Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit
Background Mortality prediction in critically ill patients with cardiogenic shock can guide triage and selection of potentially high‐risk treatment options. Methods and Results We developed and externally validated a checklist risk score to predict in‐hospital mortality among adults admitted to the...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease |
| Subjects: | |
| Online Access: | https://www.ahajournals.org/doi/10.1161/JAHA.122.029232 |
| _version_ | 1827367937999110144 |
|---|---|
| author | Eric Yamga Sreekar Mantena Darin Rosen Emily M. Bucholz Robert W. Yeh Leo A. Celi Berk Ustun Neel M. Butala |
| author_facet | Eric Yamga Sreekar Mantena Darin Rosen Emily M. Bucholz Robert W. Yeh Leo A. Celi Berk Ustun Neel M. Butala |
| author_sort | Eric Yamga |
| collection | DOAJ |
| description | Background Mortality prediction in critically ill patients with cardiogenic shock can guide triage and selection of potentially high‐risk treatment options. Methods and Results We developed and externally validated a checklist risk score to predict in‐hospital mortality among adults admitted to the cardiac intensive care unit with Society for Cardiovascular Angiography & Interventions Shock Stage C or greater cardiogenic shock using 2 real‐world data sets and Risk‐Calibrated Super‐sparse Linear Integer Modeling (RiskSLIM). We compared this model to those developed using conventional penalized logistic regression and published cardiogenic shock and intensive care unit mortality prediction models. There were 8815 patients in our training cohort (in‐hospital mortality 13.4%) and 2237 patients in our validation cohort (in‐hospital mortality 22.8%), and there were 39 candidate predictor variables. The final risk score (termed BOS,MA2) included maximum blood urea nitrogen ≥25 mg/dL, minimum oxygen saturation <88%, minimum systolic blood pressure <80 mm Hg, use of mechanical ventilation, age ≥60 years, and maximum anion gap ≥14 mmol/L, based on values recorded during the first 24 hours of intensive care unit stay. Predicted in‐hospital mortality ranged from 0.5% for a score of 0 to 70.2% for a score of 6. The area under the receiver operating curve was 0.83 (0.82–0.84) in training and 0.76 (0.73–0.78) in validation, and the expected calibration error was 0.9% in training and 2.6% in validation. Conclusions Developed using a novel machine learning method and the largest cardiogenic shock cohorts among published models, BOS,MA2 is a simple, clinically interpretable risk score that has improved performance compared with existing cardiogenic‐shock risk scores and better calibration than general intensive care unit risk scores. |
| first_indexed | 2024-03-08T09:22:55Z |
| format | Article |
| id | doaj.art-5f813ab3d3e4465ea66fcafe822a4a00 |
| institution | Directory Open Access Journal |
| issn | 2047-9980 |
| language | English |
| last_indexed | 2024-03-08T09:22:55Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease |
| spelling | doaj.art-5f813ab3d3e4465ea66fcafe822a4a002024-01-31T11:31:17ZengWileyJournal of the American Heart Association: Cardiovascular and Cerebrovascular Disease2047-99802023-07-01121310.1161/JAHA.122.029232Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care UnitEric Yamga0Sreekar Mantena1Darin Rosen2Emily M. Bucholz3Robert W. Yeh4Leo A. Celi5Berk Ustun6Neel M. Butala7Department of Medicine Centre Hospitalier de l’Université de Montréal (CHUM) Montreal QC CanadaHarvard Medical School Boston MA USAJohns Hopkins School of Medicine Baltimore MD USAUniversity of Colorado School of Medicine Aurora CO USAHarvard Medical School Boston MA USAHarvard Medical School Boston MA USAHalıcıoğlu Data Science Institute University of California San Diego CA USAUniversity of Colorado School of Medicine Aurora CO USABackground Mortality prediction in critically ill patients with cardiogenic shock can guide triage and selection of potentially high‐risk treatment options. Methods and Results We developed and externally validated a checklist risk score to predict in‐hospital mortality among adults admitted to the cardiac intensive care unit with Society for Cardiovascular Angiography & Interventions Shock Stage C or greater cardiogenic shock using 2 real‐world data sets and Risk‐Calibrated Super‐sparse Linear Integer Modeling (RiskSLIM). We compared this model to those developed using conventional penalized logistic regression and published cardiogenic shock and intensive care unit mortality prediction models. There were 8815 patients in our training cohort (in‐hospital mortality 13.4%) and 2237 patients in our validation cohort (in‐hospital mortality 22.8%), and there were 39 candidate predictor variables. The final risk score (termed BOS,MA2) included maximum blood urea nitrogen ≥25 mg/dL, minimum oxygen saturation <88%, minimum systolic blood pressure <80 mm Hg, use of mechanical ventilation, age ≥60 years, and maximum anion gap ≥14 mmol/L, based on values recorded during the first 24 hours of intensive care unit stay. Predicted in‐hospital mortality ranged from 0.5% for a score of 0 to 70.2% for a score of 6. The area under the receiver operating curve was 0.83 (0.82–0.84) in training and 0.76 (0.73–0.78) in validation, and the expected calibration error was 0.9% in training and 2.6% in validation. Conclusions Developed using a novel machine learning method and the largest cardiogenic shock cohorts among published models, BOS,MA2 is a simple, clinically interpretable risk score that has improved performance compared with existing cardiogenic‐shock risk scores and better calibration than general intensive care unit risk scores.https://www.ahajournals.org/doi/10.1161/JAHA.122.029232cardiogenic shockCICUmachine learningmortalityrisk scoreSCAI shock |
| spellingShingle | Eric Yamga Sreekar Mantena Darin Rosen Emily M. Bucholz Robert W. Yeh Leo A. Celi Berk Ustun Neel M. Butala Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease cardiogenic shock CICU machine learning mortality risk score SCAI shock |
| title | Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit |
| title_full | Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit |
| title_fullStr | Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit |
| title_full_unstemmed | Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit |
| title_short | Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit |
| title_sort | optimized risk score to predict mortality in patients with cardiogenic shock in the cardiac intensive care unit |
| topic | cardiogenic shock CICU machine learning mortality risk score SCAI shock |
| url | https://www.ahajournals.org/doi/10.1161/JAHA.122.029232 |
| work_keys_str_mv | AT ericyamga optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT sreekarmantena optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT darinrosen optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT emilymbucholz optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT robertwyeh optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT leoaceli optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT berkustun optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit AT neelmbutala optimizedriskscoretopredictmortalityinpatientswithcardiogenicshockinthecardiacintensivecareunit |