<p>Tetralogy of Fallot (TOF) repair is associated with excellent operative survival. However, a subset of patients experiences post-operative complications, which can significantly alter the early and late post-operative course. We utilized a machine learning approach to identify risk factors for post-operative complications after TOF repair. We conducted a single-center prospective cohort study of children &lt;2 years of age with TOF undergoing surgical repair. The outcome was occurrence of post-operative cardiac complications, measured between TOF repair and hospital discharge or death. Predictors included patient, operative, and echocardiographic variables, including pre-operative right ventricular strain and fractional area change as measures of right ventricular function. Gradient-boosted quantile regression models (GBM) determined predictors of post-operative complications. Cross-validated GBMs were implemented with and without a filtering stage non-parametric regression model to select a subset of clinically meaningful predictors. Sensitivity analysis with gradient-boosted Poisson regression models was used to examine if the same predictors were identified in the subset of patients with at least one complication. Of the 162 subjects enrolled between March 2012 and May 2018, 43 (26.5%) had at least one post-operative cardiac complication. The most frequent complications were arrhythmia requiring treatment ( = 22, 13.6%), cardiac catheterization ( = 17, 10.5%), and extracorporeal membrane oxygenation (ECMO) ( = 11, 6.8%). Fifty-six variables were used in the machine learning analysis, of which there were 21 predictors that were already identified from the first-stage regression. Duration of cardiopulmonary bypass (CPB) was the highest ranked predictor in all models. Other predictors included gestational age, pre-operative right ventricular (RV) global longitudinal strain, pulmonary valve Z-score, and immediate post-operative arterial oxygen level. Sensitivity analysis identified similar predictors, confirming the robustness of these findings across models. Cardiac complications after TOF repair are prevalent in a quarter of patients. A prolonged surgery remains an important predictor of post-operative complications; however, other perioperative factors are likewise important, including pre-operative right ventricular remodeling. This study identifies potential opportunities to optimize the surgical repair for TOF to diminish post-operative complications and secure improved clinical outcomes. Efforts toward optimizing pre-operative ventricular remodeling might mitigate post-operative complications and help reduce future morbidity.</p>

<p><strong>Background</strong> Despite excellent operative survival, correction of tetralogy of Fallot frequently is accompanied by residual lesions that may affect health beyond the incident hospitalization. Measuring resource utilization, specifically cost and length of stay, provides an integrated measure of morbidity not appreciable in traditional outcomes.</p>

<p><strong>Methods and Results</strong> We conducted a retrospective cohort study, using de-identified commercial insurance claims data, of 269 children who underwent operative correction of tetralogy of Fallot from January 2004 to September 2015 with ≥2&nbsp;years of continuous follow-up (1) to describe resource utilization for the incident hospitalization and subsequent 2&nbsp;years, (2) to determine whether prolonged length of stay (&gt;7&nbsp;days) in the incident hospitalization was associated with increased subsequent resource utilization, and (3) to explore whether there was regional variation in resource utilization with both direct comparisons and multivariable models adjusting for known covariates. Subjects with prolonged incident hospitalization length of stay demonstrated greater resource utilization (total cost as well as counts of outpatient visits, hospitalizations, and catheterizations) after hospital discharge (&lt;0.0001 for each), though the number of subsequent operative and transcatheter interventions were not significantly different. Regional differences were observed in the cost of incident hospitalization as well as subsequent hospitalizations, outpatient visits, and the costs associated with each.</p>

<p><strong>Conclusions</strong> This study is the first to report short- and medium-term resource utilization following tetralogy of Fallot operative correction. It also demonstrates that prolonged length of stay in the initial hospitalization is associated with increased subsequent resource utilization. This should motivate research to determine whether these differences are because of modifiable factors.</p>