Casta, Adelaida La

Abstract Background and Aims Primary sclerosing cholangitis (PSC) increases the risk of developing cholangiocarcinoma (CCA), which is the leading cause of premature death in these patients. Current diagnostic methods for early detection of either condition remain largely suboptimal. This study investigates serum metabolites as potential non-invasive diagnostic biomarkers. Methods This multicenter international study analyzed 459 serum samples from 13 international centers, including patients with PSC (n = 216), PSC who developed CCA during follow-up (PSC to CCA; n = 24), PSC with concomitant CCA (PSC-CCA; n = 88), ulcerative colitis (UC; n = 14), and healthy individuals (n = 79). Serum metabolomics was evaluated by ultra-high-performance liquid chromatography-mass spectrometry (UHPLC-MS) and the accuracy of the single candidate metabolite biomarkers was further assessed. Machine learning was used to generate the best diagnostic and predictive algorithms. Results Fifty-two serum metabolites were identified as markers of PSC, independent of age, biological sex, cirrhosis, UC, or ursodeoxycholic acid (UDCA) treatment. A diagnostic model based on only six lipids distinguished PSC patients from healthy controls with high accuracy (AUC 0.952 discovery, 0.918 validation), independently of the levels of transaminases or cholestasis markers (i.e., GGT, AP, bilirubin) in blood. Subgroup analyses were performed in PSC patients with and without inflammatory bowel disease (IBD), confirming the model’s consistent performance across both subgroups when compared with their respective control groups – UC and healthy controls (AUC 0.959 and 0.939, respectively). The PSC model also confirmed its diagnostic performance in patients with established PSC-CCA or progression to CCA within 2 years, when compared to UC and healthy controls, showing AUC values ranging from 0.911 to 0.976. Additionally, 20 metabolites were significantly altered in PSC patients with CCA (PSC-CCA), regardless of demographics, cirrhosis, UDCA treatment, IBD status, or CCA subtype, and independently of serum transaminases and cholestatic markers levels. A model incorporating six lipids accurately identified PSC-CCA cases compared to PSC patients (AUC = 0.912 discovery; 0.896 validation), showing excellent performance in early-stage tumor detection (AUC 0.921) and outperforming CA19-9 (AUC 0.708). Importantly, the model retained high accuracy even in CCA patients with low CA19-9 levels (AUC 0.905) and in PSC patients who developed CCA within a year of clinical diagnosis (AUC 0.792). Conclusion The PSC and PSC-CCA blood tests provide a non-invasive approach for diagnosing PSC and PSC-CCA, addressing an important need in this population. Their integration into clinical practice could enhance risk stratification, early detection, personalized surveillance, and treatment decision-making in PSC patients.

Abstract Background and Aims Cholangiocarcinoma (CCA) is a rare and aggressive malignancy originating from the bile ducts, characterized by a poor prognosis and limited treatment options. Potentially curative interventions include surgical resection with negative margins (R0) and liver transplantation. However, despite these treatments, the likelihood of post-surgical recurrence remains high, with 50–70% of patients experiencing disease recurrence within five years. This highlights the urgent need for reliable prognostic biomarkers to guide clinical decision-making and personalize postoperative care. Numerous prognostic biomarkers identified in tumor tissue for CCA have been proposed, but many studies suffer from limitations such as single-center designs, small patient cohorts, and semi-quantitative techniques such as immunohistochemistry. These methods often rely on observer interpretation and antibody specificity, which can compromise objectivity and reproducibility. To overcome these limitations, we aimed to identify and validate robust quantitative prognostic biomarkers for CCA by analyzing tumor mRNA expression, integrating them using machine learning (ML), and developing a web-based tool to predict tumor recurrence and overall survival (OS). Method A systematic literature review was conducted to identify candidate prognostic tissue biomarkers for CCA, which were further validated using Cox proportional hazards (PH) OS analyses in five independent transcriptomic cohorts. An international multicenter cohort of 221 patients undergoing tumor resection was assembled, and tumor mRNA expression was analyzed using high-throughput TaqMan OpenArray RT-qPCR. Associations between clinical and molecular features and recurrence-free survival (RFS) and OS were assessed using Cox PH analyses. Six ML survival models were trained and evaluated using nested cross-validation, followed by feature reduction. Shapley Additive exPlanations (SHAP) values were applied to assess feature importance and enhance model interpretability. Results Among 496 candidate CCA prognostic biomarkers identified from the literature, 52 showed prognostic value in Cox PH analyses across transcriptomic cohorts. In the multicenter validation cohort, integrative Cox PH analyses incorporating clinical variables and gene expression identified 11 genes significantly associated with RFS and 25 with OS. The 11 RFS-associated genes, combined with five clinical variables, were used to train six ML survival models, among which the random survival forest (RSF) model demonstrated the highest predictive accuracy. Following training of RSF models across all combinations of four genes and five clinical variables, and subsequent feature importance–based selection, a final model incorporating three genes (FSCN1, LDHA, and SLC2A1) and four clinical variables (CCA subtype, resection margin status, biological sex, and age at surgery) achieved a testing time-dependent AUC of 0.82. This model significantly stratified patients into high- and low recurrence-risk groups, with a median RFS (mRFS) of 8 months and 70 months, respectively. In addition, an OS prediction model using the same feature set achieved a testing AUC of 0.775 and significantly stratified patients according to 5-year OS risk, with a median OS (mOS) of 23 months in the high-risk group and 77 months in the low-risk group. Conclusion We identified and validated a robust panel of prognostic tissue biomarkers in patients with resected CCA. Integration of these biomarkers with clinical variables into ML-based prognostic models enabled accurate prediction of RFS and OS. The resulting web-based tool allows clinicians to input RT-qPCR results for the validated biomarkers and obtain precise, individualized prognostic predictions for postoperative recurrence and survival.