Citations

Background Graft-versus-host disease (GVHD) remains a major determinant of morbidity and mortality following allogeneic hematopoietic stem cell transplantation (allo-HSCT). Existing GVHD prediction models demonstrate modest discrimination and limited generalizability, and calibration drift across external populations is rarely characterized despite its essential role in the clinical interpretability of predicted probabilities. Objectives To develop and externally validate an explainable machine learning framework for predicting acute and chronic GVHD and associated overall survival in patients with acute myeloid leukemia (AML), acute lymphoblastic leukemia (ALL), and myelodysplastic syndromes (MDS) undergoing allo-HSCT, and to systematically characterize calibration across heterogeneous external validation cohorts to inform deployment requirements. Study Design The model was developed on three publicly available registry-derived datasets (N = 2,509) and externally validated across six independent cohorts (N = 14,788) comprising adult and pediatric allo-HSCT recipients, including a regional Middle Eastern cohort (UAE and Jordan). A standardized preprocessing pipeline harmonized heterogeneous datasets. Gradient boosting models (CatBoost) were used for binary GVHD prediction; exploratory overall survival analysis used a Cox proportional hazards model with predicted acute GVHD risk as a covariate. Discrimination (AUROC with bootstrap 95% CI), calibration (logistic recalibration intercept and slope with analytical 95% CI), and feature importance (SHapley Additive exPlanations, SHAP) were assessed in training out-of-fold and all external cohorts. Results In internal validation, AUROC was 0.63 (95% CI 0.61–0.65) for acute GVHD and 0.72 (95% CI 0.70–0.74) for chronic GVHD. External validation demonstrated AUROC ranges of 0.51–0.57 (acute) and 0.54–0.64 (chronic), with consistent performance across disease subgroups despite substantial heterogeneity in transplant practices and feature availability. In exploratory survival analysis, the acute-GVHD-informed Cox model achieved a training-cohort C-index of 0.679 (95% CI 0.658–0.697); external C-indices ranged from 0.47–0.53. Calibration analysis identified systematic external risk overestimation (negative calibration intercept in 10 of 11 evaluable external cohort-target combinations) with heterogeneous slope drift requiring cohort-specific recalibration. Key predictors included recipient age, graft source, conditioning intensity, GVHD prophylaxis, and HLA match ratio. Conclusions An explainable, externally validated GVHD prediction framework was developed using heterogeneous registry-derived datasets, with systematic characterization of calibration drift across multiple external cohorts, an analysis rarely reported in prior GVHD prediction literature. Predictive performance was modest for acute GVHD and moderate for chronic GVHD, constrained by missing immunobiological variables and incomplete HLA characterization. Per-cohort recalibration is required before clinical deployment, with prospective validation and benchmarking against established GVHD risk scores identified as priority next steps.

Background/Objectives: Tumor-infiltrating lymphocyte (TIL) therapy is an important option for patients with metastatic melanoma progressing after standard systemic therapy, but real-world data on treatment delivery, toxicity monitoring, and immune recovery remain limited. We evaluated clinical outcomes, treatment tolerance, immune reconstitution, and cardiac biomarker dynamics across three Mayo Clinic sites. Methods: We retrospectively analyzed adults with metastatic melanoma who received lymphodepleting chemotherapy followed by TIL infusion and high-dose interleukin-2 (IL-2) between April 2024 and December 2025. Clinical outcomes, treatment delivery, and adverse events were assessed. Longitudinal immune monitoring included CD4 and CD8 T-cell counts, CD4:CD8 ratio, and immunoglobulin G (IgG) at baseline and follow-up. In a prespecified cardiac sub-cohort, high-sensitivity troponin (hs-Tn) was measured during IL-2 administration to evaluate associations with cardiac events and IL-2 interruption. Results: Thirty-six patients underwent TIL infusion. The objective response rate was 50.0%, including complete responses in 13.9%, and the disease control rate was 72.2%. Median progression-free survival was 3.61 months, and median overall survival was 12.94 months. M1d disease was associated with inferior overall survival on univariable analysis (HR 6.55, 95% CI 2.03–21.17; p = 0.002), with attenuation after multivariable adjustment. Receipt of ≥3 IL-2 doses was associated with longer overall survival on univariable analysis (HR 0.20, 95% CI 0.06–0.64; p = 0.007), but this association also attenuated after adjustment. Longitudinal immune monitoring demonstrated persistent CD4 lymphopenia through 6 months, sustained inversion of the CD4:CD8 ratio, and declining IgG at months 3 and 6. In the cardiac sub-cohort (24 patients; 87 IL-2 doses), post-dose hs-Tn ≥15 ng/L was associated with clinically significant cardiac events (OR 9.6, 95% CI 1.5–60.6; p = 0.016) and IL-2 interruption (OR 3.4, 95% CI 1.1–10.7; p = 0.036). For cardiac events, hs-Tn ≥15 ng/L had 100% sensitivity and 100% negative predictive value. Conclusions: In routine practice, TIL therapy was feasible and active in metastatic melanoma. M1d disease identified a subgroup with poor survival, peri-dose hs-Tn showed promise as a tool to support safer IL-2 delivery, and prolonged CD4 suppression with IgG decline suggests that recovery after TIL therapy extends beyond initial hematologic reconstitution. These findings support prospective validation of biomarker-guided IL-2 monitoring and extended post-treatment immune surveillance.

Background Primary aldosteronism (PA), a renin-independent state of aldosterone excess, is associated with excess risk of stroke, myocardial infarction, atrial fibrillation, heart failure, and chronic kidney disease compared with essential hypertension. Emerging evidence suggests that renin-independent aldosterone excess exists on a continuum rather than as a dichotomous disease state, including subclinical primary aldosteronism (sPA), even in normotensive individuals. Whether sPA is associated with major adverse cardiovascular events (MACE) prior to overt hypertension remains incompletely characterized. Objective To synthesize available evidence linking renin suppression and mild aldosterone excess to cardiovascular outcomes. Methods A narrative review of the literature was conducted using PubMed/MEDLINE, the Cochrane Library, and Web of Science from inception through May 2025, to identify cohort studies evaluating renin phenotype, aldosterone levels, and cardiovascular outcomes. Results Suppressed renin and higher aldosterone levels, even within conventionally normal ranges, are associated with incident hypertension, left ventricular hypertrophy (LVH), atrial fibrillation, and cardiovascular events. In overt PA, significantly higher rates of cardiovascular diseases have been observed compared with blood pressure-matched essential hypertension. Emerging population-based data suggest a graded cardiovascular risk extending below traditional diagnostic thresholds. Conclusion Biochemical phenotypes consistent with sPA may represent an early cardiometabolic state associated with elevated risk of MACE, even before overt PA criteria are met. The absence of standardized diagnostic thresholds and randomized interventional data currently limits clinical translation. Prospective trials evaluating renin-guided screening and early mineralocorticoid receptor antagonism are needed to determine whether intervention at the subclinical stage reduces long-term cardiovascular harm.

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.

Background: A diagnosis of cancer creates a stressful situation owing to the uncertainties related to the thought of possible suffering from complications associated with treatment toxicities, the fear of not responding to the prescribed treatment, or death. The prevalence of mental health disorders is relatively higher in cancer patients vis-à-vis the general population. Methods: We performed a retrospective cohort study to evaluate the impact of mental health disorders on outcomes of relapsed and/or refractory diffuse large B-cell lymphoma (DLBCL) treated with chimeric antigen receptor T-cell (CAR T-cell) therapy using data from the TriNetX research network. Results: A total of 1587 patients met the inclusion criteria (858 with a mental health diagnosis and 729 without). After propensity score matching for age and gender, 1320 patients were included in the analysis (660 in each group). The 1-year OS was higher in patients without a mental health disorder (76.0% versus 69.4%, P = 0.004). Patients with mental health disorders had a higher incidence of cytokine release syndrome (all grades) compared with those without (35.5% versus 27.6%, P < 0.001) and immune effector cell-associated neurotoxicity syndrome (all grades) (16.8% versus 10.1%, P < 0.001). Conclusions: These findings emphasize the importance of thorough psychiatric evaluation and management in patients receiving CAR T-cell therapy. Patients with mental health disorders may need significant assistance with coordinating medical services to better adhere to required care management. Future studies are needed to help determine whether preventive and real-time mental health interventions can favorably impact outcomes of these patients.

A 70-year-old woman with a past medical history of breast cancer is undergoing surveillance. She also had a history of repeated blood transfusions for refractory anemia caused by treated marrow metastatic disease. Laboratory tests showed elevated AST (50 U/L) and ALT (115 U/L). 99m Tc MDP bone scintigraphy revealed intense diffuse splenic uptake. No splenic calcifications or infarcts were found on contrast-enhanced CT. MRI demonstrated signal dropout on in-phase sequences and marked T2 hypointensity of the spleen and liver, without focal splenic lesions, suggesting transfusion-related secondary hemosiderosis. Iron overload should be considered when diffuse splenic uptake is observed on bone scintigraphy.

Objectives To evaluate biochemical recurrence‐free survival (BRFS) and metastasis‐free survival (MFS) as potential intermediate clinical endpoints (ICEs) for overall survival (OS) in patients undergoing salvage radical prostatectomy (sRP). Patients and Methods Evaluable patients were selected from a retrospective dataset, resulting in a cohort of 879 patients with recurrent, non‐metastatic, hormone‐sensitive prostate cancer treated with sRP at 13 centres. ICE surrogacy was evaluated using a two‐stage approach: (i) at the individual‐patient level by fitting Clayton copula models and estimating Kendall's ( >0.7 indicating a strong association) and (ii) at the centre level, by fitting weighted linear regression of 5‐year OS on 3‐year BRFS and MFS. Results The two‐step analysis included 759 patients for BRFS (366 events) and 476 for MFS (137 events), with median follow‐up of 37 months (95% confidence interval [CI] 36–42 months) and 34 months (95% CI 31–37 months), respectively. At the individual‐patient level, MFS showed a strong association with OS (Kendall's 0.85, 95% CI 0.82–0.88), which was not observed for BRFS (Kendall's 0.63, 95% CI 0.56–0.69). At the centre level, neither 3‐year BRFS ( R 2 = 0.15; slope = 0.34, P = 0.2) nor 3‐year MFS ( R 2 = 0.21; slope = 0.26, P = 0.14) predicted 5‐year OS with sufficient explanatory power. Limitations include the fact that centre‐level analysis was based on single‐arm associations rather than on treatment‐effect surrogacy across arms, and retrospective data collection. Conclusions The BRFS should not be used as a surrogate endpoint in the sRP setting. MFS requires further validation in future prospective studies to confirm its association with OS. Patient‐reported outcomes, such as quality‐of‐life and treatment‐related toxicity, should be considered in parallel with OS.