Prediction of prolonged ventilation after coronary artery bypass grafting: Data from an artificial neural network

Eric S Wise, David P. Stonko, Zachary A. Glaser, Kelly L. Garcia, Jennifer J. Huang, Justine S. Kim, Justiss A. Kallos, Joseph R. Starnes, Jacob W. Fleming, Kyle M. Hocking, Colleen M. Brophy, Susan S. Eagle

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

Objectives: The need for mechanical ventilation 24 hours after coronary artery bypass grafting (CABG) is considered a morbidity by the Society of Thoracic Surgeons. The purpose of this investigation was twofold: to identify simple preoperative patient factors independently associated with prolonged ventilation and to optimize prediction and early identification of patients prone to prolonged ventilation using an artificial neural network (ANN). Methods: Using the institutional Adult Cardiac Database, 738 patients who underwent CABG since 2005 were reviewed for preoperative factors independently associated with prolonged postoperative ventilation. Prediction of prolonged ventilation from the identified variables was modeled using both "traditional" multiple logistic regression and an ANN. The two models were compared using Pearson r2 and area under the curve (AUC) parameters. Results: Of 738 included patients, 14% (104/738) required mechanical ventilation = 24 hours postoperatively. Upon multivariate analysis, higher body-mass index (BMI; odds ratio [OR] 1.10 per unit, P < 0.001), lower ejection fraction (OR 0.97 per %, P = 0.01) and use of cardiopulmonary bypass (OR 2.59, P = 0.02) were independently predictive of prolonged ventilation. The Pearson r2 and AUC of the multivariate nominal logistic regression model were 0.086 and 0.698 ± 0.05, respectively; analogous statistics of the ANN model were 0.159 and 0.732 ± 0.05, respectively. BMI, ejection fraction and cardiopulmonary bypass represent three simple factors that may predict prolonged ventilation after CABG. Early identification of these patients can be optimized using an ANN, an emerging paradigm for clinical outcomes modeling that may consider complex relationships among these variables.

Original languageEnglish (US)
Pages (from-to)E7-E14
JournalHeart Surgery Forum
Volume20
Issue number1
DOIs
StatePublished - Feb 2017
Externally publishedYes

Fingerprint Dive into the research topics of 'Prediction of prolonged ventilation after coronary artery bypass grafting: Data from an artificial neural network'. Together they form a unique fingerprint.

Cite this