Informatics Tools to Implement Late Cardiovascular Risk Prediction
Modeling for Population Management of High-Risk Childhood Cancer
Survivors
Abstract
Background: Clinical informatics tools to integrate data from
multiple sources have the potential to catalyze population health
management of childhood cancer survivors at high risk for late heart
failure through the implementation of previously validated risk
calculators. Methods: The Oklahoma cohort (n=365) harnessed
data elements from Passport for Care (PFC) and the Duke cohort (n=274)
integrated cancer registry and electronic health record data, using
standard query language, to automatically extract chemotherapy exposures
for survivors <18 years old at diagnosis. The Childhood Cancer
Survivor Study (CCSS) late cardiovascular risk calculator was
implemented and risk groups for heart failure were compared to the
Children’s Oncology Group (COG) Long-Term Follow-up Guidelines.
Results: The Oklahoma and Duke cohorts both observed good
overall concordance between the CCSS and COG risk groups for late heart
failure with weighted Kappa statistics of 0.70 and 0.75, respectively.
Low-risk groups showed excellent concordance (Kappa >0.9).
Moderate and high-risk groups showed moderate concordance (Kappa
0.44-0.60 across both cohorts). In the Oklahoma cohort, adolescents at
diagnosis were significantly less likely to receive guideline-adherent
care for echocardiogram surveillance compared with survivors
<13 years old at diagnosis (OR 0.22; 95% CI 0.10-0.49).
Conclusions: Clinical informatics tools represent a feasible
approach to leverage discrete data elements regarding key treatment
exposures from PFC or the EHR to successfully implement previously
validated late cardiovascular risk prediction models on a population
health level. Real-world evidence on the concordance of CCSS, COG, and
IGHG risk groups promises to refine current guidelines and identify
inequities in guideline-adherent care.