TY - JOUR
T1 - Machine Learning Prediction Models for In-Hospital Mortality After Transcatheter Aortic Valve Replacement
AU - Hernandez-Suarez, Dagmar F.
AU - Kim, Yeunjung
AU - Villablanca, P.
AU - Gupta, Tanush
AU - Wiley, Jose
AU - Nieves-Rodriguez, Brenda G.
AU - Rodriguez-Maldonado, Jovaniel
AU - Feliu Maldonado, Roberto
AU - da Luz Sant'Ana, Istoni
AU - Sanina, Cristina
AU - Cox-Alomar, P.
AU - Ramakrishna, Harish
AU - Lopez-Candales, A.
AU - O'Neill, William W.
AU - Pinto, Duane S.
AU - Latib, A.
AU - Roche-Lima, A.
N1 - Publisher Copyright:
© 2019 American College of Cardiology Foundation
PY - 2019/7/22
Y1 - 2019/7/22
N2 - Objectives: This study sought to develop and compare an array of machine learning methods to predict in-hospital mortality after transcatheter aortic valve replacement (TAVR) in the United States. Background: Existing risk prediction tools for in-hospital complications in patients undergoing TAVR have been designed using statistical modeling approaches and have certain limitations. Methods: Patient data were obtained from the National Inpatient Sample database from 2012 to 2015. The data were randomly divided into a development cohort (n = 7,615) and a validation cohort (n = 3,268). Logistic regression, artificial neural network, naive Bayes, and random forest machine learning algorithms were applied to obtain in-hospital mortality prediction models. Results: A total of 10,883 TAVRs were analyzed in our study. The overall in-hospital mortality was 3.6%. Overall, prediction models’ performance measured by area under the curve were good (>0.80). The best model was obtained by logistic regression (area under the curve: 0.92; 95% confidence interval: 0.89 to 0.95). Most obtained models plateaued after introducing 10 variables. Acute kidney injury was the main predictor of in-hospital mortality ranked with the highest mean importance in all the models. The National Inpatient Sample TAVR score showed the best discrimination among available TAVR prediction scores. Conclusions: Machine learning methods can generate robust models to predict in-hospital mortality for TAVR. The National Inpatient Sample TAVR score should be considered for prognosis and shared decision making in TAVR patients.
AB - Objectives: This study sought to develop and compare an array of machine learning methods to predict in-hospital mortality after transcatheter aortic valve replacement (TAVR) in the United States. Background: Existing risk prediction tools for in-hospital complications in patients undergoing TAVR have been designed using statistical modeling approaches and have certain limitations. Methods: Patient data were obtained from the National Inpatient Sample database from 2012 to 2015. The data were randomly divided into a development cohort (n = 7,615) and a validation cohort (n = 3,268). Logistic regression, artificial neural network, naive Bayes, and random forest machine learning algorithms were applied to obtain in-hospital mortality prediction models. Results: A total of 10,883 TAVRs were analyzed in our study. The overall in-hospital mortality was 3.6%. Overall, prediction models’ performance measured by area under the curve were good (>0.80). The best model was obtained by logistic regression (area under the curve: 0.92; 95% confidence interval: 0.89 to 0.95). Most obtained models plateaued after introducing 10 variables. Acute kidney injury was the main predictor of in-hospital mortality ranked with the highest mean importance in all the models. The National Inpatient Sample TAVR score showed the best discrimination among available TAVR prediction scores. Conclusions: Machine learning methods can generate robust models to predict in-hospital mortality for TAVR. The National Inpatient Sample TAVR score should be considered for prognosis and shared decision making in TAVR patients.
KW - machine learning
KW - mortality
KW - transcatheter aortic valve replacement
UR - http://www.scopus.com/inward/record.url?scp=85068443858&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068443858&partnerID=8YFLogxK
U2 - 10.1016/j.jcin.2019.06.013
DO - 10.1016/j.jcin.2019.06.013
M3 - Article
C2 - 31320027
AN - SCOPUS:85068443858
SN - 1936-8798
VL - 12
SP - 1328
EP - 1338
JO - JACC: Cardiovascular Interventions
JF - JACC: Cardiovascular Interventions
IS - 14
ER -