Fosså, Alexander

Abstract Castleman disease (CD) describes a group of rare lymphoproliferative disorders that exhibit a wide range of symptomatology and degree of lymphadenopathy, particularly across the 2 forms of CD with unknown etiology, unicentric CD (UCD), and human herpesvirus-8–negative/idiopathic multicentric CD (iMCD). Whereas UCD cases typically present with localized lymphadenopathy and mild symptoms, iMCD involves multicentric lymphadenopathy and cytokine storm–driven symptoms with 3 recognized clinical phenotypes. Increasingly, there are anecdotal reports of cases that do not fit into this framework, but these cases have not been systematically described. Herein, we use the ACCELERATE natural history registry to characterize the spectrum of CD based on disease features, symptomatology, and severity. Our results characterize a cohort of 179 CD cases, which were reviewed and confirmed by an expert panel of clinicians and hematopathologists. We show that patients with CD present on a continuous spectrum of clinical phenotypes, and we describe oligocentric CD (OligoCD), an intermediate phenotype that does not fit the criteria for UCD or iMCD. These cases tend to have “oligocentric” lymphadenopathy (median [interquartile range] regions of lymphadenopathy, 3.0 [2.0-4.0]) in a regional pattern and exhibit a mild clinical phenotype that is more similar to UCD than iMCD. We also show that patients with OligoCD are inconsistently categorized as UCD vs iMCD, highlighting the need for this characterization. Future data collected through ACCELERATE may further elucidate the natural history and risk profile of these patients.

PURPOSE Patients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS). PATIENTS AND METHODS This study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort). RESULTS In total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis. CONCLUSION The new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.