Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use
Objective Clinical notes contain information that has not been documented elsewhere, including responses to treatment and clinical findings, which are crucial for predicting key outcomes in patients in acute care. In this study, we propose the automatic annotation of phenotypes from clinical notes a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2022-02-01
|
| Series: | BMJ Health & Care Informatics |
| Online Access: | https://informatics.bmj.com/content/29/1/e100519.full |
| _version_ | 1797784212214906880 |
|---|---|
| author | Jingqing Zhang Luis Daniel Bolanos Trujillo Ashwani Tanwar Julia Ive Vibhor Gupta Yike Guo |
| author_facet | Jingqing Zhang Luis Daniel Bolanos Trujillo Ashwani Tanwar Julia Ive Vibhor Gupta Yike Guo |
| author_sort | Jingqing Zhang |
| collection | DOAJ |
| description | Objective Clinical notes contain information that has not been documented elsewhere, including responses to treatment and clinical findings, which are crucial for predicting key outcomes in patients in acute care. In this study, we propose the automatic annotation of phenotypes from clinical notes as a method to capture essential information to predict outcomes in the intensive care unit (ICU). This information is complementary to typically used vital signs and laboratory test results.Methods In this study, we developed a novel phenotype annotation model to extract the phenotypical features of patients, which were then used as input features of predictive models to predict ICU patient outcomes. We demonstrated and validated this approach by conducting experiments on three ICU prediction tasks, including in-hospital mortality, physiological decompensation and length of stay (LOS) for over 24 000 patients using the Medical Information Mart for Intensive Care (MIMIC-III) dataset.Results The predictive models incorporating phenotypical information achieved 0.845 (area under the curve–receiver operating characteristic (AUC-ROC)) for in-hospital mortality, 0.839 (AUC-ROC) for physiological decompensation and 0.430 (kappa) for LOS, all of which consistently outperformed the baseline models using only vital signs and laboratory test results. Moreover, we conducted a thorough interpretability study showing that phenotypes provide valuable insights at both the patient and cohort levels.Conclusion The proposed approach demonstrates that phenotypical information complements traditionally used vital signs and laboratory test results and significantly improves the accuracy of outcome prediction in the ICU. |
| first_indexed | 2024-03-13T00:36:41Z |
| format | Article |
| id | doaj.art-5320a728a2e54424b17326cf9f44357e |
| institution | Directory Open Access Journal |
| issn | 2632-1009 |
| language | English |
| last_indexed | 2024-03-13T00:36:41Z |
| publishDate | 2022-02-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Health & Care Informatics |
| spelling | doaj.art-5320a728a2e54424b17326cf9f44357e2023-07-09T22:30:07ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092022-02-0129110.1136/bmjhci-2021-100519Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit useJingqing Zhang0Luis Daniel Bolanos Trujillo1Ashwani Tanwar2Julia Ive3Vibhor Gupta4Yike Guo5Pangaea Data Limited, London, UKPangaea Data Limited, London, UKPangaea Data Limited, London, UKPangaea Data Limited, London, UKPangaea Data Limited, London, UKPangaea Data Limited, London, UKObjective Clinical notes contain information that has not been documented elsewhere, including responses to treatment and clinical findings, which are crucial for predicting key outcomes in patients in acute care. In this study, we propose the automatic annotation of phenotypes from clinical notes as a method to capture essential information to predict outcomes in the intensive care unit (ICU). This information is complementary to typically used vital signs and laboratory test results.Methods In this study, we developed a novel phenotype annotation model to extract the phenotypical features of patients, which were then used as input features of predictive models to predict ICU patient outcomes. We demonstrated and validated this approach by conducting experiments on three ICU prediction tasks, including in-hospital mortality, physiological decompensation and length of stay (LOS) for over 24 000 patients using the Medical Information Mart for Intensive Care (MIMIC-III) dataset.Results The predictive models incorporating phenotypical information achieved 0.845 (area under the curve–receiver operating characteristic (AUC-ROC)) for in-hospital mortality, 0.839 (AUC-ROC) for physiological decompensation and 0.430 (kappa) for LOS, all of which consistently outperformed the baseline models using only vital signs and laboratory test results. Moreover, we conducted a thorough interpretability study showing that phenotypes provide valuable insights at both the patient and cohort levels.Conclusion The proposed approach demonstrates that phenotypical information complements traditionally used vital signs and laboratory test results and significantly improves the accuracy of outcome prediction in the ICU.https://informatics.bmj.com/content/29/1/e100519.full |
| spellingShingle | Jingqing Zhang Luis Daniel Bolanos Trujillo Ashwani Tanwar Julia Ive Vibhor Gupta Yike Guo Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use BMJ Health & Care Informatics |
| title | Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use |
| title_full | Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use |
| title_fullStr | Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use |
| title_full_unstemmed | Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use |
| title_short | Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use |
| title_sort | clinical utility of automatic phenotype annotation in unstructured clinical notes intensive care unit use |
| url | https://informatics.bmj.com/content/29/1/e100519.full |
| work_keys_str_mv | AT jingqingzhang clinicalutilityofautomaticphenotypeannotationinunstructuredclinicalnotesintensivecareunituse AT luisdanielbolanostrujillo clinicalutilityofautomaticphenotypeannotationinunstructuredclinicalnotesintensivecareunituse AT ashwanitanwar clinicalutilityofautomaticphenotypeannotationinunstructuredclinicalnotesintensivecareunituse AT juliaive clinicalutilityofautomaticphenotypeannotationinunstructuredclinicalnotesintensivecareunituse AT vibhorgupta clinicalutilityofautomaticphenotypeannotationinunstructuredclinicalnotesintensivecareunituse AT yikeguo clinicalutilityofautomaticphenotypeannotationinunstructuredclinicalnotesintensivecareunituse |