Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study
Abstract Introduction Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED. Aim The main objective of this study...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Emergency Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12873-024-01141-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544932899160064 |
|---|---|
| author | Cyrielle Brossard Christophe Goetz Pierre Catoire Lauriane Cipolat Christophe Guyeux Cédric Gil Jardine Mahuna Akplogan Laure Abensur Vuillaume |
| author_facet | Cyrielle Brossard Christophe Goetz Pierre Catoire Lauriane Cipolat Christophe Guyeux Cédric Gil Jardine Mahuna Akplogan Laure Abensur Vuillaume |
| author_sort | Cyrielle Brossard |
| collection | DOAJ |
| description | Abstract Introduction Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED. Aim The main objective of this study was to build and test a prediction tool for ED admissions using artificial intelligence. Methods We performed a retrospective multicenter study in two French ED from January 1st, 2010 to December 31st, 2019.We tested several machine learning algorithms and compared the results. Results The arrival and departure times from the ED of 2 hospitals were collected from all consultations during the study period, then grouped into 87 600 one-hour slots. Through the development of two models (one for each location), we found that the XGBoost method with hyperparameter adaptations was the best, suggesting that the studied data could be predicted (mean absolute error) at 2.63 for Hospital 1 and 2.64 for Hospital 2). Conclusions This study ran the construction and validation of a powerful tool for predicting ED admissions in 2 French ED. This type of tool should be integrated into the overall organization of an ED, to optimize the resources of healthcare professionals. |
| format | Article |
| id | doaj-art-99336f38099d4014921f18b8caa38127 |
| institution | Kabale University |
| issn | 1471-227X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Emergency Medicine |
| spelling | doaj-art-99336f38099d4014921f18b8caa381272025-01-12T12:10:37ZengBMCBMC Emergency Medicine1471-227X2025-01-0125111110.1186/s12873-024-01141-4Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective studyCyrielle Brossard0Christophe Goetz1Pierre Catoire2Lauriane Cipolat3Christophe Guyeux4Cédric Gil Jardine5Mahuna Akplogan6Laure Abensur Vuillaume7Emergency department, CHR Metz-ThionvilleClinical Research Support Unit, CHR Metz-ThionvilleEmergency department, CHU BordeauxEmergency department, CHR Metz-ThionvilleInstitut Femto-ST, UMR 6174 CNRS, Université de Bourgogne Franche-ComtéEmergency department, CHU BordeauxExtome, Research & Development TeamEmergency department, CHR Metz-ThionvilleAbstract Introduction Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED. Aim The main objective of this study was to build and test a prediction tool for ED admissions using artificial intelligence. Methods We performed a retrospective multicenter study in two French ED from January 1st, 2010 to December 31st, 2019.We tested several machine learning algorithms and compared the results. Results The arrival and departure times from the ED of 2 hospitals were collected from all consultations during the study period, then grouped into 87 600 one-hour slots. Through the development of two models (one for each location), we found that the XGBoost method with hyperparameter adaptations was the best, suggesting that the studied data could be predicted (mean absolute error) at 2.63 for Hospital 1 and 2.64 for Hospital 2). Conclusions This study ran the construction and validation of a powerful tool for predicting ED admissions in 2 French ED. This type of tool should be integrated into the overall organization of an ED, to optimize the resources of healthcare professionals.https://doi.org/10.1186/s12873-024-01141-4Emergency departmentArtificial intelligenceOvercrowding |
| spellingShingle | Cyrielle Brossard Christophe Goetz Pierre Catoire Lauriane Cipolat Christophe Guyeux Cédric Gil Jardine Mahuna Akplogan Laure Abensur Vuillaume Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study BMC Emergency Medicine Emergency department Artificial intelligence Overcrowding |
| title | Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study |
| title_full | Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study |
| title_fullStr | Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study |
| title_full_unstemmed | Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study |
| title_short | Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study |
| title_sort | predicting emergency department admissions using a machine learning algorithm a proof of concept with retrospective study |
| topic | Emergency department Artificial intelligence Overcrowding |
| url | https://doi.org/10.1186/s12873-024-01141-4 |
| work_keys_str_mv | AT cyriellebrossard predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT christophegoetz predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT pierrecatoire predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT laurianecipolat predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT christopheguyeux predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT cedricgiljardine predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT mahunaakplogan predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy AT laureabensurvuillaume predictingemergencydepartmentadmissionsusingamachinelearningalgorithmaproofofconceptwithretrospectivestudy |