Cited 1 times in
Machine Learning Model for the Prediction of Hemorrhage in Intensive Care Units
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 윤덕용 | - |
dc.date.accessioned | 2023-04-07T01:17:31Z | - |
dc.date.available | 2023-04-07T01:17:31Z | - |
dc.date.issued | 2022-10 | - |
dc.identifier.issn | 2093-3681 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/193866 | - |
dc.description.abstract | Objectives: Early hemorrhage detection in intensive care units (ICUs) enables timely intervention and reduces the risk of irreversible outcomes. In this study, we aimed to develop a machine learning model to predict hemorrhage by learning the patterns of continuously changing, real-world clinical data. Methods: We used the Medical Information Mart for Intensive Care databases (MIMIC-III and MIMIC-IV). A recurrent neural network was used to predict severe hemorrhage in the ICU. We developed three machine learning models with an increasing number of input features and levels of complexity: model 1 (11 features), model 2 (18 features), and model 3 (27 features). MIMIC-III was used for model training, and MIMIC-IV was split for internal validation. Using the model with the highest performance, external verification was performed using data from a subgroup extracted from the eICU Collaborative Research Database. Results: We included 5,670 ICU admissions, with 3,150 in the training set and 2,520 in the internal test set. A positive correlation was found between model complexity and performance. As a measure of performance, three models developed with an increasing number of features showed area under the receiver operating characteristic (AUROC) curve values of 0.61-0.94 according to the range of input data. In the subgroup extracted from the eICU database for external validation, an AUROC value of 0.74 was observed. Conclusions: Machine learning models that rely on real clinical data can be used to predict patients at high risk of bleeding in the ICU. | - |
dc.description.statementOfResponsibility | open | - |
dc.format | application/pdf | - |
dc.language | Korean | - |
dc.publisher | Korean Society of Medical Informatics | - |
dc.relation.isPartOf | HEALTHCARE INFORMATICS RESEARCH | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.title | Machine Learning Model for the Prediction of Hemorrhage in Intensive Care Units | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Dept. of Biomedical Systems Informatics (의생명시스템정보학교실) | - |
dc.contributor.googleauthor | Sora Kang | - |
dc.contributor.googleauthor | Chul Park | - |
dc.contributor.googleauthor | Jinseok Lee | - |
dc.contributor.googleauthor | Dukyong Yoon | - |
dc.identifier.doi | 10.4258/hir.2022.28.4.364 | - |
dc.contributor.localId | A06062 | - |
dc.relation.journalcode | J00974 | - |
dc.identifier.eissn | 2093-369X | - |
dc.identifier.pmid | 36380433 | - |
dc.subject.keyword | Blood Transfusion | - |
dc.subject.keyword | Hemorrhage | - |
dc.subject.keyword | Intensive Care Units | - |
dc.subject.keyword | Monitoring | - |
dc.subject.keyword | Physiological | - |
dc.subject.keyword | Prognosis | - |
dc.contributor.alternativeName | Yoon, Dukyong | - |
dc.contributor.affiliatedAuthor | 윤덕용 | - |
dc.citation.volume | 28 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 364 | - |
dc.citation.endPage | 375 | - |
dc.identifier.bibliographicCitation | HEALTHCARE INFORMATICS RESEARCH, Vol.28(4) : 364-375, 2022-10 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.