Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients.
Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstruct...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262182&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849707843148578816 |
|---|---|
| author | Maria Mahbub Sudarshan Srinivasan Ioana Danciu Alina Peluso Edmon Begoli Suzanne Tamang Gregory D Peterson |
| author_facet | Maria Mahbub Sudarshan Srinivasan Ioana Danciu Alina Peluso Edmon Begoli Suzanne Tamang Gregory D Peterson |
| author_sort | Maria Mahbub |
| collection | DOAJ |
| description | Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients' length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores. |
| format | Article |
| id | doaj-art-3e0af8197a5c4624b85ca3ca663db3c6 |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-3e0af8197a5c4624b85ca3ca663db3c62025-08-20T03:15:48ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01171e026218210.1371/journal.pone.0262182Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients.Maria MahbubSudarshan SrinivasanIoana DanciuAlina PelusoEdmon BegoliSuzanne TamangGregory D PetersonMortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients' length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262182&type=printable |
| spellingShingle | Maria Mahbub Sudarshan Srinivasan Ioana Danciu Alina Peluso Edmon Begoli Suzanne Tamang Gregory D Peterson Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. PLoS ONE |
| title | Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. |
| title_full | Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. |
| title_fullStr | Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. |
| title_full_unstemmed | Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. |
| title_short | Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. |
| title_sort | unstructured clinical notes within the 24 hours since admission predict short mid long term mortality in adult icu patients |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0262182&type=printable |
| work_keys_str_mv | AT mariamahbub unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients AT sudarshansrinivasan unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients AT ioanadanciu unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients AT alinapeluso unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients AT edmonbegoli unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients AT suzannetamang unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients AT gregorydpeterson unstructuredclinicalnoteswithinthe24hourssinceadmissionpredictshortmidlongtermmortalityinadulticupatients |