Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations.
José Castela ForteHubert E MungroopFred de GeusMaureen L van der GrintenHjalmar R BoumaVille PettiläThomas W L ScheerenMaarten W N NijstenMassimo A MarianiIwan C C van der HorstRobert H HenningMarco A WieringAnne H EpemaPublished in: Scientific reports (2021)
Despite having a similar post-operative complication profile, cardiac valve operations are associated with a higher mortality rate compared to coronary artery bypass grafting (CABG) operations. For long-term mortality, few predictors are known. In this study, we applied an ensemble machine learning (ML) algorithm to 88 routinely collected peri-operative variables to predict 5-year mortality after different types of cardiac operations. The Super Learner algorithm was trained using prospectively collected peri-operative data from 8241 patients who underwent cardiac valve, CABG and combined operations. Model performance and calibration were determined for all models, and variable importance analysis was conducted for all peri-operative parameters. Results showed that the predictive accuracy was the highest for solitary mitral (0.846 [95% CI 0.812-0.880]) and solitary aortic (0.838 [0.813-0.864]) valve operations, confirming that ensemble ML using routine data collected perioperatively can predict 5-year mortality after cardiac operations with high accuracy. Additionally, post-operative urea was identified as a novel and strong predictor of mortality for several types of operation, having a seemingly additive effect to better known risk factors such as age and postoperative creatinine.
Keyphrases
- aortic valve
- coronary artery bypass grafting
- machine learning
- aortic stenosis
- left ventricular
- risk factors
- mitral valve
- transcatheter aortic valve replacement
- ejection fraction
- aortic valve replacement
- coronary artery disease
- transcatheter aortic valve implantation
- percutaneous coronary intervention
- big data
- cardiovascular events
- artificial intelligence
- end stage renal disease
- newly diagnosed
- neural network
- heart failure
- convolutional neural network
- type diabetes
- chronic kidney disease
- patients undergoing
- acute coronary syndrome
- patient reported outcomes
- high intensity
- prognostic factors
- clinical practice
- data analysis