Bush, Brian J.

INTRODUCTION: Nosocomial infections (NIs) in cirrhosis are associated with high mortality but could be preventable. Logistic regression (LR) models have failed to identify high-risk patients. We aimed to develop machine learning (ML) models to predict NI. METHODS: The CLEARED consortium consists of prospectively enrolled cirrhosis inpatients from >120 centers. Using day-of-admission clinical data, 3 ML approaches (random forest [RF], extreme gradient boosting, and neural networks [NNs]) were used to predict NI. Data were split 80:20 for training and testing stratified by the outcome. Models were compared using area under the receiver operating characteristic curve (AUC). RESULTS: In total, 8,263 patients (55.90 ± 13.34 years; 64.1% men) from 127 centers in 37 countries were included. NI developed in 869 (10.5%), a median of 6 (4–11) days of postadmission. Major NIs were respiratory (29.6%) and urinary tract infection (15.7%), and spontaneous bacterial peritonitis (13.5%). NIs occurred more frequently in patients from low/low-middle income countries and those with severe liver disease, alcohol etiology, and admission infections. NIs were associated with inpatient mortality (31.9% vs 8.1%, P < 0.001) and liver transplantation (4.8% vs 1.9%, P < 0.001). Although the RF model (AUC 0.69) showed good calibration (Brier score 0.09), outperforming extreme gradient boosting, neural network, and LR models (AUC 0.66 for all; LR comparison P = 0.043), no model achieved AUC ≥0.80 for clinical utility. At 10% predicted probability threshold, the RF model demonstrated only 75.4% sensitivity, 52.9% specificity, and 15.9% positive predictive value (PPV). DISCUSSION: NIs cannot be accurately predicted from day-of-admission data using ML models, even in a large, prospective, global cirrhosis cohort. Every hospitalized patient with cirrhosis should receive protocolized infection control measures.

Background/Aims: Infections with drug-resistant organisms (DROs) are associated with poor outcomes in cirrhosis. Rifaximin, widely used for hepatic encephalopathy (HE), could promote cross-resistance, but data regarding clinical impact are conflicting. Aim: Determine predictors of DROs in a global cirrhosis inpatient cohort focusing on preadmission rifaximin use.Methods: From the global CLEARED consortium, we focused on cirrhosis inpatients with infections on/during admission. Clinical/demographic/medication, especially rifaximin details were recorded. The primary outcome was DRO development. Multivariable regression for DRO including clinical, medications, and country income was performed.Results: 2,949 infected inpatients (55.3 years, 62.9% male) were included. 12.2% of all and 24.4% of culture-positive infections developed DROs; these patients had higher HE (39 vs. 31%, <i>P</i>=0.003), hepatorenal syndrome (25 vs. 19%, <i>P</i>=0.006), lactulose (55 vs. 47%, <i>P</i>=0.008) and rifaximin use (34 vs. 27%, <i>P</i>=0.006) on crude comparisons but country-income distributions were similar. 29.7% were on pre-admission rifaximin, mostly HE-related; they had more advanced cirrhosis and from low/low-middle-income countries. Daptomycin was used in 1.5%, linked with DROs (5.0 vs. 1.0%, <i>P</i><0.0001) without a difference in rifaximin use (1.4 vs.1.7%, <i>P</i>=0.61). On adjusted analysis, MELD-Na (1.03, 95% CI 1.02–1.04, <i>P</i><0.001) increased, whereas male sex (0.73, 95% CI 0.58–0.92, <i>P</i>=0.008) and hepatitis-B (0.65, 95% CI 0.45–0.92, <i>P</i>=0.020) decreased DRO. Rifaximin was not associated with DROs overall (OR 1.07, 95% CI 0.80–1.43, <i>P</i>=0.65) or within income strata (high: 1.07, 95% CI 0.59–1.92, <i>P</i>=0.82, upper-middle: 1.18, 95% CI 0.74–1.85, <i>P</i>=0.49, low/low-middle: 1.04, 95% CI 0.60–1.81, <i>P</i>=0.90) despite sensitivity analyses.Conclusions: In this large global cohort of hospitalized patients with cirrhosis and infections, 12% developed infections involving DROs. 30% had pre-admission rifaximin use which was not linked with daptomycin use or with DRO development on adjusted analysis overall or across country income groups.

Background and Aims: Prognosticating outcomes such as hospitalizations in outpatients with cirrhosis is challenging, especially with changing etiologies and demographics. This study aims to determine the impact of multi-omic strategies on outcome prediction. Approach and Results: NACSELD3 enrolls outpatients with cirrhosis with controlled/eradicated etiologies from 10 centers and follows them systematically. At baseline, clinical/demographic and cirrhosis details were recorded and saliva and serum samples were collected for microbiome and metabolome analysis, respectively. Multi-omic bioinformatic studies to determine the interaction of microbiota and metabolites with the clinical prediction of 6-month hospitalizations were performed. Five hundred sixty-five patients (60.2 y, 68% men, 35% alcohol, 33% metabolic dysfunction-associated steatohepatitis, 21%, eradicated HCV with MELD 3.0 12) were enrolled. One hundred sixty-three (29%) required 6-month hospitalizations; most (75%) were liver-related. Those hospitalized had worse cirrhosis severity and comorbidity indices but similar demographics and oral health variables. Salivary microbiome alpha-diversity was lower (1.96±0.48 vs. 2.09±0.45, p =0.018) with greater pathobionts ( Streptococcus , Treponema, Enterococcaceae) and lower commensal genhospitalized/noera ( Veillonella, Prevotella, Haemophilus , Lachnospiraceae spp) at baseline. Serum metabolomics showed significant separation at baseline between hospitalized/non-hospitalized patients using supervised analyses with microbial-origin (phenyllactate, secondary bile acids, indoles), choline moieties, and polyamine/GABA (3-ureidopropionate/spermidine) metabolites being most prominent. Area under the curve using random forest for clinical, microbial, and metabolomic variables was higher than that of these individually. Latent factor analysis showed clinical variables (MELD 3.0, hemoglobin, and albumin) with the greatest impact, followed by salivary microbiota and then serum microbiome for hospitalization prediction. Conclusions: In a multicenter North American outpatient cirrhosis cohort with controlled etiologies, serum metabolomics and salivary microbiome add to clinical variables to prognosticate 6-month hospitalization.