Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning
Abstract Background Both in-hospital cardiac arrest (IHCA) and out-of-hospital cardiac arrest (OHCA) have higher incidence and lower survival rates. Predictors of in-hospital mortality for intensive care unit (ICU) admitted cardiac arrest (CA) patients remain unclear. Methods The Medical Information...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-05-01
|
| Series: | BMC Anesthesiology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12871-023-02138-5 |
| _version_ | 1797817862652428288 |
|---|---|
| author | Yiwu Sun Zhaoyi He Jie Ren Yifan Wu |
| author_facet | Yiwu Sun Zhaoyi He Jie Ren Yifan Wu |
| author_sort | Yiwu Sun |
| collection | DOAJ |
| description | Abstract Background Both in-hospital cardiac arrest (IHCA) and out-of-hospital cardiac arrest (OHCA) have higher incidence and lower survival rates. Predictors of in-hospital mortality for intensive care unit (ICU) admitted cardiac arrest (CA) patients remain unclear. Methods The Medical Information Mart for Intensive Care IV (MIMIC-IV) database was used to perform a retrospective study. Patients meeting the inclusion criteria were identified from the MIMIC-IV database and randomly divided into training set (n = 1206, 70%) and validation set (n = 516, 30%). Candidate predictors consisted of the demographics, comorbidity, vital signs, laboratory test results, scoring systems, and treatment information on the first day of ICU admission. Independent risk factors for in-hospital mortality were screened using the least absolute shrinkage and selection operator (LASSO) regression model and the extreme gradient boosting (XGBoost) in the training set. Multivariate logistic regression analysis was used to build prediction models in training set, and then validated in validation set. Discrimination, calibration and clinical utility of these models were compared using the area under the curve (AUC) of the receiver operating characteristic (ROC) curves, calibration curves and decision curve analysis (DCA). After pairwise comparison, the best performing model was chosen to build a nomogram. Results Among the 1722 patients, in-hospital mortality was 53.95%. In both sets, the LASSO, XGBoost,the logistic regression(LR) model and the National Early Warning Score 2 (NEWS 2) models showed acceptable discrimination. In pairwise comparison, the prediction effectiveness was higher with the LASSO,XGBoost and LR models than the NEWS 2 model (p < 0.001). The LASSO,XGBoost and LR models also showed good calibration. The LASSO model was chosen as our final model for its higher net benefit and wider threshold range. And the LASSO model was presented as the nomogram. Conclusions The LASSO model enabled good prediction of in-hospital mortality in ICU admission CA patients, which may be widely used in clinical decision-making. |
| first_indexed | 2024-03-13T08:59:43Z |
| format | Article |
| id | doaj.art-b00c2864cd40445197344261b37ccb6e |
| institution | Directory Open Access Journal |
| issn | 1471-2253 |
| language | English |
| last_indexed | 2024-03-13T08:59:43Z |
| publishDate | 2023-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Anesthesiology |
| spelling | doaj.art-b00c2864cd40445197344261b37ccb6e2023-05-28T11:26:07ZengBMCBMC Anesthesiology1471-22532023-05-0123111710.1186/s12871-023-02138-5Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learningYiwu Sun0Zhaoyi He1Jie Ren2Yifan Wu3Department of Anesthesiology, Dazhou Central HospitalDepartment of Anesthesiology, The Third Affiliated Hospital of Harbin Medical UniversityDepartment of Anesthesiology, Guizhou Provincial People’s HospitalDepartment of Anesthesiology, Shanghai Sixth People’s HospitalAbstract Background Both in-hospital cardiac arrest (IHCA) and out-of-hospital cardiac arrest (OHCA) have higher incidence and lower survival rates. Predictors of in-hospital mortality for intensive care unit (ICU) admitted cardiac arrest (CA) patients remain unclear. Methods The Medical Information Mart for Intensive Care IV (MIMIC-IV) database was used to perform a retrospective study. Patients meeting the inclusion criteria were identified from the MIMIC-IV database and randomly divided into training set (n = 1206, 70%) and validation set (n = 516, 30%). Candidate predictors consisted of the demographics, comorbidity, vital signs, laboratory test results, scoring systems, and treatment information on the first day of ICU admission. Independent risk factors for in-hospital mortality were screened using the least absolute shrinkage and selection operator (LASSO) regression model and the extreme gradient boosting (XGBoost) in the training set. Multivariate logistic regression analysis was used to build prediction models in training set, and then validated in validation set. Discrimination, calibration and clinical utility of these models were compared using the area under the curve (AUC) of the receiver operating characteristic (ROC) curves, calibration curves and decision curve analysis (DCA). After pairwise comparison, the best performing model was chosen to build a nomogram. Results Among the 1722 patients, in-hospital mortality was 53.95%. In both sets, the LASSO, XGBoost,the logistic regression(LR) model and the National Early Warning Score 2 (NEWS 2) models showed acceptable discrimination. In pairwise comparison, the prediction effectiveness was higher with the LASSO,XGBoost and LR models than the NEWS 2 model (p < 0.001). The LASSO,XGBoost and LR models also showed good calibration. The LASSO model was chosen as our final model for its higher net benefit and wider threshold range. And the LASSO model was presented as the nomogram. Conclusions The LASSO model enabled good prediction of in-hospital mortality in ICU admission CA patients, which may be widely used in clinical decision-making.https://doi.org/10.1186/s12871-023-02138-5Prediction modelMachine learningCardiac arrestIntensive care unitIn-hospital mortalityMIMIC-IV database |
| spellingShingle | Yiwu Sun Zhaoyi He Jie Ren Yifan Wu Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning BMC Anesthesiology Prediction model Machine learning Cardiac arrest Intensive care unit In-hospital mortality MIMIC-IV database |
| title | Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning |
| title_full | Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning |
| title_fullStr | Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning |
| title_full_unstemmed | Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning |
| title_short | Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning |
| title_sort | prediction model of in hospital mortality in intensive care unit patients with cardiac arrest a retrospective analysis of mimic iv database based on machine learning |
| topic | Prediction model Machine learning Cardiac arrest Intensive care unit In-hospital mortality MIMIC-IV database |
| url | https://doi.org/10.1186/s12871-023-02138-5 |
| work_keys_str_mv | AT yiwusun predictionmodelofinhospitalmortalityinintensivecareunitpatientswithcardiacarrestaretrospectiveanalysisofmimicivdatabasebasedonmachinelearning AT zhaoyihe predictionmodelofinhospitalmortalityinintensivecareunitpatientswithcardiacarrestaretrospectiveanalysisofmimicivdatabasebasedonmachinelearning AT jieren predictionmodelofinhospitalmortalityinintensivecareunitpatientswithcardiacarrestaretrospectiveanalysisofmimicivdatabasebasedonmachinelearning AT yifanwu predictionmodelofinhospitalmortalityinintensivecareunitpatientswithcardiacarrestaretrospectiveanalysisofmimicivdatabasebasedonmachinelearning |