Search

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. Machine-Learning based advanced-stage Hodgkin lymphoma (aHL) prognosis surpasses International Prognostic Score, competes with aHL international prognostic index in overall survival and progression-free survival prediction. [ABSTRACT FROM AUTHOR]

Summary: We analysed a large cohort of Hodgkin lymphoma (HL) patients in order to characterize: (1) the pattern of late recurrence of lymphoid malignancies (LR) after initial treatment for HL over a 35‐year period; (2) the clinicopathological parameters influencing the risk of LR; and (3) the outcome of patients experiencing LR. We reviewed data of 3350 HL patients diagnosed in Denmark between 1982 and 2018 and registered in the Danish National Lymphoma Registry (LYFO). LR was defined as a recurrence of lymphoid malignancy at least five years after initial diagnosis. LR occurred in 58 patients, with a cumulative incidence at 10, 15 and 20 years of 2.7%, 4.0% and 5.4% respectively. LR was more frequently observed in patients with nodular lymphocyte‐predominant HL (NLPHL) [hazard ratio (HR) 4.5; 95% confidence interval (CI): 2.4–8.4, p < 0.001]. In classical HL (cHL) patients, older age and lymphocytopenia were risk factors for LR with HRs of 1.04 per additional year (95% CI: 1.02–1.06) and 5.6 (95% CI: 2.7–11.5) respectively. Mixed cellularity histological subtype was a risk factor for LR, but only in females, with a HR of 5.4 (95% CI: 1.4–20.4, p = 0.014). In contrast to what was observed in NLPHL, LR in cHL was associated with an almost threefold increased risk of death compared with patients in continuous complete remission. Approximately one fifth (22.4%) of patients with LR experienced a second relapse. [ABSTRACT FROM AUTHOR]