Hu, Chang

Abstract Background: Primary sclerosing cholangitis (PSC) patients have a risk of developing cholangiocarcinoma (CCA). Establishing predictive models for CCA in PSC is important. Methods: In a large cohort of 1,459 PSC patients seen at Mayo Clinic (1993-2020), we quantified the impact of clinical/laboratory variables on CCA development using univariate and multivariate Cox models and predicted CCA using statistical and artificial intelligence approaches. We explored plasma bile acid (BA) levels’ predictive power of CCA (subset of 300 patients, BA cohort). Results: Eight significant risk factors (false discovery rate: 20%) were identified with univariate analysis; prolonged inflammatory bowel disease (IBD) was the most important one. IBD duration, PSC duration, and total bilirubin remained significant (p<0.05) with multivariate analysis. Clinical/laboratory variables predicted CCA with cross-validated C-indexes of 0.68–0.71 at different time points of disease, significantly better compared to commonly used PSC risk scores. Lower chenodeoxycholic acid, higher conjugated fraction of lithocholic acid and hyodeoxycholic acid, and higher ratio of cholic acid to chenodeoxycholic acid were predictive of CCA. BAs predicted CCA with a cross-validated C-index of 0.66 (std: 0.11, BA cohort), similar to clinical/laboratory variables (C-index=0.64, std: 0.11, BA cohort). Combining BAs with clinical/laboratory variables leads to the best average C-index of 0.67 (std: 0.13, BA cohort). Conclusions: In a large PSC cohort, we identified clinical and laboratory risk factors for CCA development and demonstrated the first artificial intelligence based predictive models that performed significantly better than common risk scores. More predictive data modalities are needed for clinical adoption of these models.

Background and Aims Altered bile acid (BA) homeostasis is an intrinsic facet of cholestatic liver diseases, but clinical usefulness of plasma BA assessment in primary sclerosing cholangitis (PSC) remains understudied. We performed BA profiling in a large retrospective cohort of patients with PSC and matched healthy controls, hypothesizing that plasma BA profiles vary among patients and have clinical utility. Approach and Results Plasma BA profiling was performed in the Clinical Biochemical Genetics Laboratory at Mayo Clinic using a mass spectrometry based assay. Cox proportional hazard (univariate) and gradient boosting machines (multivariable) models were used to evaluate whether BA variables predict 5‐year risk of hepatic decompensation (HD; defined as ascites, variceal hemorrhage, or encephalopathy). There were 400 patients with PSC and 302 controls in the derivation cohort (Mayo Clinic) and 108 patients with PSC in the validation cohort (Norwegian PSC Research Center). Patients with PSC had increased BA levels, conjugated fraction, and primary‐to‐secondary BA ratios relative to controls. Ursodeoxycholic acid (UDCA) increased total plasma BA level while lowering cholic acid and chenodeoxycholic acid concentrations. Patients without inflammatory bowel disease (IBD) had primary‐to‐secondary BA ratios between those of controls and patients with ulcerative colitis. HD risk was associated with increased concentration and conjugated fraction of many BA, whereas higher G:T conjugation ratios were protective. The machine‐learning model, PSC‐BA profile score (concordance statistic [C‐statistic], 0.95), predicted HD better than individual measures, including alkaline phosphatase, and performed well in validation (C‐statistic, 0.86). Conclusions Patients with PSC demonstrated alterations of plasma BA consistent with known mechanisms of cholestasis, UDCA treatment, and IBD. Notably, BA profiles predicted future HD, establishing the clinical potential of BA profiling, which may be suited for use in clinical trials.

Abstract Background: The association of pre-existing diabetes mellitus and outcomes among critically ill patients remains unknown.Methods: This retrospective study enrolled patients who were covered by the eICU Collaborative Research Database from 2014 to 2015. DM was the exposure of interest, and diabetic individuals were adjudicated by the medical history, and blood glucose level (BGL). We abstracted basic characteristics, laboratory variables, and primary exposures. ICU mortality was the primary outcome.Results: In a cohort of 134,429 critically ill patients (male 54.4%, median age 66 [54-77] years, BMI 28[24-33] kg/m2), the prevalence of DM was 29%. In comparison with nondiabetics, DM patients were older, more obese, had higher Acute Physiology and Chronic Health Evaluation (APACHE)-IV score, and ICU admission BGL. In comparison with nondiabetics, pre-existing DM was associated with lower ICU mortality (OR: 0.846, 95%CI: 0.791-0.905). In multivariable logistic regression and Cox proportional hazard analyses, pre-existing DM was associated with decreased odds of ICU mortality in hyperglycemic patients (>163 mg/dL), higher APACHE IV score (>67), middle to old age (45-75 years), sepsis and morbid obesity (BMI>35 kg/m2). Also, in comparison with nondiabetics, pre-existing DM was associated with lower mortality among those with higher mean BGL (>128 mg/dL), and higher mortality in lower mean BGL (<107 mg/dL). Conclusions: In comparison with nondiabetics, pre-existing DM is associated with a lower adjusted ICU mortality. This association is stronger in DM patients with hyperglycemia, obesity, sepsis, middle to old age, and higher APACHE IV score.

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).