Alkhatib, Yaser

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.

Heparin-induced thrombocytopenia (HIT) is an immune complication of heparin therapy caused by antibodies to complexes of platelet factor 4 (PF4) and heparin. Pathogenic antibodies to PF4/heparin bind and activate platelets to propagate a hypercoagulable state culminating in life-threatening thrombosis. The serotonin-release assay (SRA) is considered the gold-standard test to diagnose HIT. However, the sensitivity of the SRA was questioned with reported cases of clinical diagnosis of HIT and negative SRA. Herein, we present the utility of platelet factor 4-dependent P-selectin expression assay (PEA) in diagnosing HIT in a patient with thrombocytopenia and recurrent thrombosis who repeatedly tested negative with SRA.

Background: Thrombocytopenia is a frequently encountered laboratory abnormality and a common reason for hematology referrals. Workup for thrombocytopenia is not standardized and frequently does not follow an evidence-based algorithm. We conducted a systematic analysis to evaluate the laboratory testing and outcomes of patients evaluated for thrombocytopenia at hematology clinics in a tertiary referral center between 2013 and 2016. Patient and methods: We performed a comprehensive chart review for patients evaluated for thrombocytopenia during the study period. Patients were followed for 1 year from the initial hematology evaluation and assessed for the development of a hematologic malignancy, rheumatologic, or infectious diseases among other clinical outcomes. Results: We evaluated 472 patients with a median (range) age of 61 (17–94) years. The majority (63.8%) had mild thrombocytopenia. Within 1 year of follow-up, 14 patients (3.0%) were diagnosed with a hematologic malignancy. A higher likelihood of developing a hematologic malignancy was noted in patients with concurrent leukopenia (hazard ratio [HR] 9.97, 95% confidence interval [CI] 3.28–30.32, p < .01) and increasing age (HR per 10-year deciles 1.52, 95% CI 1.03–2.25, p = .03). In patients with asymptomatic isolated mild thrombocytopenia, laboratory testing did not reveal any significant positive findings and patients did not receive any new major diagnosis during the follow-up period. Conclusion: Our findings provide basis and call for development of an evidence-based algorithmic approach for evaluation of patients with thrombocytopenia, testing, and referrals. It also supports a conservative approach mainly driven by physical exam signs, symptoms, and other laboratory findings for patients with isolated mild thrombocytopenia.