Allen, Alina M.

AbstractBackground and aimsNonalcoholic steatohepatitis (NASH) is associated with metabolic conditions that increase the risk of de novo malignancy following transplant. Patients often have more than one underlying liver disease, which could change the risk of de novo malignancy. This study assessed the incidence of NASH overlap and its effect on de novo malignancy in liver transplant recipients.MethodsData was analyzed from the United Network for Organ Sharing database for all liver transplant recipients from 1997 to 2017 for NASH alone or in combination with another liver disease.ResultsThere is an increasing prevalence of NASH overlap. Of the 98,679 patients included in the analysis, 1238 had a de novo malignancy identified (7.4% by 5 years post‐transplant). The cumulative incidence of de novo malignancy increases in primary sclerosing cholangitis (PSC)/NASH overlap after 5 years and was increased in alcohol‐related liver disease (ALD)/NASH through 10 years compared to ether disease alone. NASH overlaps with “other” diseases experience a cumulative incidence similar to NASH and not the “other” disease. An increased risk of de novo solid organ malignancy was associated with older age, male gender, previous malignancy, and multiorgan transplant.ConclusionThe prevalence of liver transplant recipients with NASH overlap is increasing. These patients may experience different long‐term outcomes than patients with either diagnosis alone. De novo malignancy risk can be influenced by multiple factors and metabolic comorbidities. Further study of patients with overlap diagnoses is important moving forward to guide individualized care and cancer screening programs.

INTRODUCTION: Cirrhosis is associated with cardiac dysfunction and distinct electrocardiogram (ECG) abnormalities. This study aimed to develop a proof-of-concept deep learning-based artificial intelligence (AI) model that could detect cirrhosis-related signals on ECG and generate an AI-Cirrhosis-ECG (ACE) score that would correlate with disease severity. METHODS: A review of Mayo Clinic's electronic health records identified 5,212 patients with advanced cirrhosis ≥18 years who underwent liver transplantation at the 3 Mayo Clinic transplant centers between 1988 and 2019. The patients were matched by age and sex in a 1:4 ratio to controls without liver disease and then divided into training, validation, and test sets using a 70%-10%-20% split. The primary outcome was the performance of the model in distinguishing patients with cirrhosis from controls using their ECGs. In addition, the association between the ACE score and the severity of patients' liver disease was assessed. RESULTS: The model's area under the curve in the test set was 0.908 with 84.9% sensitivity and 83.2% specificity, and this performance remained consistent after additional matching for medical comorbidities. Significant elevations in the ACE scores were seen with increasing model for end-stage liver disease-sodium score. Longitudinal trends in the ACE scores before and after liver transplantation mirrored the progression and resolution of liver disease. DISCUSSION: The ACE score, a deep learning model, can accurately discriminate ECGs from patients with and without cirrhosis. This novel relationship between AI-enabled ECG analysis and cirrhosis holds promise as the basis for future low-cost tools and applications in the care of patients with liver disease.

Abstract Cirrhosis, highly prevalent worldwide, develops after years of hepatic inflammation triggering progressive fibrosis. Currently, the main etiologies of cirrhosis are non‐alcoholic fatty liver disease and alcohol‐related liver disease, although chronic hepatitis B and C infections are still major etiological factors in some areas of the world. Recent studies have shown that liver fibrosis can be assessed with relatively high accuracy noninvasively by serological tests, transient elastography, and radiological methods. These modalities may be utilized for screening for liver fibrosis in at‐risk populations. Thus far, a limited number of population‐based studies using noninvasive tests in different areas of the world indicate that a significant percentage of subjects without known liver disease (around 5% in general populations and a higher rate −18% to 27%‐in populations with risk factors for liver disease) have significant undetected liver fibrosis or established cirrhosis. Larger international studies are required to show the harms and benefits before concluding that screening for liver fibrosis should be applied to populations at risk for chronic liver diseases. Screening for liver fibrosis has the potential for changing the current approach from diagnosing chronic liver diseases late when patients have already developed complications of cirrhosis to diagnosing liver fibrosis in asymptomatic subjects providing the opportunity of preventing disease progression.

Abstract Background and Aims Although magnetic resonance elastography (MRE) has been well‐established for detecting and staging liver fibrosis, its prognostic role in determining outcomes of chronic liver disease (CLD) is mostly unknown. Approach and Results This retrospective study consisted of 1269 subjects who underwent MRE between 2007 and 2009 and followed up until death or last known clinical encounter or end of study period. Charts were reviewed for cirrhosis development, decompensation, and transplant or death. The cohort was split into baseline noncirrhosis (group 1), compensated cirrhosis (group 2), and decompensated cirrhosis (group 3). Cox‐regression analysis with age, sex, splenomegaly, CLD etiology, Child‐Pugh Score (CPS), Fibrosis‐4 Index (FIB‐4) score, and Model for End‐Stage Liver Disease (MELD)–adjusted HR for every 1‐kPa increase in liver stiffness measurement (LSM) were used to assess the predictive performance of MRE on outcomes. Group 1 ( n = 821) had baseline median LSM of 2.8 kPa, and cirrhosis developed in 72 (8.8%) subjects with an overall rate of about 1% cirrhosis/year. Baseline LSM predicted the future cirrhosis with multivariable adjusted HR of 2.38 ( p < 0.0001) (concordance, 0.84). In group 2 ( n = 277) with baseline median LSM of 5.7 kPa, 83 (30%) subjects developed decompensation. Baseline LSM predicted the future decompensation in cirrhosis with FIB‐4 and MELD‐adjusted HR of 1.22 ( p < 0.0001) (concordance, 0.75). In group 3 ( n = 171) with median baseline LSM of 6.8 kPa (5.2, 8.4), 113 (66%) subjects had either death or transplant. Baseline LSM predicted the future transplant or death with HR of 1.11 ( p = 0.013) (concordance 0.53) but not in CPS and MELD‐adjusted models ( p = 0.08). Conclusion MRE‐based LSM is independently predictive of development of future cirrhosis and decompensation, and has predictive value in future transplant/death in patients with CLD.

(1) Purpose: To determine the association between visceral adipose tissue (VAT) and proton density fat fraction (PDFF) with magnetic resonance imaging (MRI), and hepatic steatosis (HS), non-alcoholic steatohepatitis (NASH) and hepatic fibrosis (HF) in patients with known or suspected non-alcoholic fatty liver disease (NAFLD). (2) Methods: 135 subjects that had a liver biopsy performed within 3 months (bariatric cohort) or 1 month (NAFLD cohort) of an MRI exam formed the study group. VAT volume was quantified at L2-L3 level on opposed-phase images with signal intensity-based painting using a semi-quantitative software. Liver PDFF and pancreas PDFF were calculated on fat fraction maps. Liver volume (Lvol) and spleen volume (Svol) were also calculated using a semi-automated 3D volume tool available on PACS. A histological analysis was performed by an expert hepatopathologist blinded to imaging findings. (3) Results: The mean Lvol, Svol, liver PDFF, pancreas PDFF and VAT of the study population were 2492.2 mL, 381.6 mL, 13.2%, 12.7% and 120.6 mL, respectively. VAT showed moderate correlation with liver PDFF (r = 0.41, p < 0.001) and weak correlation with Lvol (r = 0.38, p < 0.001), Svol (r = 0.20, p = 0.025) and pancreas PDFF (rs = 0.29, p = 0.001). VAT, Lvol and liver PDFF were significantly higher in patients with HS (p < 0.001), NASH (p < 0.05) and HF (p < 0.05). VAT was also significantly higher in the presence of lobular inflammation (p = 0.019) and hepatocyte ballooning (p = 0.001). The cut-off VAT volumes for predicting HS, NASH and HF were 101.8 mL (AUC, 0.7), 111.8 mL (AUC, 0.64) and 111.6 mL (AUC, 0.66), respectively. (4) Conclusion: The MRI determined VAT can be used for predicting the presence of HS, NASH and HF in patients with known or suspected NAFLD.

BackgroundNonalcoholic fatty liver disease (NAFLD) affects 25% of the global population. The standard of diagnosis, biopsy, is invasive and affected by sampling error and inter‐reader variability. We hypothesized that widely available rapid MRI techniques could be used to predict nonalcoholic steatohepatitis (NASH) noninvasively by measuring liver stiffness, with magnetic resonance elastography (MRE), and liver fat, with chemical shift‐encoded (CSE) MRI. Besides, we validate an automated image analysis technique to maximize the utility of these methods.PurposeTo implement and test an automated system for analyzing CSE‐MRI and MRE data coupled with model‐based prediction of NASH.Study TypeProspective.SubjectsEighty‐three patients with suspected NAFLD.Field Strength/SequenceA 1.5 T using a flow‐compensated motion‐encoded gradient echo MRE sequence and a multiecho CSE‐MRI sequence.AssessmentsThe MRE and CSE‐MRI data were analyzed by two readers (5+ and 1 years of experience) and an automated algorithm. A logistic regression model to predict pathology‐diagnosed NASH was trained based on stiffness and proton density fat fraction, and the area under the receiver operating characteristic curve (AUROC) was calculated using 10‐fold cross validation for models based on both automated and manual measurements. A separate model was trained to predict the NASH severity score (NAS).Statistical TestsPearson's correlation, Bland–Altman, AUROC, C‐statistic.ResultsThe agreement between automated measurements and the more experienced reader (R2 = 0.87 for stiffness and R2 = 0.99 for proton density fat fraction [PDFF]) was slightly better than the agreement between readers (R2 = 0.85 and 0.98). The model for predicting biopsy‐diagnosed NASH had an AUROC of 0.87. The NAS‐prediction model had a C‐statistic of 0.85.Data ConclusionWe demonstrated a workflow that used a limited MRI acquisition protocol and fully automated analysis to predict NASH with high accuracy. These methods show promise to provide a reliable noninvasive alternative to biopsy for NASH‐screening in populations with NAFLD.Level of Evidence2Technical Efficacy Stage2

Background and Aims Electronic health record (EHR)‐based research allows the capture of large amounts of data, which is necessary in NAFLD, where the risk of clinical liver outcomes is generally low. The lack of consensus on which International Classification of Diseases (ICD) codes should be used as exposures and outcomes limits comparability and generalizability of results across studies. We aimed to establish consensus among a panel of experts on ICD codes that could become the reference standard and provide guidance around common methodological issues. Approach and Results Researchers with an interest in EHR‐based NAFLD research were invited to collectively define which administrative codes are most appropriate for documenting exposures and outcomes. We used a modified Delphi approach to reach consensus on several commonly encountered methodological challenges in the field. After two rounds of revision, a high level of agreement (>67%) was reached on all items considered. Full consensus was achieved on a comprehensive list of administrative codes to be considered for inclusion and exclusion criteria in defining exposures and outcomes in EHR‐based NAFLD research. We also provide suggestions on how to approach commonly encountered methodological issues and identify areas for future research. Conclusions This expert panel consensus statement can help harmonize and improve generalizability of EHR‐based NAFLD research.