Predicting Absolute Risk of First Relapse in Classical Hodgkin Lymphoma by Incorporating Contemporary Treatment Effects

Abstract

Background/Objectives: There is a need for prediction models which enable weighing benefits against risks of different treatment strategies for individual Hodgkin lymphoma (HL) patients. Therefore, we aimed to predict absolute risk of progression, first relapse or death (PRD) with and without incorporating HL treatment. Methods: The prognostic and treatment information of 2343 patients treated for classical HL at ages 15-60 years between 2008 and 2018 in the Netherlands was used to predict absolute risk of PRD up to 5 years after diagnosis using Cox proportional hazard models allowing for time-varying coefficients. Models were externally validated in 1675 patients treated for classical HL in Denmark between 2000 and 2018. Results: In early stages, gender, leukocyte, and lymphocyte counts were associated with risk of PRD. Additionally, receiving >4 cycles of ABVD (doxorubicin, bleomycin, vinblastine, and dacarbazine) or ABVD plus radiotherapy predicted lower risk of relapse compared with receiving ≤4 cycles of ABVD. In advanced stages, age, albumin and leukocyte counts predicted PRD risk. Receiving (escalated) BEACOPP (bleomycin, etoposide, doxorubicin, cyclophosphamide, vincristine, procarbazine, prednisone) predicted lower PRD risk compared to ABVD. In Danish patients treated between 2008 and 2018, adding treatment information improved 5-year Inverse Probability of Censoring Weighted (IPCW) Area Under the Curve (AUC) values from 0.63 (95% Confidence Interval (CI): 0.55-0.72) to 0.71 (95% CI: 0.63-0.79) in early stages (p-value = 0.04) and from 0.59 (95% CI: 0.52-0.65) to 0.62 (95% CI: 0.55-0.68) in advanced stages (p-value = 0.33). Conclusions: We developed well calibrated models with reasonable discrimination, not only incorporating pre-treatment prognostic factors but also treatment effect enabling the prediction of absolute risk of first relapse/progression.

Keywords: Hodgkin lymphoma; absolute risk; prediction; relapse; validation.

Figure 1

ROC-Calibration plots of early-stage models for progression-free survival on Danish HL patients. ROC: receiver operating characteristic. HL: Hodgkin lymphoma.

Figure 2

ROC-Calibration plots of advanced-stage models for progression-free survival on Danish HL patients. ROC: receiver operating characteristic. HL: Hodgkin lymphoma. A-HIPI: Advanced-Stage Hodgkin International Prognostic Index. IPS: International Prognostic Index.

Figure 3

Absolute risk estimates up to 5 years after diagnosis based on a treatment-based model for early-stage HL patients. HL: Hodgkin lymphoma. The data are represented at the 1st and 3rd quartile cut-off values of age in years, leukocyte count ($\times {10}^9$/L), and lymphocyte count ($\times {10}^9$/L).

Figure 4

Absolute risk estimates up to 5 years after diagnosis based on treatment-based model for advanced stage HL patients. HL: Hodgkin lymphoma. The data are represented at the 1st and 3rd quartile cut-off values of age in years, albumin in gr/L, and leukocyte count ($\times {10}^9$/L).