Vesterhus, Mette

Background and Aims: Among those with primary sclerosing cholangitis (PSC), perihilar cholangiocarcinoma (pCCA) is often diagnosed at a late stage and is a leading source of mortality. Detection of pCCA in PSC when curative action can be taken is challenging. Our aim was to create a deep learning model that analyzed MRI to detect early-stage pCCA and compare its diagnostic performance with expert radiologists. Approach and Results: We conducted a multicenter, international, retrospective cohort study involving adults with large duct PSC who underwent contrast-enhanced MRI. Senior abdominal radiologists reviewed the images. All patients with pCCA had early-stage cancer and were registered for liver transplantation. We trained a 3D DenseNet-121 model, a form of deep learning, using MRI images and assessed its performance in a separate test cohort. The study included 398 patients (training cohort n=150; test cohort n=248). pCCA was present in 230 individuals (training cohort n=64; test cohort n=166). In the test cohort, the respective performances of the model compared to the radiologists were: sensitivity 87.9% versus 50.0%, p <0.001; specificity 84.1% versus 100.0%, p <0.001; area under receiving operating curve 86.0% versus 75.0%, p <0.001. Even when a mass was absent, the model had a higher sensitivity for pCCA than radiologists (91.6% vs. 50.6%, p <0.001) and maintained good specificity (84.1%). Conclusions: The 3D DenseNet-121 MRI model effectively detects early-stage pCCA in PSC patients. Compared to expert radiologists, the model missed fewer cases of cancer.

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.

Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine‐based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C‐statistic, 0.90; 95% confidence interval [CI], 0.84‐0.95) and performed well compared to Model for End‐Stage Liver Disease (MELD) score (C‐statistic, 0.72; 95% CI, 0.57‐0.84), Mayo PSC risk score (C‐statistic, 0.85; 95% CI, 0.77‐0.92), and SAP <1.5 × ULN (C‐statistic, 0.65; 95% CI, 0.55‐0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C‐statistic, 0.90; 95% CI, 0.82‐0.96) and when the score was reapplied at a later course in the disease (C‐statistic, 0.82; 95% CI, 0.64‐0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.