Dagmar F Hernandez-Suarez1, Yeunjung Kim2, Pedro Villablanca3, Tanush Gupta4, Jose Wiley4, Brenda G Nieves-Rodriguez5, Jovaniel Rodriguez-Maldonado5, Roberto Feliu Maldonado5, Istoni da Luz Sant'Ana5, Cristina Sanina4, Pedro Cox-Alomar6, Harish Ramakrishna7, Angel Lopez-Candales8, William W O'Neill3, Duane S Pinto9, Azeem Latib4, Abiel Roche-Lima5. 1. Division of Cardiovascular Medicine, Department of Medicine, University of Puerto Rico School of Medicine, San Juan, Puerto Rico. Electronic address: dagmar.hernandez@upr.edu. 2. Division of Cardiovascular Medicine, Department of Medicine, Yale University School of Medicine, New Haven, Connecticut. 3. Division of Cardiovascular Medicine, Department of Medicine, Henry Ford Hospital, Detroit, Michigan. 4. Division of Cardiology, Department of Medicine, Montefiore Medical Center/Albert Einstein College of Medicine, New York, New York. 5. Center for Collaborative Research in Health Disparities, University of Puerto Rico School of Medicine, San Juan, Puerto Rico. 6. Division of Cardiology, Department of Medicine, Louisiana State University, New Orleans, Louisiana. 7. Division of Cardiovascular and Thoracic Anesthesiology, Mayo Clinic, Phoenix, Arizona. 8. Division of Cardiovascular Medicine, Department of Medicine, University of Puerto Rico School of Medicine, San Juan, Puerto Rico. 9. Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts.
Abstract
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.
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.
Authors: Bharath Ambale-Venkatesh; Xiaoying Yang; Colin O Wu; Kiang Liu; W Gregory Hundley; Robyn McClelland; Antoinette S Gomes; Aaron R Folsom; Steven Shea; Eliseo Guallar; David A Bluemke; João A C Lima Journal: Circ Res Date: 2017-08-09 Impact factor: 17.367
Authors: J L Vincent; A de Mendonça; F Cantraine; R Moreno; J Takala; P M Suter; C L Sprung; F Colardyn; S Blecher Journal: Crit Care Med Date: 1998-11 Impact factor: 7.598
Authors: Tanush Gupta; Kashish Goel; Dhaval Kolte; Sahil Khera; Pedro A Villablanca; Wilbert S Aronow; Anna E Bortnick; David P Slovut; Cynthia C Taub; Jorge R Kizer; Robert T Pyo; J Dawn Abbott; Gregg C Fonarow; Charanjit S Rihal; Mario J Garcia; Deepak L Bhatt Journal: JACC Cardiovasc Interv Date: 2017-10-23 Impact factor: 11.195
Authors: Moritz Seiffert; Jan-Malte Sinning; Alexander Meyer; Sandra Wilde; Lenard Conradi; Mariuca Vasa-Nicotera; Alexander Ghanem; Jörg Kempfert; Christoph Hammerstingl; Francisco M Ojeda; Won-Keun Kim; Dietmar H Koschyk; Johannes Schirmer; Stephan Baldus; Eberhard Grube; Helge Möllmann; Hermann Reichenspurner; Georg Nickenig; Stefan Blankenberg; Patrick Diemert; Hendrik Treede; Thomas Walther; Nikos Werner; Renate B Schnabel Journal: Clin Res Cardiol Date: 2014-03-19 Impact factor: 5.460
Authors: Glen P Martin; Matthew Sperrin; Peter F Ludman; Mark A de Belder; Simon R Redwood; Jonathan N Townend; Mark Gunning; Neil E Moat; Adrian P Banning; Iain Buchan; Mamas A Mamas Journal: Heart Date: 2017-12-07 Impact factor: 5.994
Authors: Xinsong Du; Jae Min; Chintan P Shah; Rohit Bishnoi; William R Hogan; Dominick J Lemas Journal: Int J Med Inform Date: 2020-04-15 Impact factor: 4.046
Authors: Bruna Gomes; Maximilian Pilz; Christoph Reich; Florian Leuschner; Mathias Konstandin; Hugo A Katus; Benjamin Meder Journal: Clin Res Cardiol Date: 2020-06-24 Impact factor: 5.460
Authors: Dagmar F Hernandez-Suarez; Sagar Ranka; Yeunjung Kim; Azeem Latib; Jose Wiley; Angel Lopez-Candales; Duane S Pinto; Maday C Gonzalez; Harish Ramakrishna; Cristina Sanina; Brenda G Nieves-Rodriguez; Jovaniel Rodriguez-Maldonado; Roberto Feliu Maldonado; Israel J Rodriguez-Ruiz; Istoni da Luz Sant'Ana; Karlo A Wiley; Pedro Cox-Alomar; Pedro A Villablanca; Abiel Roche-Lima Journal: Cardiovasc Revasc Med Date: 2020-06-15
Authors: Marco Penso; Mauro Pepi; Laura Fusini; Manuela Muratori; Claudia Cefalù; Valentina Mantegazza; Paola Gripari; Sarah Ghulam Ali; Franco Fabbiocchi; Antonio L Bartorelli; Enrico G Caiani; Gloria Tamborini Journal: J Cardiovasc Dev Dis Date: 2021-04-16