Key result
Machine learning model using preimplantation clinical factors predicts pediatric VAD mortality with 0.95 AUC.
Why the study?
A contemporary risk assessment tool for mortality on pediatric VADs using readily available preimplantation clinical data was needed.
Can a machine learning-based risk prediction model accurately estimate mortality risk in pediatric ventricular assist device candidates?
Observational
Yes
Can a machine learning-based risk prediction model accurately estimate mortality risk in pediatric ventricular assist device candidates?
A novel machine learning-based prognostic tool using preimplantation clinical data demonstrates excellent discrimination (AUC 0.95) for predicting mortality in pediatric VAD candidates.
Answers are grounded in this paper and cite their sources.
May aid preimplant risk stratification in pediatric VAD candidates; leaves open need for prospective validation before clinical adoption.
We sought to develop a contemporary risk assessment tool for use in pediatric ventricular assist device (VAD) candidates to estimate risk for mortality on the device using readily available preimplantation clinical data. Training and testing datasets were created from Advanced Cardiac Therapies Improving Outcomes Network (ACTION) registry data on patients supported with a VAD from 2012 to 2021. Potential risk factors for mortality were assessed and incorporated into a simplified risk prediction model utilizing an open-source, gradient-boosted decision tree machine learning library, known as random forest. Predictive performance was assessed by the area under the receiver operating characteristic curve in the testing dataset. Nine significant risk factors were included in the final predictive model which demonstrated excellent discrimination with an area under the curve of 0.95. In addition to providing a framework for establishing pediatric-specific risk profiles, our model can help inform team expectations, guide optimal patient selection, and ultimately improve patient outcomes.
No takes yet. Share an insight, caveat, or question.
Boucek et al. (2023) conducted an observational in Pediatric ventricular assist device (VAD) candidates. Preimplantation clinical risk factors was evaluated on Mortality on the device (AUC 0.95). A random forest machine learning model incorporating nine preimplantation clinical risk factors demonstrated excellent discrimination for predicting mortality in pediatric VAD candidates (AUC 0.95).
Synapse has enriched 10 related papers. Consider them for comparative context: