Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm
Abstract Intensive care for patients with traumatic brain injury (TBI) aims to optimize intracranial pressure (ICP) and cerebral perfusion pressure (CPP). The transformation of ICP and CPP time-series data into a dynamic prediction model could aid clinicians to make more data-driven treatment decisi...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-022-00652-3 |
| _version_ | 1827614124890128384 |
|---|---|
| author | Rahul Raj Jenni M. Wennervirta Jonathan Tjerkaski Teemu M. Luoto Jussi P. Posti David W. Nelson Riikka Takala Stepani Bendel Eric P. Thelin Teemu Luostarinen Miikka Korja |
| author_facet | Rahul Raj Jenni M. Wennervirta Jonathan Tjerkaski Teemu M. Luoto Jussi P. Posti David W. Nelson Riikka Takala Stepani Bendel Eric P. Thelin Teemu Luostarinen Miikka Korja |
| author_sort | Rahul Raj |
| collection | DOAJ |
| description | Abstract Intensive care for patients with traumatic brain injury (TBI) aims to optimize intracranial pressure (ICP) and cerebral perfusion pressure (CPP). The transformation of ICP and CPP time-series data into a dynamic prediction model could aid clinicians to make more data-driven treatment decisions. We retrained and externally validated a machine learning model to dynamically predict the risk of mortality in patients with TBI. Retraining was done in 686 patients with 62,000 h of data and validation was done in two international cohorts including 638 patients with 60,000 h of data. The area under the receiver operating characteristic curve increased with time to 0.79 and 0.73 and the precision recall curve increased with time to 0.57 and 0.64 in the Swedish and American validation cohorts, respectively. The rate of false positives decreased to ≤2.5%. The algorithm provides dynamic mortality predictions during intensive care that improved with increasing data and may have a role as a clinical decision support tool. |
| first_indexed | 2024-03-09T08:50:14Z |
| format | Article |
| id | doaj.art-b4bb3fb6ce544b78948a233b4b61af91 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T08:50:14Z |
| publishDate | 2022-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-b4bb3fb6ce544b78948a233b4b61af912023-12-02T14:33:25ZengNature Portfolionpj Digital Medicine2398-63522022-07-01511810.1038/s41746-022-00652-3Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithmRahul Raj0Jenni M. Wennervirta1Jonathan Tjerkaski2Teemu M. Luoto3Jussi P. Posti4David W. Nelson5Riikka Takala6Stepani Bendel7Eric P. Thelin8Teemu Luostarinen9Miikka Korja10Department of Neurosurgery, Helsinki University Hospital and University of HelsinkiDepartment of Neurosurgery, Helsinki University Hospital and University of HelsinkiDepartment of Clinical Neuroscience, Karolinska InstitutetDepartment of Neurosurgery, Tampere University Hospital and Tampere UniversityDepartment of Neurosurgery, and Turku Brain Injury Centre, Turku University Hospital and University of TurkuSection for Anesthesiology and Intensive Care, Department of Physiology and Pharmacology, Karolinska InstitutetPerioperative Services, Intensive Care Medicine and Pain Management, Turku University Hospital and University of TurkuDivision of Intensive Care, Department of Anesthesiology and Intensive Care, Kuopio University HospitalDepartment of Clinical Neuroscience, Karolinska InstitutetAnaesthesiology and Intensive Care, Hyvinkää Hospital, Helsinki University Hospital and University of HelsinkiDepartment of Neurosurgery, Helsinki University Hospital and University of HelsinkiAbstract Intensive care for patients with traumatic brain injury (TBI) aims to optimize intracranial pressure (ICP) and cerebral perfusion pressure (CPP). The transformation of ICP and CPP time-series data into a dynamic prediction model could aid clinicians to make more data-driven treatment decisions. We retrained and externally validated a machine learning model to dynamically predict the risk of mortality in patients with TBI. Retraining was done in 686 patients with 62,000 h of data and validation was done in two international cohorts including 638 patients with 60,000 h of data. The area under the receiver operating characteristic curve increased with time to 0.79 and 0.73 and the precision recall curve increased with time to 0.57 and 0.64 in the Swedish and American validation cohorts, respectively. The rate of false positives decreased to ≤2.5%. The algorithm provides dynamic mortality predictions during intensive care that improved with increasing data and may have a role as a clinical decision support tool.https://doi.org/10.1038/s41746-022-00652-3 |
| spellingShingle | Rahul Raj Jenni M. Wennervirta Jonathan Tjerkaski Teemu M. Luoto Jussi P. Posti David W. Nelson Riikka Takala Stepani Bendel Eric P. Thelin Teemu Luostarinen Miikka Korja Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm npj Digital Medicine |
| title | Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm |
| title_full | Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm |
| title_fullStr | Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm |
| title_full_unstemmed | Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm |
| title_short | Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm |
| title_sort | dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm |
| url | https://doi.org/10.1038/s41746-022-00652-3 |
| work_keys_str_mv | AT rahulraj dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT jennimwennervirta dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT jonathantjerkaski dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT teemumluoto dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT jussipposti dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT davidwnelson dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT riikkatakala dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT stepanibendel dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT ericpthelin dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT teemuluostarinen dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm AT miikkakorja dynamicpredictionofmortalityaftertraumaticbraininjuryusingamachinelearningalgorithm |