Simonetto, Douglas A.

Background and Aims: Alcohol-associated hepatitis (AH) poses significant short-term mortality. Existing prognostic models lack precision for 90-day mortality. Utilizing artificial intelligence in a global cohort, we sought to derive and validate an enhanced prognostic model. Approach and Results: The Global AlcHep initiative, a retrospective study across 23 centers in 12 countries, enrolled patients with AH per National Institute for Alcohol Abuse and Alcoholism criteria. Centers were partitioned into derivation (11 centers, 860 patients) and validation cohorts (12 centers, 859 patients). Focusing on 30 and 90-day postadmission mortality, 3 artificial intelligence algorithms (Random Forest, Gradient Boosting Machines, and eXtreme Gradient Boosting) informed an ensemble model, subsequently refined through Bayesian updating, integrating the derivation cohort’s average 90-day mortality with each center’s approximate mortality rate to produce posttest probabilities. The ALCoholic Hepatitis Artificial INtelligence Ensemble score integrated age, gender, cirrhosis, and 9 laboratory values, with center-specific mortality rates. Mortality was 18.7% (30 d) and 27.9% (90 d) in the derivation cohort versus 21.7% and 32.5% in the validation cohort. Validation cohort 30 and 90-day AUCs were 0.811 (0.779–0.844) and 0.799 (0.769–0.830), significantly surpassing legacy models like Maddrey’s Discriminant Function, Model for End-Stage Liver Disease variations, age-serum bilirubin-international normalized ratio-serum Creatinine score, Glasgow, and modified Glasgow Scores (p < 0.001). ALCoholic Hepatitis Artificial INtelligence Ensemble score also showcased superior calibration against MELD and its variants. Steroid use improved 30-day survival for those with an ALCoholic Hepatitis Artificial INtelligence Ensemble score > 0.20 in both derivation and validation cohorts. Conclusions: Harnessing artificial intelligence within a global consortium, we pioneered a scoring system excelling over traditional models for 30 and 90-day AH mortality predictions. Beneficial for clinical trials, steroid therapy, and transplant indications, it’s accessible at: https://aihepatology.shinyapps.io/ALCHAIN/.

The liver transplantation (LT) evaluation and waitlisting process is subject to variations in care that can impede quality. The American Association for the Study of Liver Diseases (AASLD) Practice Metrics Committee (PMC) developed quality measures and patient-reported experience measures along the continuum of pre-LT care to reduce care variation and guide patient-centered care. Following a systematic literature review, candidate pre-LT measures were grouped into 4 phases of care: referral, evaluation and waitlisting, waitlist management, and organ acceptance. A modified Delphi panel with content expertise in hepatology, transplant surgery, psychiatry, transplant infectious disease, palliative care, and social work selected the final set. Candidate patient-reported experience measures spanned domains of cognitive health, emotional health, social well-being, and understanding the LT process. Of the 71 candidate measures, 41 were selected: 9 for referral; 20 for evaluation and waitlisting; 7 for waitlist management; and 5 for organ acceptance. A total of 14 were related to structure, 17 were process measures, and 10 were outcome measures that focused on elements not typically measured in routine care. Among the patient-reported experience measures, candidates of LT rated items from understanding the LT process domain as the most important. The proposed pre-LT measures provide a framework for quality improvement and care standardization among candidates of LT. Select measures apply to various stakeholders such as referring practitioners in the community and LT centers. Clinically meaningful measures that are distinct from those used for regulatory transplant reporting may facilitate local quality improvement initiatives to improve access and quality of care.

ABSTRACT Objective: The aim of the study is to develop a predictive model for in-hospital mortality in critically ill patients with cirrhosis and sepsis, using clinical and laboratory data. Design: This is a retrospective cohort study. Setting: Medical and mixed intensive care units (ICUs) of a tertiary medical center. Patients: Cirrhotic adults were admitted with sepsis to the ICUs from January of 2007 to May of 2017. Interventions: None. Measurements and Main Results: Of 2,595 ICU admissions of patients with cirrhosis, 277 with first ICU admission for sepsis were included in the analysis, and 37% died in the hospital. Patients who stayed in the ICU for at least 6 h (n = 275) were considered for the multivariate model. Ten-fold cross-validation was used to estimate best parameter values and model performance, and the final model was chosen as the model maximizing area under the receiver-operating characteristic curve. Variables in order of impact were Acute Physiology and Chronic Health Evaluation (APACHE) III score, initial serum lactate, conjugated bilirubin, serum creatinine, model for end-stage liver disease score, age, body mass index, and serum hemoglobin. The final best model from cross-validation presented an area under the receiver operator characteristic curve (AUC) of 0.75, using a cut-point of 50% estimated probability, sensitivity and specificity were 0.46 and 0.90, respectively, with positive predictive value of 0.72 and negative predictive value of 0.74. These results were similar to the APACHE III only model (AUC = 0.74, sensitivity = 0.43, specificity = 0.89, positive predictive value = 0.69, negative predictive value = 0.73). Conclusion: The combination of initial serum lactate level, conjugated bilirubin, initial serum creatinine, model for end-stage liver disease score, age, body mass index, and serum hemoglobin did not yield meaningful improvement in the AUC and did not provide advantage over the APACHE III score for the prediction of in-hospital mortality in critically ill patients with cirrhosis and sepsis.

INTRODUCTION: Management of hepatic encephalopathy relies on self-titration of lactulose. In this feasibility trial, we assess an artificial intelligence–enabled tool to guide lactulose use through a smartphone application. METHODS: Subjects with hepatic encephalopathy on lactulose captured bowel movement pictures during lead-in and intervention phases. During the intervention phase, daily feedback on lactulose titration was delivered through the application. Goals were determined according to number of bowel movement and Bristol Stool Scale reports. RESULTS: Subjects completed the study with more than 80% satisfaction. In the lead-in phase, less compliant subjects achieved Bristol Stool Scale goal on 62/111 (56%) of days compared with 107/136 (79%) in the intervention phase ( P = 0.041), while the most compliant subjects showed no difference. Severe/recurrent hepatic encephalopathy group achieved Bristol Stool Scale goal on 80/104 (77%) days in the lead-in phase and 90/110 (82%) days in the intervention phase ( P = NS), compared with 89/143 (62%) days and 86/127 (68%) days in the stable group. DISCUSSION: Dieta application is a promising tool for objective Bowel Movement/Bristol Stool Scale tracking for hepatic encephalopathy and may potentially be used to assist with lactulose titration.

Background: The Sepsis-3 guidelines have incorporated serum lactate levels of >2 mmol/L in septic shock definition to account for higher observed mortality. Further evidence is needed to support this threshold in cirrhosis, as well as target mean arterial pressure (MAP) during resuscitation. Methods: This observational cohort study investigated the association between initial serum lactate and resuscitation MAP levels on in-hospital mortality in patients with and without cirrhosis. Patients admitted to the intensive care unit for the treatment of septic shock between 2006 and 2021 in a quaternary academic center were included. Patients with cirrhosis documented on imaging and International Classification of Disease codes (n=595) were compared to patients without cirrhosis (n=575). The association of intensive care unit admission lactate levels and median 2-hour MAP with in-hospital mortality and the need for continuous renal replacement therapy was assessed. The association between median 24-hour MAP and in-hospital mortality was analyzed post hoc. Results: Within the cirrhosis group, admission lactate levels of 2–4 and >4 mmol/L were associated with increased in-hospital mortality compared to lactate <2 mmol/L [adjusted odds ratio (aOR): 1.69, CI: 1.03–2.81, aOR: 4.02, CI: 2.53–6.52]. Median 24-hour MAP 60–65 and <60 mm Hg were also associated with increased in-hospital mortality compared with MAP >65 mm Hg (aOR: 2.84, CI: 1.64–4.92 and aOR: 7.34, CI: 3.17–18.76). In the noncirrhosis group, associations with in-hospital mortality were weaker for lactate 2–4 and >4 mmol/L (aOR: 1.32, CI: 0.77–2.27 and aOR: 2.25, CI: 1.40–3.67) and median 24-hour MAP 60–65 and <60 mm Hg (aOR: 1.70, CI: 0.65–4.14 and aOR: 4.41, CI: 0.79–29.38). Conclusions: These findings support utilizing lactate >2 mmol/L in the definition of septic shock, as well as a target MAP of >65 mm Hg during resuscitation in patients with cirrhosis.

Lactulose-based hepatic encephalopathy treatment requires bowel movements/day titration, which is improved with Bristol stool scale (BSS) incorporation. Dieta app evaluates artificial intelligence (AI)-based BSS (AI-BSS) with stool images. Initially, controls (N = 13) and cirrhosis patients on lactulose/not on lactulose (n = 33) were trained on the app. They entered self-reported BSS (self-BSS) with AI-BSS communicated. Lactulose dose changes were tracked. A subset (n = 12) was retested with AI communication blocked. Most subjects were comfortable with the app. Self/AI-BSS and lactulose dose/AI-BSS correlation increased with app use. AI-BSS communications improved insight into self-BSS over time. Dieta app to gauge stool AI characteristics was acceptable and increased insight into lactulose dose and BSS in cirrhosis.

Background: Sensors within smartphones, such as accelerometer and location, can describe longitudinal markers of behavior as represented through devices in a method called digital phenotyping. This study aimed to assess the feasibility of digital phenotyping for patients with alcohol-associated liver disease and alcohol use disorder, determine correlations between smartphone data and alcohol craving, and establish power assessment for future studies to prognosticate clinical outcomes. Methods: A total of 24 individuals with alcohol-associated liver disease and alcohol use disorder were instructed to download the AWARE application to collect continuous sensor data and complete daily ecological momentary assessments on alcohol craving and mood for up to 30 days. Data from sensor streams were processed into features like accelerometer magnitude, number of calls, and location entropy, which were used for statistical analysis. We used repeated measures correlation for longitudinal data to evaluate associations between sensors and ecological momentary assessments and standard Pearson correlation to evaluate within-individual relationships between sensors and craving. Results: Alcohol craving significantly correlated with mood obtained from ecological momentary assessments. Across all sensors, features associated with craving were also significantly correlated with all moods (eg, loneliness and stress) except boredom. Individual-level analysis revealed significant relationships between craving and features of location entropy and average accelerometer magnitude. Conclusions: Smartphone sensors may serve as markers for alcohol craving and mood in alcohol-associated liver disease and alcohol use disorder. Findings suggest that location-based and accelerometer-based features may be associated with alcohol craving. However, data missingness and low participant retention remain challenges. Future studies are needed for further digital phenotyping of relapse risk and progression of liver disease.

INTRODUCTION: Evidence on the comparison of treatments for hepatorenal syndrome-acute kidney injury (HRS-AKI) in a US population is limited. An indirect comparison of terlipressin plus albumin vs midodrine and octreotide plus albumin (MO) may provide further insight into treatment efficacy. METHODS: Cohorts of patients treated for HRS-AKI characterized by inclusion of patients with serum creatinine (SCr) <5 mg/dL and baseline acute-on-chronic liver failure grades 0–2 and exclusion of patients listed for transplant if model for end-stage liver disease scores ≥35 were pooled from (i) the CONFIRM and REVERSE randomized controlled trials (N = 159 meeting eligibility criteria from N = 216 overall, treated with terlipressin) and (ii) a retrospective review of medical records from 10 US tertiary hospitals (2016–2019; N = 55 treated with MO meeting eligibility criteria from N = 200 overall). The primary end point comparing the 2 cohorts was HRS reversal defined as achieving SCr ≤1.5 mg/dL at least once during the treatment. Covariate balancing propensity scoring was used to adjust for differences in baseline characteristics. RESULTS: HRS-AKI reversal was achieved in 52.35% of terlipressin-treated patients compared with 20% of MO-treated patients (adjusted mean difference 32.35%, 95% confidence interval [CI] 17.40–47.30, P < 0.0001). Terlipressin-treated patients had increased overall survival (adjusted hazard ratio 0.57, 95% CI 0.35–0.93, P = 0.02) but similar transplant-free survival (adjusted hazard ratio 0.79, 95% CI 0.53–1.17, P = 0.24). Achievement of HRS-AKI reversal was associated with increased OS and TFS regardless of treatment ( P < 0.001). DISCUSSION: Consistent with prior reports, terlipressin plus albumin is more effective in improving kidney function and achieving HRS-AKI reversal than MO plus albumin based on indirect comparison in a US population.