Machine Learning-Based Survival Prediction Models for Progression-Free and Overall Survival in Advanced-Stage Hodgkin Lymphoma

Abstract

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.

FIG 1.

CONSORT diagram of patient flow in the development and validation cohorts. ABVD, doxorubicin, bleomycin, vinblastine, and dacarbazine; BEACOPP, bleomycin, etoposide, doxorubicin hydrochloride, cyclophosphamide, vincristine, procarbazine, and prednisone; HL, Hodgkin lymphoma; IIBX, Ann Arbor stage II with B-symptoms and extranodal involvement.

FIG 2.

(A) Time-varying AUC for predicting OS and PFS for the ML model, the IPS-7, IPS-3, and A-HIPI. For the development cohort, the calculations for the ML model were performed by pooling predictions from each validation set in the cross-validation scheme. (B) Time-varying AUC for predicting OS and PFS for the ML model, the IPS-7, IPS-3, and A-HIPI in the validation cohort. A-HIPI, advanced-stage Hodgkin lymphoma international prognostic index; IPS, International Prognostic Score; ML, machine learning; OS, overall survival; PFS, progression-free survival.

FIG 3.

(A) Kaplan-Meier estimates of OS and PFS for high-risk patients (IPS-7, 5-7) and the same number of patients with the lowest predicted probability according to the ML model and the A-HIPI in the development cohort. (B) Kaplan-Meier estimates of OS and PFS for high-risk patients (IPS-7, 5-7) and the same number of patients with the lowest predicted probability according to the ML model in the validation cohort. A-HIPI, advanced-stage Hodgkin lymphoma international prognostic index; IPS, International Prognostic Score; ML, machine learning; OS, overall survival; PFS, progression-free survival.