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 Telemonitoring on Health Status.

BACKGROUND: Although noninvasive telemonitoring in patients with heart failure does not reduce mortality or hospitalizations, less is known about its effect on health status. This study reports the results of a randomized clinical trial of telemonitoring on health status in patients with heart failure. METHODS AND RESULTS: Among 1521 patients with recent heart failure hospitalization randomized in the Tele-HF trial (Telemonitoring to Improve Heart Failure Outcomes), 756 received telephonic monitoring and 765 usual care. Disease-specific health status was measured with the Kansas City Cardiomyopathy Questionnaire (KCCQ) within 2 weeks of discharge and at 3 and 6 months. Repeated measures linear regression models were used to assess differences in KCCQ scores between patients assigned to telemonitoring and usual care over 6 months. The baseline characteristics of the 2 treatment arms were similar (mean age, 61 years; 43% female and 39% black). Over the 6-month follow-up period, there was a statistically significant, but clinically small, difference between the 2 groups in their KCCQ overall summary and subscale scores. The average KCCQ overall summary score for those receiving telemonitoring was 2.5 points (95% confidence interval, 0.38-4.67; P=0.02) higher than usual care, driven primarily by improvements in symptoms (3.5 points; 95% confidence interval, 1.18-5.82; P=0.003) and social function (3.1 points; 95% confidence interval, 0.30-6.00; P=0.03). CONCLUSIONS: Telemonitoring results in statistically significant, but clinically small, improvements in health status when compared with usual care. Given that the KCCQ was a secondary outcome, the benefits should be confirmed in future studies. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov/. Unique identifier: NCT00303212.