Key result
A CART analysis model using RRT, blood urea nitrogen, hematocrit, and alanine transaminase predicted >3 months post-transplant survival with 83% accuracy, 95% sensitivity, and 76% specificity.
Why the study?
Can CART analysis accurately predict which infants listed for heart transplantation will survive at least 3 months post-transplantation?
Observational (n=48)
Can CART analysis accurately predict which infants listed for heart transplantation will survive at least 3 months post-transplantation?
CART analysis can generate accurate prediction models for early post-transplant survival in small populations of infants listed for heart transplantation, identifying factors like RRT and ECLS use as high-risk.
Answers are grounded in this paper and cite their sources.
May aid risk stratification in infant heart transplant candidates; leaves open need for prospective validation before clinical use.
Infants listed for heart transplantation experience high waitlist and early post-transplant mortality, and thus, optimal allocation of scarce donor organs is required. Unfortunately, the creation and validation of multivariable regression models to identify risk factors and generate individual-level predictions are challenging. We sought to explore the use of data mining methods to generate a prediction model. CART analysis was used to create a model which, at the time of listing, would predict which infants listed for heart transplantation would survive at least 3 months post-transplantation. A total of 48 infants were included; 13 died while waiting, and six died within 3 months of heart transplant. CART analysis identified RRT, blood urea nitrogen, and hematocrit as terminal nodes with alanine transaminase as an intermediate node predicting death. No patients listed on RRT (n = 10) survived and only three of 12 (25%) patients listed on ECLS survived >3 months post-transplant. CART analysis overall accuracy was 83%, with sensitivity of 95% and specificity 76%. This study shows that CART analysis can be used to generate accurate prediction models in small patient populations. Model validation will be necessary before incorporation into decision-making algorithms used to determine transplant candidacy.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2017) conducted an observational in Infants listed for heart transplantation (n=48). Risk factors (RRT, blood urea nitrogen, hematocrit, alanine transaminase) was evaluated on Survival at least 3 months post-transplantation. A CART analysis model using RRT, blood urea nitrogen, hematocrit, and alanine transaminase predicted >3 months post-transplant survival with 83% accuracy, 95% sensitivity, and 76% specificity.
Synapse has enriched 10 related papers. Consider them for comparative context: