ABSTRACT
Valvular Heart Disease (VHD) is a known late complication of radiotherapy for childhood cancer (CC), and identifying high-risk survivors correctly remains a challenge. This paper focuses on the distribution of the radiation dose absorbed by heart tissues. We propose that a dosiomics signature could provide insight into the spatial characteristics of the heart dose associated with a VHD, beyond the already-established risk induced by high doses. We analyzed data from the 7670 survivors of the French Childhood Cancer Survivors' Study (FCCSS), 3902 of whom were treated with radiotherapy. In all, 63 (1.6%) survivors that had been treated with radiotherapy experienced a VHD, and 57 of them had heterogeneous heart doses. From the heart-dose distribution of each survivor, we extracted 93 first-order and spatial dosiomics features. We trained random forest algorithms adapted for imbalanced classification and evaluated their predictive performance compared to the performance of standard mean heart dose (MHD)-based models. Sensitivity analyses were also conducted for sub-populations of survivors with spatially heterogeneous heart doses. Our results suggest that MHD and dosiomics-based models performed equally well globally in our cohort and that, when considering the sub-population having received a spatially heterogeneous dose distribution, the predictive capability of the models is significantly improved by the use of the dosiomics features. If these findings are further validated, the dosiomics signature may be incorporated into machine learning algorithms for radiation-induced VHD risk assessment and, in turn, into the personalized refinement of follow-up guidelines.
ABSTRACT
Background: Childhood cancer survivors (CCS) are at an elevated risk of developing both a second malignant neoplasm (SMN) and cardiac disease. Objectives: This study sought to assess the excess of occurrence of cardiac disease after a SMN among CCS. Methods: Analyses included 7,670 CCS from the French Childhood Cancer Survivors Study cohort diagnosed between 1945 and 2000. To account for the time dependence of the occurrence of a SMN, we employed a landmark approach, considering an additive regression model for the cumulative incidence of cardiac disease. We estimated the effect of a SMN on the instantaneous risk of cardiac disease using a proportional cause-specific hazard model, considering a SMN as a time-dependent exposure. In both models, we adjusted for demographic and treatment information and considered death as a competing event. Results: In 7,670 CCS over a median follow-up of 30 years (IQR: 22-38 years), there were 378 cases of cardiac disease identified, of which 49 patients experienced a SMN. Patients who survived 25 years after their childhood cancer diagnosis and had a SMN in that time frame had a significantly increased cumulative incidence of cardiac disease, which was 3.8% (95% CI: 0.5% to 7.1%) higher compared with those without a SMN during this period. No SMN-induced excess of cardiac disease was observed at subsequent landmark times. SMNs were associated with a 2-fold increase (cause-specific HR: 2.0; 95% CI: 1.4-2.8) of cardiac disease. Conclusions: The occurrence of a SMN among CCS is associated with an increased risk of cardiac disease occurrence and risk at younger ages.
