Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population
Abstract Background Traditional risk stratification tools do not describe the complex principle determinant relationships that exist amongst pre-operative and peri-operative factors and their influence on cardiac surgical outcomes. This paper reports on the use of Bayesian networks to investigate su...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-02-01
|
| Series: | BMC Cardiovascular Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12872-023-03100-6 |
| _version_ | 1811166044527525888 |
|---|---|
| author | Khurum Mazhar Saifullah Mohamed Akshay J. Patel Sarah Berger Veith Giles Roberts Richard Warwick Lognathen Balacumaraswami Qamar Abid Marko Raseta |
| author_facet | Khurum Mazhar Saifullah Mohamed Akshay J. Patel Sarah Berger Veith Giles Roberts Richard Warwick Lognathen Balacumaraswami Qamar Abid Marko Raseta |
| author_sort | Khurum Mazhar |
| collection | DOAJ |
| description | Abstract Background Traditional risk stratification tools do not describe the complex principle determinant relationships that exist amongst pre-operative and peri-operative factors and their influence on cardiac surgical outcomes. This paper reports on the use of Bayesian networks to investigate such outcomes. Methods Data were prospectively collected from 4776 adult patients undergoing cardiac surgery at a single UK institute between April 2012 and May 2019. Machine learning techniques were used to construct Bayesian networks for four key short-term outcomes including death, stroke and renal failure. Results Duration of operation was the most important determinant of death irrespective of EuroSCORE. Duration of cardiopulmonary bypass was the most important determinant of re-operation for bleeding. EuroSCORE was predictive of new renal replacement therapy but not mortality. Conclusions Machine-learning algorithms have allowed us to analyse the significance of dynamic processes that occur between pre-operative and peri-operative elements. Length of procedure and duration of cardiopulmonary bypass predicted mortality and morbidity in patients undergoing cardiac surgery in the UK. Bayesian networks can be used to explore potential principle determinant mechanisms underlying outcomes and be used to help develop future risk models. |
| first_indexed | 2024-04-10T15:46:04Z |
| format | Article |
| id | doaj.art-1ce0533480cf41119db1f24ae5594e7e |
| institution | Directory Open Access Journal |
| issn | 1471-2261 |
| language | English |
| last_indexed | 2024-04-10T15:46:04Z |
| publishDate | 2023-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cardiovascular Disorders |
| spelling | doaj.art-1ce0533480cf41119db1f24ae5594e7e2023-02-12T12:04:00ZengBMCBMC Cardiovascular Disorders1471-22612023-02-012311810.1186/s12872-023-03100-6Bayesian networks identify determinants of outcomes following cardiac surgery in a UK populationKhurum Mazhar0Saifullah Mohamed1Akshay J. Patel2Sarah Berger Veith3Giles Roberts4Richard Warwick5Lognathen Balacumaraswami6Qamar Abid7Marko Raseta8Royal Stoke University HospitalRoyal Stoke University HospitalInstitute of Immunology and Immunotherapy, University of BirminghamFaculty of Medicine Carl Gustav Carus, TU DresdenRoyal Stoke University HospitalRoyal Stoke University HospitalRoyal Stoke University HospitalRoyal Stoke University HospitalRoyal Stoke University HospitalAbstract Background Traditional risk stratification tools do not describe the complex principle determinant relationships that exist amongst pre-operative and peri-operative factors and their influence on cardiac surgical outcomes. This paper reports on the use of Bayesian networks to investigate such outcomes. Methods Data were prospectively collected from 4776 adult patients undergoing cardiac surgery at a single UK institute between April 2012 and May 2019. Machine learning techniques were used to construct Bayesian networks for four key short-term outcomes including death, stroke and renal failure. Results Duration of operation was the most important determinant of death irrespective of EuroSCORE. Duration of cardiopulmonary bypass was the most important determinant of re-operation for bleeding. EuroSCORE was predictive of new renal replacement therapy but not mortality. Conclusions Machine-learning algorithms have allowed us to analyse the significance of dynamic processes that occur between pre-operative and peri-operative elements. Length of procedure and duration of cardiopulmonary bypass predicted mortality and morbidity in patients undergoing cardiac surgery in the UK. Bayesian networks can be used to explore potential principle determinant mechanisms underlying outcomes and be used to help develop future risk models.https://doi.org/10.1186/s12872-023-03100-6Bayesian networkRisk stratificationEuroSCORECardiac surgeryOutcomes |
| spellingShingle | Khurum Mazhar Saifullah Mohamed Akshay J. Patel Sarah Berger Veith Giles Roberts Richard Warwick Lognathen Balacumaraswami Qamar Abid Marko Raseta Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population BMC Cardiovascular Disorders Bayesian network Risk stratification EuroSCORE Cardiac surgery Outcomes |
| title | Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population |
| title_full | Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population |
| title_fullStr | Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population |
| title_full_unstemmed | Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population |
| title_short | Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population |
| title_sort | bayesian networks identify determinants of outcomes following cardiac surgery in a uk population |
| topic | Bayesian network Risk stratification EuroSCORE Cardiac surgery Outcomes |
| url | https://doi.org/10.1186/s12872-023-03100-6 |
| work_keys_str_mv | AT khurummazhar bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT saifullahmohamed bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT akshayjpatel bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT sarahbergerveith bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT gilesroberts bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT richardwarwick bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT lognathenbalacumaraswami bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT qamarabid bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation AT markoraseta bayesiannetworksidentifydeterminantsofoutcomesfollowingcardiacsurgeryinaukpopulation |