Benchmarking emergency department prediction models with machine learning and public electronic health records
Abstract The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure ca...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-022-01782-9 |
| _version_ | 1811257000871329792 |
|---|---|
| author | Feng Xie Jun Zhou Jin Wee Lee Mingrui Tan Siqi Li Logasan S/O Rajnthern Marcel Lucas Chee Bibhas Chakraborty An-Kwok Ian Wong Alon Dagan Marcus Eng Hock Ong Fei Gao Nan Liu |
| author_facet | Feng Xie Jun Zhou Jin Wee Lee Mingrui Tan Siqi Li Logasan S/O Rajnthern Marcel Lucas Chee Bibhas Chakraborty An-Kwok Ian Wong Alon Dagan Marcus Eng Hock Ong Fei Gao Nan Liu |
| author_sort | Feng Xie |
| collection | DOAJ |
| description | Abstract The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care. |
| first_indexed | 2024-04-12T17:49:41Z |
| format | Article |
| id | doaj.art-33f6df0814e9492ca8f68e30723700f8 |
| institution | Directory Open Access Journal |
| issn | 2052-4463 |
| language | English |
| last_indexed | 2024-04-12T17:49:41Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj.art-33f6df0814e9492ca8f68e30723700f82022-12-22T03:22:32ZengNature PortfolioScientific Data2052-44632022-10-019111210.1038/s41597-022-01782-9Benchmarking emergency department prediction models with machine learning and public electronic health recordsFeng Xie0Jun Zhou1Jin Wee Lee2Mingrui Tan3Siqi Li4Logasan S/O Rajnthern5Marcel Lucas Chee6Bibhas Chakraborty7An-Kwok Ian Wong8Alon Dagan9Marcus Eng Hock Ong10Fei Gao11Nan Liu12Centre for Quantitative Medicine and Programme in Health Services and Systems Research, Duke-NUS Medical SchoolInstitute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)Centre for Quantitative Medicine and Programme in Health Services and Systems Research, Duke-NUS Medical SchoolInstitute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)Centre for Quantitative Medicine and Programme in Health Services and Systems Research, Duke-NUS Medical SchoolSchool of Electrical and Electronic Engineering, Nanyang Technological UniversityFaculty of Medicine, Nursing and Health Sciences, Monash UniversityCentre for Quantitative Medicine and Programme in Health Services and Systems Research, Duke-NUS Medical SchoolDivision of Pulmonary, Allergy, and Critical Care Medicine, Duke UniversityDepartment of Emergency Medicine, Beth Israel Deaconess Medical Center, Harvard Medical SchoolCentre for Quantitative Medicine and Programme in Health Services and Systems Research, Duke-NUS Medical SchoolInstitute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)Centre for Quantitative Medicine and Programme in Health Services and Systems Research, Duke-NUS Medical SchoolAbstract The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care.https://doi.org/10.1038/s41597-022-01782-9 |
| spellingShingle | Feng Xie Jun Zhou Jin Wee Lee Mingrui Tan Siqi Li Logasan S/O Rajnthern Marcel Lucas Chee Bibhas Chakraborty An-Kwok Ian Wong Alon Dagan Marcus Eng Hock Ong Fei Gao Nan Liu Benchmarking emergency department prediction models with machine learning and public electronic health records Scientific Data |
| title | Benchmarking emergency department prediction models with machine learning and public electronic health records |
| title_full | Benchmarking emergency department prediction models with machine learning and public electronic health records |
| title_fullStr | Benchmarking emergency department prediction models with machine learning and public electronic health records |
| title_full_unstemmed | Benchmarking emergency department prediction models with machine learning and public electronic health records |
| title_short | Benchmarking emergency department prediction models with machine learning and public electronic health records |
| title_sort | benchmarking emergency department prediction models with machine learning and public electronic health records |
| url | https://doi.org/10.1038/s41597-022-01782-9 |
| work_keys_str_mv | AT fengxie benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT junzhou benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT jinweelee benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT mingruitan benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT siqili benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT logasansorajnthern benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT marcellucaschee benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT bibhaschakraborty benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT ankwokianwong benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT alondagan benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT marcusenghockong benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT feigao benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords AT nanliu benchmarkingemergencydepartmentpredictionmodelswithmachinelearningandpublicelectronichealthrecords |