Citations

INTRODUCTION: Readmission and death in cirrhosis are common, expensive, and difficult to predict. Our aim was to evaluate the abilities of multiple artificial intelligence (AI) techniques to predict clinical outcomes based on variables collected at admission, during hospitalization, and at discharge. METHODS: We used the multicenter North American Consortium for the Study of End-Stage Liver Disease (NACSELD) cohort of cirrhotic inpatients who are followed up through 90-days postdischarge for readmission and death. We used statistical methods to select variables that are significant for readmission and death and trained 3 AI models, including logistic regression (LR), kernel support vector machine (SVM), and random forest classifiers (RFC), to predict readmission and death. We used the area under the receiver operating characteristic curve (AUC) from 10-fold crossvalidation for evaluation to compare sexes. Data were compared with model for end-stage liver disease (MELD) at discharge. RESULTS: We included 2,170 patients (57 ± 11 years, MELD 18 ± 7, 61% men, 79% White, and 8% Hispanic). The 30-day and 90-day readmission rates were 28% and 47%, respectively, and 13% died at 90 days. Prediction for 30-day readmission resulted in 0.60 AUC for all patients with RFC, 0.57 AUC with LR for women-only subpopulation, and 0.61 AUC with LR for men-only subpopulation. For 90-day readmission, the highest AUC was achieved with kernel SVM and RFC (AUC = 0.62). We observed higher predictive value when training models with only women (AUC = 0.68 LR) vs men (AUC = 0.62 kernel SVM). Prediction for death resulted in 0.67 AUC for all patients, 0.72 for women-only subpopulation, and 0.69 for men-only subpopulation, all with LR. MELD-Na model AUC was similar to those from the AI models. DISCUSSION: Despite using multiple AI techniques, it is difficult to predict 30- and 90-day readmissions and death in cirrhosis. AI model accuracies were equivalent to models generated using only MELD-Na scores. Additional biomarkers are needed to improve our predictive capability (See also the visual abstract at http://links.lww.com/AJG/B710).

The burden of cirrhosis hospitalizations is increasing. The admission Model for End‐Stage Liver Disease–lactate (MELD‐lactate) was recently demonstrated to be a superior predictor of in‐hospital mortality compared with MELD in limited cohorts. We identified specific classes of hospitalizations where MELD‐lactate may be especially useful and evaluated the predictive role of lactate clearance. This was a retrospective cohort study of 1036 cirrhosis hospitalizations for gastrointestinal bleeding, infection, or other portal hypertension–related indications in the Veterans Health Administration where MELD‐lactate was measured on admission. Performance characteristics for in‐hospital mortality were compared between MELD‐lactate and MELD/MELD‐sodium (MELD‐Na), with stratified analyses of MELD categories (≤15, >15 to <25, ≥25) and reason for admission. We also incorporated day 3 lactate levels into modeling and tested for an interaction between day 1 MELD‐lactate and day 3 lactate clearance. MELD‐lactate had superior discrimination for in‐hospital mortality compared with MELD or MELD‐Na (area under the curve [AUC] 0.789 versus 0.776 versus 0.760, respectively; P < 0.001) and superior calibration. MELD‐lactate had higher discrimination among hospitalizations with MELD ≤15 (AUC 0.763 versus 0.608 for MELD, global P = 0.01) and hospitalizations for infection (AUC 0.791 versus 0.674 for MELD, global P < 0.001). We found a significant interaction between day 1 MELD‐lactate and day 3 lactate clearance; heat maps were created as clinical tools to risk‐stratify patients based on these clinical data. MELD‐lactate had significantly superior performance in predicting in‐hospital mortality among patients hospitalized for infection and/or with MELD ≤15 when compared with MELD or MELD‐Na. Incorporating day 3 lactate clearance may further improve prognostication.

INTRODUCTION: The purpose of this study was to find out whether 3-dimensional (3D)–printed models improved the learners' ability to identify liver segments. METHODS: A total of 116 physicians from 3 disciplines were tested in a cross-over trial at baseline and after teaching with 3D models and 2-dimensional (2D) images. Adjusted multilevel-mixed models were used to compare scores at baseline and after 3D and 2D. RESULTS: Accuracy in identifying hepatic segments was higher with 3D first than 2D (77% vs 69%; P = 0.05) and not significantly improved by a combination of 3D and 2D. Increased confidence in segment identification was highest in trainees after 3D ( P = 0.04). DISCUSSION: 3D-printed models facilitate learning hepatic segmental anatomy.

AbstractBackground & AimsPhosphodiesterase‐5 inhibitors (PDE‐5‐I) are used for treatment of erectile dysfunction (ED), which is common in patients with cirrhosis. They may improve portal hypertension (PH), but contradictory data on efficacy and side‐effects have been reported. Non‐selective beta blockers (NSBB) reduce portal pressure, but might aggravate ED. Thus, we evaluated the combination of PDE‐5‐I with NSBB and its impact on PH and ED in experimental cirrhosis.MethodsED was assessed in cirrhotic patients (n = 86) using standardized questionnaire. Experimental cirrhosis was induced by bile‐duct‐ligation or carbon‐tetrachloride intoxication in rats. Corpus cavernosum pressure – a surrogate of ED ‐, as well as systemic and portal haemodynamics, were measured in vivo and in situ after acute administration of udenafil alone or in combination with propranolol. mRNA and protein levels of PDE‐5 signalling were analysed using PCR and western Blot.ResultsED in humans was related to severity of liver disease and to NSBB treatment. PDE‐5 was mainly expressed in hepatic stellate cells and upregulated in human and experimental cirrhosis. Propranolol reduced corpus cavernosum pressure in cirrhotic rats and it was restored by udenafil. Even though udenafil treatment improved PH, it led to a reduction of mean arterial pressure. The combination of udenafil and propranolol reduced portal pressure and hepatic resistance without systemic side‐effects.ConclusionsED is common with advanced cirrhosis and concomitant NSBB treatment. The combination of PDE‐5‐I and NSBB improves ED and PH in experimental cirrhosis.

Background and Aims Reliance on exception points to prioritize children for liver transplantation (LT) stems from concerns that the Pediatric End‐Stage Liver Disease (PELD) score underestimates mortality. Renal dysfunction and serum sodium disturbances are negative prognosticators in adult LT candidates and various pediatric populations, but are not accounted for in PELD. We retrospectively evaluated the effect of these parameters in predicting 90‐day wait‐list death/deterioration among pediatric patients (<12 years) listed for isolated LT in the United States between February 2002 and June 2018. Approach and Results Among 4,765 patients, 2,303 (49.3%) were transplanted, and 231 (4.8%) died or deteriorated beyond transplantability within 90 days of listing. Estimated glomerular filtration rate (eGFR) (hazard ratio [HR] 1.09 per 5‐unit decrease, 95% confidence interval [CI] 1.06‐1.10) and dialysis (HR 7.24, 95% CI 3.57‐14.66) were univariate predictors of 90‐day death/deterioration (P < 0.001). The long‐term benefit of LT persisted in patients with renal dysfunction, with LT as a time‐dependent covariate conferring a 2.4‐fold and 17‐fold improvement in late survival among those with mild and moderate‐to‐severe dysfunction, respectively. Adjusting for PELD, sodium was a significant nonlinear predictor of outcome, with 90‐day death/deterioration risk increased at both extremes of sodium (HR 1.20 per 1‐unit decrease below 137 mmol/L, 95% CI 1.16‐1.23; HR per 1‐unit increase above 137 mmol/L 1.13, 95% CI 1.10‐1.17, P < 0.001). A multivariable model incorporating PELD, eGFR, dialysis, and sodium demonstrated improved performance and superior calibration in predicting wait‐list outcomes relative to the PELD score. Conclusions Listing eGFR, dialysis, and serum sodium are potent, independent predictors of 90‐day death/deterioration in pediatric LT candidates, capturing risk not accounted for by PELD. Incorporation of these variables into organ allocation systems may highlight patient subsets with previously underappreciated risk, augment ability of PELD to prioritize patients for transplantation, and ultimately mitigate reliance on nonstandard exceptions.

OBJECTIVES: Hepatic encephalopathy (HE) is common in advanced cirrhosis and is characterized by marked neuropsychiatric abnormalities. However, despite its severity and effects on brain function, the impact of HE on psychological status of patients has not been adequately assessed. The aim of this study was to evaluate the effect of HE on psychological status of patients and their informal caregivers. METHODS: Fifteen patients with cirrhosis and episodic or persistent HE and their corresponding informal caregivers were included. Semistructured interviews were performed in patients and caregivers. Quality of life (QoL) was assessed by the short-form 36 in both patients and caregivers, and the Zarit burden score was measured in caregivers. The analysis of interviews was performed using qualitative methodology. RESULTS: HE causes a major psychological impact on patients with HE. The first episode of HE caused a very significant impact that was reported with deep feelings, mainly of fear, anger, misery, anxiety, and sorrow, which persisted with time. Symptoms causing more psychological impact on patients were impaired ability to walk and speak. All effects were associated with a marked impairment in QoL. The psychological impact was also marked in caregivers who had a major burden, as assessed by the Zarit score. Moreover, QoL, particularly the mental component score, was markedly impaired in caregivers in intensity similar to that of patients. DISCUSSION: HE has a profound psychological impact on patients and their informal caregivers, associated with a marked negative influence on QoL. The psychological effects of HE on patients and caregivers should be evaluated and treated.

Background and Aims Alcoholic hepatitis (AH) is diagnosed by clinical criteria, although several objective scores facilitate risk stratification. Extracellular vesicles (EVs) have emerged as biomarkers for many diseases and are also implicated in the pathogenesis of AH. Therefore, we investigated whether plasma EV concentration and sphingolipid cargo could serve as diagnostic biomarkers for AH and inform prognosis to permit dynamic risk profiling of AH subjects. Approach and Results EVs were isolated and quantified from plasma samples from healthy controls, heavy drinkers, and subjects with end‐stage liver disease (ESLD) attributed to cholestatic liver diseases and nonalcoholic steatohepatitis, decompensated alcohol‐associated cirrhosis (AC), and AH. Sphingolipids were quantified by tandem mass spectroscopy. The median plasma EV concentration was significantly higher in AH subjects (5.38 × 1011/mL) compared to healthy controls (4.38 × 1010/mL; P < 0.0001), heavy drinkers (1.28 × 1011/mL; P < 0.0001), ESLD (5.35 × 1010/mL; P < 0.0001), and decompensated AC (9.2 × 1010/mL; P < 0.0001) disease controls. Among AH subjects, EV concentration correlated with Model for End‐Stage Liver Disease score. When EV counts were dichotomized at the median, survival probability for AH subjects at 90 days was 63.0% in the high‐EV group and 90.0% in the low‐EV group (log‐rank P value = 0.015). Interestingly, EV sphingolipid cargo was significantly enriched in AH when compared to healthy controls, heavy drinkers, ESLD, and decompensated AC (P = 0.0001). Multiple sphingolipids demonstrated good diagnostic and prognostic performance as biomarkers for AH. Conclusions Circulating EV concentration and sphingolipid cargo signature can be used in the diagnosis and differentiation of AH from heavy drinkers, decompensated AC, and other etiologies of ESLD and predict 90‐day survival permitting dynamic risk profiling.