Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations
Abstract 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...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/9336156248a1408d8a4dc57b72808a9b |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:9336156248a1408d8a4dc57b72808a9b |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:9336156248a1408d8a4dc57b72808a9b2021-12-02T12:15:01ZEnsemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations10.1038/s41598-021-82403-02045-2322https://doaj.org/article/9336156248a1408d8a4dc57b72808a9b2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-82403-0https://doaj.org/toc/2045-2322Abstract 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.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. EpemaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q José Castela Forte Hubert E. Mungroop Fred de Geus Maureen L. van der Grinten Hjalmar R. Bouma Ville Pettilä Thomas W. L. Scheeren Maarten W. N. Nijsten Massimo A. Mariani Iwan C. C. van der Horst Robert H. Henning Marco A. Wiering Anne H. Epema Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations |
| description |
Abstract 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. |
| format |
article |
| author |
José Castela Forte Hubert E. Mungroop Fred de Geus Maureen L. van der Grinten Hjalmar R. Bouma Ville Pettilä Thomas W. L. Scheeren Maarten W. N. Nijsten Massimo A. Mariani Iwan C. C. van der Horst Robert H. Henning Marco A. Wiering Anne H. Epema |
| author_facet |
José Castela Forte Hubert E. Mungroop Fred de Geus Maureen L. van der Grinten Hjalmar R. Bouma Ville Pettilä Thomas W. L. Scheeren Maarten W. N. Nijsten Massimo A. Mariani Iwan C. C. van der Horst Robert H. Henning Marco A. Wiering Anne H. Epema |
| author_sort |
José Castela Forte |
| title |
Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations |
| title_short |
Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations |
| title_full |
Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations |
| title_fullStr |
Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations |
| title_full_unstemmed |
Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations |
| title_sort |
ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and cabg operations |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/9336156248a1408d8a4dc57b72808a9b |
| work_keys_str_mv |
AT josecastelaforte ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT hubertemungroop ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT freddegeus ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT maureenlvandergrinten ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT hjalmarrbouma ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT villepettila ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT thomaswlscheeren ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT maartenwnnijsten ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT massimoamariani ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT iwanccvanderhorst ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT roberthhenning ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT marcoawiering ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations AT annehepema ensemblemachinelearningpredictionandvariableimportanceanalysisof5yearmortalityaftercardiacvalveandcabgoperations |
| _version_ |
1718394587409547264 |