Derivation and Validation of a General Predictive Model for Long Term Risks for Mortality and Invasive Interventions in Congenital and Acquired Cardiac Conditions Encountered in the Young

Accurate prognostic assessment is a key driver of clinical decision making in heart disease in the young (HDY). This investigation aims to derive, validate, and calibrate multivariable predictive models for time to surgical or catheter-mediated intervention (INT) and for time to death in HDY. 4108 unique subjects were prospectively and consecutively enrolled, and randomized to derivation and validation cohorts. Total follow-up was 26,578 patient-years, with 102 deaths and 868 INTs. Accelerated failure time multivariable predictive models for the outcomes, based on primary and secondary diagnoses, pathophysiologic severity, age, sex, genetic comorbidities, and prior interventional history, were derived using piecewise exponential methodology. Model predictions were validated, calibrated, and evaluated for sensitivity to changes in the independent variables. Model validity was excellent for predicting mortality and INT at 4 months, 1, 5, 10, and 22 years (areas under receiver operating characteristic curves 0.813–0.915). Model calibration was better for INT than for mortality. Age, sex, and genetic comorbidities were significant independent factors, but predicted outcomes were most sensitive to variations in composite predictors incorporating primary diagnosis, pathophysiologic severity, secondary diagnosis, and prior intervention. Despite 22 years of data acquisition, no significant cohort effects were identified in which predicted mortality and intervention varied by study entry date. A piecewise exponential model predicting survival and freedom from INT is derived which demonstrates excellent validity, and performs well on a clinical sample of HDY outpatients. Objective model-based predictions could educate both patient and provider, and inform clinical decision making in HDY.