Transformer-based model for predicting length of stay in intensive care unit in sepsis patients
IntroductionSepsis, a life-threatening condition with a high mortality rate, requires intensive care unit (ICU) admission. The increasing hospitalization rate for patients with sepsis has escalated medical costs due to the strain on ICU resources. Efficient management of ICU resources is critical to...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2024.1473533/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556757535522816 |
|---|---|
| author | Jeesu Kim Jeesu Kim Geun-Hyeong Kim Geun-Hyeong Kim Jae-Woo Kim Jae-Woo Kim Ka Hyun Kim Ka Hyun Kim Jae-Young Maeng Yong-Goo Shin Seung Park Seung Park |
| author_facet | Jeesu Kim Jeesu Kim Geun-Hyeong Kim Geun-Hyeong Kim Jae-Woo Kim Jae-Woo Kim Ka Hyun Kim Ka Hyun Kim Jae-Young Maeng Yong-Goo Shin Seung Park Seung Park |
| author_sort | Jeesu Kim |
| collection | DOAJ |
| description | IntroductionSepsis, a life-threatening condition with a high mortality rate, requires intensive care unit (ICU) admission. The increasing hospitalization rate for patients with sepsis has escalated medical costs due to the strain on ICU resources. Efficient management of ICU resources is critical to addressing this challenge.MethodsThis study utilized the dataset collected from 521 patients with sepsis at Chungbuk National University Hospital between July 2020 and August 2023. A transformer-based deep learning model was developed to predict ICU length of stay (LOS). The model incorporated global and local input data analysis through classification and feature-wise tokens, based on sequential organ failure assessment (SOFA) criteria. Model performance was evaluated using four-fold cross-validation.ResultsThe proposed model achieved a mean absolute error (MAE) of 2.05 days for predicting ICU LOS. The result demonstrates the ability of the proposed model to provide accurate and reliable predictions.DiscussionThe proposed model offers valuable insights for healthcare resource management by optimizing ICU resource allocation and potentially reducing medical expenses. These findings highlight the applicability of the proposed model to efficient healthcare cost management. |
| format | Article |
| id | doaj-art-e97d763d3b8b4556b4550525e45581e2 |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-e97d763d3b8b4556b4550525e45581e22025-01-07T06:40:32ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-01-011110.3389/fmed.2024.14735331473533Transformer-based model for predicting length of stay in intensive care unit in sepsis patientsJeesu Kim0Jeesu Kim1Geun-Hyeong Kim2Geun-Hyeong Kim3Jae-Woo Kim4Jae-Woo Kim5Ka Hyun Kim6Ka Hyun Kim7Jae-Young Maeng8Yong-Goo Shin9Seung Park10Seung Park11Medical Artificial Intelligence Center, Chungbuk National University Hospital, Cheongju, Republic of KoreaCollege of Medicine, Chungbuk National University, Cheongju, Republic of KoreaMedical Artificial Intelligence Center, Chungbuk National University Hospital, Cheongju, Republic of KoreaCollege of Medicine, Chungbuk National University, Cheongju, Republic of KoreaMedical Artificial Intelligence Center, Chungbuk National University Hospital, Cheongju, Republic of KoreaCollege of Medicine, Chungbuk National University, Cheongju, Republic of KoreaMedical Artificial Intelligence Center, Chungbuk National University Hospital, Cheongju, Republic of KoreaCollege of Medicine, Chungbuk National University, Cheongju, Republic of KoreaMedical Artificial Intelligence Center, Chungbuk National University Hospital, Cheongju, Republic of KoreaDepartment of Electronics and Information Engineering, Korea University, Sejong, Republic of KoreaCollege of Medicine, Chungbuk National University, Cheongju, Republic of KoreaDepartment of Biomedical Engineering, Chungbuk National University Hospital, Cheongju, Republic of KoreaIntroductionSepsis, a life-threatening condition with a high mortality rate, requires intensive care unit (ICU) admission. The increasing hospitalization rate for patients with sepsis has escalated medical costs due to the strain on ICU resources. Efficient management of ICU resources is critical to addressing this challenge.MethodsThis study utilized the dataset collected from 521 patients with sepsis at Chungbuk National University Hospital between July 2020 and August 2023. A transformer-based deep learning model was developed to predict ICU length of stay (LOS). The model incorporated global and local input data analysis through classification and feature-wise tokens, based on sequential organ failure assessment (SOFA) criteria. Model performance was evaluated using four-fold cross-validation.ResultsThe proposed model achieved a mean absolute error (MAE) of 2.05 days for predicting ICU LOS. The result demonstrates the ability of the proposed model to provide accurate and reliable predictions.DiscussionThe proposed model offers valuable insights for healthcare resource management by optimizing ICU resource allocation and potentially reducing medical expenses. These findings highlight the applicability of the proposed model to efficient healthcare cost management.https://www.frontiersin.org/articles/10.3389/fmed.2024.1473533/fullsepsisintensive care unitlength of staysequential organ failure assessmenttransformertabular data |
| spellingShingle | Jeesu Kim Jeesu Kim Geun-Hyeong Kim Geun-Hyeong Kim Jae-Woo Kim Jae-Woo Kim Ka Hyun Kim Ka Hyun Kim Jae-Young Maeng Yong-Goo Shin Seung Park Seung Park Transformer-based model for predicting length of stay in intensive care unit in sepsis patients Frontiers in Medicine sepsis intensive care unit length of stay sequential organ failure assessment transformer tabular data |
| title | Transformer-based model for predicting length of stay in intensive care unit in sepsis patients |
| title_full | Transformer-based model for predicting length of stay in intensive care unit in sepsis patients |
| title_fullStr | Transformer-based model for predicting length of stay in intensive care unit in sepsis patients |
| title_full_unstemmed | Transformer-based model for predicting length of stay in intensive care unit in sepsis patients |
| title_short | Transformer-based model for predicting length of stay in intensive care unit in sepsis patients |
| title_sort | transformer based model for predicting length of stay in intensive care unit in sepsis patients |
| topic | sepsis intensive care unit length of stay sequential organ failure assessment transformer tabular data |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2024.1473533/full |
| work_keys_str_mv | AT jeesukim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT jeesukim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT geunhyeongkim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT geunhyeongkim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT jaewookim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT jaewookim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT kahyunkim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT kahyunkim transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT jaeyoungmaeng transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT yonggooshin transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT seungpark transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients AT seungpark transformerbasedmodelforpredictinglengthofstayinintensivecareunitinsepsispatients |