnosis of significant non-alcoholic fatty liver disease was 0.89. CONCLUSIONS: Multiparametric magnetic resonance is a promising technique with good diagnostic accuracy for non-alcoholic fatty liver disease histological parameters, and can potentially identify patients with non-alcoholic steatohepatitis and cirrhosis.

Translating the potential of the urine steroid metabolome to stage NAFLD (TrUSt-NAFLD): study protocol for a multicentre, prospective validation study.

INTRODUCTION: Non-alcoholic fatty liver disease (NAFLD) affects approximately one in four individuals and its prevalence continues to rise. The advanced stages of NAFLD with significant liver fibrosis are associated with adverse morbidity and mortality outcomes. Currently, liver biopsy remains the 'gold-standard' approach to stage NAFLD severity. Although generally well tolerated, liver biopsies are associated with significant complications, are resource intensive, costly, and sample only a very small area of the liver as well as requiring day case admission to a secondary care setting. As a result, there is a significant unmet need to develop non-invasive biomarkers that can accurately stage NAFLD and limit the need for liver biopsy. The aim of this study is to validate the use of the urine steroid metabolome as a strategy to stage NAFLD severity and to compare its performance against other non-invasive NAFLD biomarkers. METHODS AND ANALYSIS: The TrUSt-NAFLD study is a multicentre prospective test validation study aiming to recruit 310 patients with biopsy-proven and staged NAFLD across eight centres within the UK. 150 appropriately matched control patients without liver disease will be recruited through the Oxford Biobank. Blood and urine samples, alongside clinical data, will be collected from all participants. Urine samples will be analysed by liquid chromatography-tandem mass spectroscopy to quantify a panel of predefined steroid metabolites. A machine learning-based classifier, for example, Generalized Matrix Relevance Learning Vector Quantization that was trained on retrospective samples, will be applied to the prospective steroid metabolite data to determine its ability to identify those patients with advanced, as opposed to mild-moderate, liver fibrosis as a consequence of NAFLD. ETHICS AND DISSEMINATION: Research ethical approval was granted by West Midlands, Black Country Research Ethics Committee (REC reference: 21/WM/0177). A substantial amendment (TrUSt-NAFLD-SA1) was approved on 26 November 2021. TRIAL REGISTRATION NUMBER: ISRCTN19370855.

Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information.

AIMS: Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints. METHODS: Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable. RESULTS: Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance. CONCLUSIONS: This study developed a series of ML models of accuracy ranging from 71.9-99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.

Non-alcoholic fatty liver disease in pregnancy.

Non-alcoholic fatty liver disease (NAFLD) is now the commonest liver pathology in the UK; however, relatively little is known about its course in pregnancy or the effect it has on maternal or fetal outcomes. Described here is a 24-year-old woman in her first pregnancy who presented with non-specific symptoms and raised alanine aminotransferase with ultrasonography of her liver showing changes of steatosis and suspicious for cirrhosis, leading to a diagnosis of NAFLD. The case illustrates the need for the clinician to have awareness of this increasingly prevalent condition and for multidisciplinary management.

A low-energy total diet replacement program demonstrates a favorable safety profile and improves liver disease severity in nonalcoholic steatohepatitis.

OBJECTIVE: Low-energy diets are used to treat obesity and diabetes, but there are fears that they may worsen liver disease in patients with nonalcoholic steatohepatitis (NASH) and significant-to-advanced fibrosis. METHODS: In this 24-week single-arm trial, 16 adults with NASH, fibrosis, and obesity received one-to-one remote dietetic support to follow a low-energy (880 kcal/d) total diet replacement program for 12 weeks and stepped food reintroduction for another 12 weeks. Liver disease severity was blindly evaluated (magnetic resonance imaging proton density fat fraction [MRI-PDFF], iron-corrected T1 [cT1], liver stiffness on magnetic resonance elastography [MRE], and liver stiffness on vibration-controlled transient elastography [VCTE]). Safety signals included liver biochemical markers and adverse events. RESULTS: A total of 14 participants (87.5%) completed the intervention. Weight loss was 15% (95% CI: 11.2%-18.6%) at 24 weeks. Compared with baseline, MRI-PDFF reduced by 13.1% (95% CI: 8.9%-16.7%), cT1 by 159 milliseconds (95% CI: 108-216.5), MRE liver stiffness by 0.4 kPa (95% CI: 0.1-0.8), and VCTE liver stiffness by 3.9 kPa (95% CI: 2.6-7.2) at 24 weeks. The proportions with clinically relevant reductions in MRI-PDFF (≥30%), cT1 (≥88 milliseconds), MRE liver stiffness (≥19%), and VCTE liver stiffness (≥19%) were 93%, 77%, 57%, and 93%, respectively. Liver biochemical markers improved. There were no serious intervention-related adverse events. CONCLUSIONS: The intervention demonstrates high adherence, favorable safety profile, and promising efficacy as a treatment for NASH.

Profiling the genome and proteome of metabolic dysfunction-associated steatotic liver disease identifies potential therapeutic targets.

BACKGROUND & AIMS: Metabolic dysfunction-associated steatotic liver disease (MASLD) affects over 25% of the population and currently has no effective treatments. Plasma proteins with causal evidence may represent promising drug targets. We aimed to identify plasma proteins in the causal pathway of MASLD and explore their interaction with obesity. METHODS: We analysed 2,941 plasma proteins in 43,978 European participants from UK Biobank. We performed genome-wide association study (GWAS) for all MASLD-associated proteins and created the largest MASLD GWAS (109,885 cases/1,014,923 controls). We performed Mendelian Randomization (MR) and integrated proteins and their encoding genes in MASLD ranges to identify candidate causal proteins. We then validated them through independent replication, exome sequencing, liver imaging, bulk and single-cell gene expression, liver biopsies, pathway, and phenome-wide data. We explored the role of obesity by MR and multivariable MR across proteins, body mass index, and MASLD. RESULTS: We found 929 proteins associated with MASLD, reported five novel genetic loci associated with MASLD, and identified 17 candidate MASLD protein targets. We identified four novel targets for MASLD (CD33, GRHPR, HMOX2, and SCG3), provided protein evidence supporting roles of AHCY, FCGR2B, ORM1, and RBKS in MASLD, and validated nine previously known targets. We found that CD33, FCGR2B, ORM1, RBKS, and SCG3 mediated the association of obesity and MASLD, and HMOX2, ORM1, and RBKS had effect on MASLD independent of obesity. CONCLUSIONS: This study identified new protein targets in the causal pathway of MASLD, providing new insights into the multi-omics architecture and pathophysiology of MASLD. These findings advise further therapeutic interventions for MASLD.

Biomarkers for staging fibrosis and non-alcoholic steatohepatitis in non-alcoholic fatty liver disease (the LITMUS project): a comparative diagnostic accuracy study.

BACKGROUND: The reference standard for detecting non-alcoholic steatohepatitis (NASH) and staging fibrosis-liver biopsy-is invasive and resource intensive. Non-invasive biomarkers are urgently needed, but few studies have compared these biomarkers in a single cohort. As part of the Liver Investigation: Testing Marker Utility in Steatohepatitis (LITMUS) project, we aimed to evaluate the diagnostic accuracy of 17 biomarkers and multimarker scores in detecting NASH and clinically significant fibrosis in patients with non-alcoholic fatty liver disease (NAFLD) and identify their optimal cutoffs as screening tests in clinical trial recruitment. METHODS: This was a comparative diagnostic accuracy study in people with biopsy-confirmed NAFLD from 13 countries across Europe, recruited between Jan 6, 2010, and Dec 29, 2017, from the LITMUS metacohort of the prospective European NAFLD Registry. Adults (aged ≥18 years) with paired liver biopsy and serum samples were eligible; those with excessive alcohol consumption or evidence of other chronic liver diseases were excluded. The diagnostic accuracy of the biomarkers was expressed as the area under the receiver operating characteristic curve (AUC) with liver histology as the reference standard and compared with the Fibrosis-4 index for liver fibrosis (FIB-4) in the same subgroup. Target conditions were the presence of NASH with clinically significant fibrosis (ie, at-risk NASH; NAFLD Activity Score ≥4 and F≥2) or the presence of advanced fibrosis (F≥3), analysed in all participants with complete data. We identified thres holds for each biomarker for reducing the number of biopsy-based screen failures when recruiting people with both NASH and clinically significant fibrosis for future trials. FINDINGS: Of 1430 participants with NAFLD in the LITMUS metacohort with serum samples, 966 (403 women and 563 men) were included after all exclusion criteria had been applied. 335 (35%) of 966 participants had biopsy-confirmed NASH and clinically significant fibrosis and 271 (28%) had advanced fibrosis. For people with NASH and clinically significant fibrosis, no single biomarker or multimarker score significantly reached the predefined AUC 0·80 acceptability threshold (AUCs ranging from 0·61 [95% CI 0·54-0·67] for FibroScan controlled attenuation parameter to 0·81 [0·75-0·86] for SomaSignal), with accuracy mostly similar to FIB-4. Regarding detection of advanced fibrosis, SomaSignal (AUC 0·90 [95% CI 0·86-0·94]), ADAPT (0·85 [0·81-0·89]), and FibroScan liver stiffness measurement (0·83 [0·80-0·86]) reached acceptable accuracy. With 11 of 17 markers, histological screen failure rates could be reduced to 33% in trials if only people who were marker positive had a biopsy for evaluating eligibility. The best screening performance for NASH and clinically significant fibrosis was observed for SomaSignal (number needed to test [NNT] to find one true positive was four [95% CI 4-5]), then ADAPT (six [5-7]), MACK-3 (seven [6-8]), and PRO-C3 (nine [7-11]). INTERPRETATION: None of the single markers or multimarker scores achieved the predefined acceptable AUC for replacing biopsy in detecting people with both NASH and clinically significant fibrosis. However, several biomarkers could be applied in a prescreening strategy in clinical trial recruitment. The performance of promising markers will be further evaluated in the ongoing prospective LITMUS study cohort. FUNDING: The Innovative Medicines Initiative 2 Joint Undertaking.

Performance of non-invasive tests and histology for the prediction of clinical outcomes in patients with non-alcoholic fatty liver disease: an individual participant data meta-analysis.

BACKGROUND: Histologically assessed liver fibrosis stage has prognostic significance in patients with non-alcoholic fatty liver disease (NAFLD) and is accepted as a surrogate endpoint in clinical trials for non-cirrhotic NAFLD. Our aim was to compare the prognostic performance of non-invasive tests with liver histology in patients with NAFLD. METHODS: This was an individual participant data meta-analysis of the prognostic performance of histologically assessed fibrosis stage (F0-4), liver stiffness measured by vibration-controlled transient elastography (LSM-VCTE), fibrosis-4 index (FIB-4), and NAFLD fibrosis score (NFS) in patients with NAFLD. The literature was searched for a previously published systematic review on the diagnostic accuracy of imaging and simple non-invasive tests and updated to Jan 12, 2022 for this study. Studies were identified through PubMed/MEDLINE, EMBASE, and CENTRAL, and authors were contacted for individual participant data, including outcome data, with a minimum of 12 months of follow-up. The primary outcome was a composite endpoint of all-cause mortality, hepatocellular carcinoma, liver transplantation, or cirrhosis complications (ie, ascites, variceal bleeding, hepatic encephalopathy, or progression to a MELD score ≥15). We calculated aggregated survival curves for trichotomised groups and compared them using stratified log-rank tests (histology: F0-2 vs F3 vs F4; LSM: <10 vs 10 to <20 vs ≥20 kPa; FIB-4: <1·3 vs 1·3 to ≤2·67 vs >2·67; NFS: <-1·455 vs -1·455 to ≤0·676 vs >0·676), calculated areas under the time-dependent receiver operating characteristic curves (tAUC), and performed Cox proportional-hazards regression to adjust for confounding. This study was registered with PROSPERO, CRD42022312226. FINDINGS: Of 65 eligible studies, we included data on 2518 patients with biopsy-proven NAFLD from 25 studies (1126 [44·7%] were female, median age was 54 years [IQR 44-63), and 1161 [46·1%] had type 2 diabetes). After a median follow-up of 57 months [IQR 33-91], the composite endpoint was observed in 145 (5·8%) patients. Stratified log-rank tests showed significant differences between the trichotomised patient groups (p<0·0001 for all comparisons). The tAUC at 5 years were 0·72 (95% CI 0·62-0·81) for histology, 0·76 (0·70-0·83) for LSM-VCTE, 0·74 (0·64-0·82) for FIB-4, and 0·70 (0·63-0·80) for NFS. All index tests were significant predictors of the primary outcome after adjustment for confounders in the Cox regression. INTERPRETATION: Simple non-invasive tests performed as well as histologically assessed fibrosis in predicting clinical outcomes in patients with NAFLD and could be considered as alternatives to liver biopsy in some cases. FUNDING: Innovative Medicines Initiative 2.