Background/Objectives: Liver transplantation may provide prolonged survival in fibrolamellar carcinoma (FLC), but the frequency and timing of post-transplant recurrence, and the basis for patient selection, remain poorly defined. We described the course from listing through long-term follow-up and tested whether routine pretransplant measurements distinguished the recurrence risk. Methods: Scientific Registry of Transplant Recipients data identified separate listing and first-transplant cohorts during 2002–2025. Competing-risk analyses assessed waiting-list outcomes and reported recurrence of the pretransplant tumour. Exploratory recurrence models were internally validated with 500 patient bootstrap samples, with performance assessed only in omitted recipients. Recorded explant tumour extent was examined in the registry’s liver explant file. Results: This study included 61 listed candidates and 51 first-transplant recipients; 42 recipients had a pathology-supported discharge diagnosis of FLC. One-year incidence of transplantation was 76.5% (95% CI 65.9–86.6). After a median potential follow-up of 8.1 years, five-year post-transplant survival was 63.3% (95% CI 46.4–76.2). Seventeen recurrences were reported and the three-year cumulative incidence was 26.1% (95% CI 13.9–39.1). Malignancy was the recorded primary cause in 13 of 23 deaths. Laboratory-component and compact clinical models had mean three-year validation areas under the curve of 0.571 and 0.507, and neither reduced prediction error relative to its matched cohort-average prediction. Conclusions: Transplantation was followed by prolonged survival in selected patients with FLC, although reported recurrence was common and sometimes late. Routine pretransplant variables did not identify reproducible recurrence-risk groups. With 51 recipients and 17 recurrences, these estimates are imprecise and the prediction analyses are exploratory; selection should remain multidisciplinary while tumour extent, treatment response and biological markers are evaluated prospectively.

Background/Objectives: Machine-learning (ML) models are promoted for predicting delayed graft function (DGF) and graft survival after kidney transplantation; we examined whether they outperform regression and how well either has been validated. Methods: We searched PubMed/MEDLINE, Embase, and Web of Science through 28 June 2026, searched citations for named DGF models, extracted data in duplicate, assessed risk of bias using the Prediction Model Risk of Bias ASsessment Tool (PROBAST), and pooled only external validations of the same published model. Results: We included 217 reports (145 on DGF and 91 on graft survival, 19 on both); across seven external cohorts, the Irish 2010 DGF model had a pooled area under the curve (AUC) of 0.73 (95% confidence interval 0.69–0.77), the median difference in AUC or C-statistic between ML and regression in 28 same-cohort comparisons was 0.01 (interquartile range −0.02 to 0.03), and 208 of the 212 non-pediatric reports were at high risk of bias. Conclusions: ML has not been shown to predict DGF or graft survival better than regression, and the comparisons are too heterogeneous to show that it is worse; a model should inform organ acceptance or recipient counseling only after it has shown discrimination and calibration in an independent cohort.