Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study
Abstract BackgroundNursing narratives are an intriguing feature in the prediction of short-term clinical outcomes. However, it is unclear which nursing narratives significantly impact the prediction of postoperative length of stay (LOS) in deep learning models. Obj...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2023-12-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2023/1/e45377 |
| _version_ | 1827392671059017728 |
|---|---|
| author | Sungjoo Han Yong Bum Kim Jae Hong No Dong Hoon Suh Kidong Kim Soyeon Ahn |
| author_facet | Sungjoo Han Yong Bum Kim Jae Hong No Dong Hoon Suh Kidong Kim Soyeon Ahn |
| author_sort | Sungjoo Han |
| collection | DOAJ |
| description |
Abstract
BackgroundNursing narratives are an intriguing feature in the prediction of short-term clinical outcomes. However, it is unclear which nursing narratives significantly impact the prediction of postoperative length of stay (LOS) in deep learning models.
ObjectiveTherefore, we applied the Reverse Time Attention (RETAIN) model to predict LOS, entering nursing narratives as the main input.
MethodsA total of 354 patients who underwent ovarian cancer surgery at the Seoul National University Bundang Hospital from 2014 to 2020 were retrospectively enrolled. Nursing narratives collected within 3 postoperative days were used to predict prolonged LOS (≥10 days). The physician’s assessment was conducted based on a retrospective review of the physician’s note within the same period of the data model used.
ResultsThe model performed better than the physician’s assessment (area under the receiver operating curve of 0.81 vs 0.58; P
ConclusionsThe use of the RETAIN model on nursing narratives predicted postoperative LOS effectively for patients who underwent ovarian cancer surgery. These findings suggest that accurate and interpretable deep learning information obtained shortly after surgery may accurately predict prolonged LOS. |
| first_indexed | 2024-03-08T17:36:39Z |
| format | Article |
| id | doaj.art-2b6a25eb134a4bd494defc14bb88f39e |
| institution | Directory Open Access Journal |
| issn | 2291-9694 |
| language | English |
| last_indexed | 2024-03-08T17:36:39Z |
| publishDate | 2023-12-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj.art-2b6a25eb134a4bd494defc14bb88f39e2024-01-02T11:46:57ZengJMIR PublicationsJMIR Medical Informatics2291-96942023-12-0111e45377e4537710.2196/45377Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort StudySungjoo Hanhttp://orcid.org/0000-0002-8185-2592Yong Bum Kimhttp://orcid.org/0000-0003-1196-369XJae Hong Nohttp://orcid.org/0000-0002-2389-6757Dong Hoon Suhhttp://orcid.org/0000-0002-4312-966XKidong Kimhttp://orcid.org/0000-0001-9254-6024Soyeon Ahnhttp://orcid.org/0000-0003-3440-2027 Abstract BackgroundNursing narratives are an intriguing feature in the prediction of short-term clinical outcomes. However, it is unclear which nursing narratives significantly impact the prediction of postoperative length of stay (LOS) in deep learning models. ObjectiveTherefore, we applied the Reverse Time Attention (RETAIN) model to predict LOS, entering nursing narratives as the main input. MethodsA total of 354 patients who underwent ovarian cancer surgery at the Seoul National University Bundang Hospital from 2014 to 2020 were retrospectively enrolled. Nursing narratives collected within 3 postoperative days were used to predict prolonged LOS (≥10 days). The physician’s assessment was conducted based on a retrospective review of the physician’s note within the same period of the data model used. ResultsThe model performed better than the physician’s assessment (area under the receiver operating curve of 0.81 vs 0.58; P ConclusionsThe use of the RETAIN model on nursing narratives predicted postoperative LOS effectively for patients who underwent ovarian cancer surgery. These findings suggest that accurate and interpretable deep learning information obtained shortly after surgery may accurately predict prolonged LOS.https://medinform.jmir.org/2023/1/e45377 |
| spellingShingle | Sungjoo Han Yong Bum Kim Jae Hong No Dong Hoon Suh Kidong Kim Soyeon Ahn Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study JMIR Medical Informatics |
| title | Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study |
| title_full | Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study |
| title_fullStr | Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study |
| title_full_unstemmed | Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study |
| title_short | Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study |
| title_sort | predicting postoperative hospital stays using nursing narratives and the reverse time attention retain model retrospective cohort study |
| url | https://medinform.jmir.org/2023/1/e45377 |
| work_keys_str_mv | AT sungjoohan predictingpostoperativehospitalstaysusingnursingnarrativesandthereversetimeattentionretainmodelretrospectivecohortstudy AT yongbumkim predictingpostoperativehospitalstaysusingnursingnarrativesandthereversetimeattentionretainmodelretrospectivecohortstudy AT jaehongno predictingpostoperativehospitalstaysusingnursingnarrativesandthereversetimeattentionretainmodelretrospectivecohortstudy AT donghoonsuh predictingpostoperativehospitalstaysusingnursingnarrativesandthereversetimeattentionretainmodelretrospectivecohortstudy AT kidongkim predictingpostoperativehospitalstaysusingnursingnarrativesandthereversetimeattentionretainmodelretrospectivecohortstudy AT soyeonahn predictingpostoperativehospitalstaysusingnursingnarrativesandthereversetimeattentionretainmodelretrospectivecohortstudy |