Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage
Abstract Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a te...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-14422-4 |
| _version_ | 1811334582884106240 |
|---|---|
| author | Hansol Chang Jae Yong Yu Sunyoung Yoon Taerim Kim Won Chul Cha |
| author_facet | Hansol Chang Jae Yong Yu Sunyoung Yoon Taerim Kim Won Chul Cha |
| author_sort | Hansol Chang |
| collection | DOAJ |
| description | Abstract Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a tertiary hospital located in a Korean metropolitan city. Patient who visited ED from January 1, 2016, to December 31, 2018, were included. Need of six CrIs were selected as prediction outcomes, namely, arterial line (A-line) insertion, oxygen therapy, high-flow nasal cannula (HFNC), intubation, Massive Transfusion Protocol (MTP), and inotropes and vasopressor. Extreme gradient boosting (XGBoost) prediction model was built by using only data available at the initial stage of ED. Overall, 137,883 patients were included in the study. The areas under the receiver operating characteristic curve for the prediction of A-line insertion was 0·913, oxygen therapy was 0.909, HFNC was 0.962, intubation was 0.945, MTP was 0.920, and inotropes or vasopressor administration was 0.899 in the XGBoost method. In addition, an increase in the need for CrIs was associated with worse ED outcomes. The CrIs model was integrated into the study site's electronic medical record and could be used to suggest early interventions for emergency physicians. |
| first_indexed | 2024-04-13T17:11:03Z |
| format | Article |
| id | doaj.art-bdca65dd8fe54d9aa55d6ce55ba70477 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-13T17:11:03Z |
| publishDate | 2022-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-bdca65dd8fe54d9aa55d6ce55ba704772022-12-22T02:38:17ZengNature PortfolioScientific Reports2045-23222022-06-0112111010.1038/s41598-022-14422-4Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triageHansol Chang0Jae Yong Yu1Sunyoung Yoon2Taerim Kim3Won Chul Cha4Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of MedicineDepartment of Digital Health, Samsung Advanced Institute for Health Science & Technology (SAIHST), Sungkyunkwan UniversityDepartment of Digital Health, Samsung Advanced Institute for Health Science & Technology (SAIHST), Sungkyunkwan UniversityDepartment of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of MedicineDepartment of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of MedicineAbstract Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a tertiary hospital located in a Korean metropolitan city. Patient who visited ED from January 1, 2016, to December 31, 2018, were included. Need of six CrIs were selected as prediction outcomes, namely, arterial line (A-line) insertion, oxygen therapy, high-flow nasal cannula (HFNC), intubation, Massive Transfusion Protocol (MTP), and inotropes and vasopressor. Extreme gradient boosting (XGBoost) prediction model was built by using only data available at the initial stage of ED. Overall, 137,883 patients were included in the study. The areas under the receiver operating characteristic curve for the prediction of A-line insertion was 0·913, oxygen therapy was 0.909, HFNC was 0.962, intubation was 0.945, MTP was 0.920, and inotropes or vasopressor administration was 0.899 in the XGBoost method. In addition, an increase in the need for CrIs was associated with worse ED outcomes. The CrIs model was integrated into the study site's electronic medical record and could be used to suggest early interventions for emergency physicians.https://doi.org/10.1038/s41598-022-14422-4 |
| spellingShingle | Hansol Chang Jae Yong Yu Sunyoung Yoon Taerim Kim Won Chul Cha Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage Scientific Reports |
| title | Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage |
| title_full | Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage |
| title_fullStr | Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage |
| title_full_unstemmed | Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage |
| title_short | Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage |
| title_sort | machine learning based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage |
| url | https://doi.org/10.1038/s41598-022-14422-4 |
| work_keys_str_mv | AT hansolchang machinelearningbasedsuggestionforcriticalinterventionsinthemanagementofpotentiallysevereconditionedpatientsinemergencydepartmenttriage AT jaeyongyu machinelearningbasedsuggestionforcriticalinterventionsinthemanagementofpotentiallysevereconditionedpatientsinemergencydepartmenttriage AT sunyoungyoon machinelearningbasedsuggestionforcriticalinterventionsinthemanagementofpotentiallysevereconditionedpatientsinemergencydepartmenttriage AT taerimkim machinelearningbasedsuggestionforcriticalinterventionsinthemanagementofpotentiallysevereconditionedpatientsinemergencydepartmenttriage AT wonchulcha machinelearningbasedsuggestionforcriticalinterventionsinthemanagementofpotentiallysevereconditionedpatientsinemergencydepartmenttriage |