Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320917439> ?p ?o ?g. }
- W4320917439 endingPage "82" @default.
- W4320917439 startingPage "82" @default.
- W4320917439 abstract "Background: This study aims to get an effective machine learning (ML) prediction model of new-onset postoperative atrial fibrillation (POAF) following coronary artery bypass grafting (CABG) and to highlight the most relevant clinical factors. Methods: Four ML algorithms were employed to analyze 394 patients undergoing CABG, and their performances were compared: Multivariate Adaptive Regression Spline, Neural Network, Random Forest, and Support Vector Machine. Each algorithm was applied to the training data set to choose the most important features and to build a predictive model. The better performance for each model was obtained by a hyperparameters search, and the Receiver Operating Characteristic Area Under the Curve metric was selected to choose the best model. The best instances of each model were fed with the test data set, and some metrics were generated to assess the performance of the models on the unseen data set. A traditional logistic regression was also performed to be compared with the machine learning models. Results: Random Forest model showed the best performance, and the top five predictive features included age, preoperative creatinine values, time of aortic cross-clamping, body surface area, and Logistic Euro-Score. Conclusions: The use of ML for clinical predictions requires an accurate evaluation of the models and their hyperparameters. Random Forest outperformed all other models in the clinical prediction of POAF following CABG." @default.
- W4320917439 created "2023-02-16" @default.
- W4320917439 creator A5002710091 @default.
- W4320917439 creator A5004060743 @default.
- W4320917439 creator A5016545357 @default.
- W4320917439 creator A5017940932 @default.
- W4320917439 creator A5029312514 @default.
- W4320917439 creator A5031776037 @default.
- W4320917439 creator A5037490050 @default.
- W4320917439 creator A5044573532 @default.
- W4320917439 creator A5044866592 @default.
- W4320917439 creator A5049157340 @default.
- W4320917439 creator A5066437317 @default.
- W4320917439 date "2023-02-15" @default.
- W4320917439 modified "2023-09-25" @default.
- W4320917439 title "Machine Learning to Identify Patients at Risk of Developing New-Onset Atrial Fibrillation after Coronary Artery Bypass" @default.
- W4320917439 cites W1823306425 @default.
- W4320917439 cites W1831050183 @default.
- W4320917439 cites W1924098982 @default.
- W4320917439 cites W1971318135 @default.
- W4320917439 cites W1972142091 @default.
- W4320917439 cites W1985485297 @default.
- W4320917439 cites W1987131471 @default.
- W4320917439 cites W1990240357 @default.
- W4320917439 cites W1992454438 @default.
- W4320917439 cites W1992910941 @default.
- W4320917439 cites W1998134891 @default.
- W4320917439 cites W2032459930 @default.
- W4320917439 cites W2035289668 @default.
- W4320917439 cites W2036215984 @default.
- W4320917439 cites W2036816448 @default.
- W4320917439 cites W2068096910 @default.
- W4320917439 cites W2069608457 @default.
- W4320917439 cites W2070350109 @default.
- W4320917439 cites W2073852966 @default.
- W4320917439 cites W2078856783 @default.
- W4320917439 cites W2081497884 @default.
- W4320917439 cites W2087431627 @default.
- W4320917439 cites W2088170288 @default.
- W4320917439 cites W2089996171 @default.
- W4320917439 cites W2108667197 @default.
- W4320917439 cites W2111466538 @default.
- W4320917439 cites W2115960395 @default.
- W4320917439 cites W2122843638 @default.
- W4320917439 cites W2125056507 @default.
- W4320917439 cites W2125757462 @default.
- W4320917439 cites W2132505348 @default.
- W4320917439 cites W2141246655 @default.
- W4320917439 cites W2141616636 @default.
- W4320917439 cites W2146404132 @default.
- W4320917439 cites W2147018083 @default.
- W4320917439 cites W2152412672 @default.
- W4320917439 cites W2155185788 @default.
- W4320917439 cites W2160868889 @default.
- W4320917439 cites W2162131419 @default.
- W4320917439 cites W2164861810 @default.
- W4320917439 cites W2166100730 @default.
- W4320917439 cites W2177858235 @default.
- W4320917439 cites W2177870565 @default.
- W4320917439 cites W2278422430 @default.
- W4320917439 cites W2396955211 @default.
- W4320917439 cites W2400601461 @default.
- W4320917439 cites W2784212335 @default.
- W4320917439 cites W2913705661 @default.
- W4320917439 cites W2913991666 @default.
- W4320917439 cites W2915632761 @default.
- W4320917439 cites W2916333596 @default.
- W4320917439 cites W2947446138 @default.
- W4320917439 cites W2963074577 @default.
- W4320917439 cites W2987212315 @default.
- W4320917439 cites W3004830772 @default.
- W4320917439 cites W3008919023 @default.
- W4320917439 cites W3037226097 @default.
- W4320917439 cites W3038611982 @default.
- W4320917439 cites W3082188176 @default.
- W4320917439 cites W3119165686 @default.
- W4320917439 cites W3134473784 @default.
- W4320917439 cites W3177440253 @default.
- W4320917439 cites W3187949263 @default.
- W4320917439 cites W3209934936 @default.
- W4320917439 cites W4200456592 @default.
- W4320917439 cites W4226402787 @default.
- W4320917439 doi "https://doi.org/10.3390/jcdd10020082" @default.
- W4320917439 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36826578" @default.
- W4320917439 hasPublicationYear "2023" @default.
- W4320917439 type Work @default.
- W4320917439 citedByCount "0" @default.
- W4320917439 crossrefType "journal-article" @default.
- W4320917439 hasAuthorship W4320917439A5002710091 @default.
- W4320917439 hasAuthorship W4320917439A5004060743 @default.
- W4320917439 hasAuthorship W4320917439A5016545357 @default.
- W4320917439 hasAuthorship W4320917439A5017940932 @default.
- W4320917439 hasAuthorship W4320917439A5029312514 @default.
- W4320917439 hasAuthorship W4320917439A5031776037 @default.
- W4320917439 hasAuthorship W4320917439A5037490050 @default.
- W4320917439 hasAuthorship W4320917439A5044573532 @default.
- W4320917439 hasAuthorship W4320917439A5044866592 @default.
- W4320917439 hasAuthorship W4320917439A5049157340 @default.