Machine Learning to Predict Interstage Mortality Following Single Ventricle Palliation: A NPC-QIC Database Analysis.

There is high risk of mortality between stage I and stage II palliation of single ventricle heart disease. This study aimed to leverage advanced machine learning algorithms to optimize risk-prediction models and identify features most predictive of interstage mortality. This study utilized retrospective data from the National Pediatric Cardiology Quality Improvement Collaborative and included all patients who underwent stage I palliation and survived to hospital discharge (2008-2019). Multiple machine learning models were evaluated, including logistic regression, random forest, gradient boosting trees, extreme gradient boost trees, and light gradient boosting machines. A total of 3267 patients were included with 208 (6.4%) interstage deaths. Machine learning models were trained on 180 clinical features. Digoxin use at discharge was the most influential factor resulting in a lower risk of interstage mortality (p < 0.0001). Stage I surgery with Blalock-Taussig-Thomas shunt portended higher risk than Sano conduit (7.8% vs 4.4%, p = 0.0002). Non-modifiable risk factors identified with increased risk of interstage mortality included female sex, lower gestational age, and lower birth weight. Post-operative risk factors included the requirement of unplanned catheterization and more severe atrioventricular valve insufficiency at discharge. Light gradient boosting machines demonstrated the best performance with an area under the receiver operative characteristic curve of 0.642. Advanced machine learning algorithms highlight a number of modifiable and non-modifiable risk factors for interstage mortality following stage I palliation. However, model performance remains modest, suggesting the presence of unmeasured confounders that contribute to interstage risk.

Impact of Digoxin Use on Interstage Outcomes of Single Ventricle Heart Disease (From a NPC-QIC Registry Analysis).

Digoxin has been associated with lower interstage mortality (ISM) following stage 1 palliation (S1P). Despite a substantial increase in digoxin use nationally, ISM has not declined. We aimed to determine the impact of digoxin on ISM in the current era. This study analyzed data from the National Pediatric Cardiology Quality Improvement Collaborative (NPC-QIC) registry. All patients who survived to hospital discharge following S1P were included. Comparisons were made between pre-specified eras (1: 2010-2015, 2: 2016-2019) based on digoxin use. ISM risk was estimated using the previously published NEONATE score (excluding digoxin). Multivariable Cox proportional hazard models assessed the impact of digoxin on ISM and freedom from unplanned readmission in era 2. A total of 1400 (46.8%) patients were included from era 1 and 1589 (53.2%) from era 2. Digoxin use (22.4% vs 61.7%, p < 0.001) and the proportion of high-risk patients (9.1% vs 20.3%, p < 0.001) increased across eras. There was no difference in predicted ISM risk between those who did vs did not receive digoxin in era 2 (p = 0.82). In era 2, digoxin use was independently associated with lower ISM (AHR 0.60, 95%CI 0.36 to 0.98, p = 0.043) and greater freedom from unplanned readmission (AHR 0.44, 95%CI 0.32 - 0.59, p < 0.001). In conclusion, digoxin is independently associated with lower ISM and greater freedom from interstage readmission. The lack of improvement in overall ISM in the current era may be secondary to a greater proportion of high-risk patients and/or disproportionately higher digoxin use in lower risk patients, who may not derive the same benefit.