{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:18:48Z","timestamp":1777450728901,"version":"3.51.4"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T00:00:00Z","timestamp":1618963200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Electronic health record documentation by intensive care unit (ICU) clinicians may predict patient outcomes. However, it is unclear whether physician and nursing notes differ in their ability to predict short-term ICU prognosis. We aimed to investigate and compare the ability of physician and nursing notes, written in the first 48 hours of admission, to predict ICU length of stay and mortality using 3 analytical methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>This was a retrospective cohort study with split sampling for model training and testing. We included patients \u226518 years of age admitted to the ICU at Beth Israel Deaconess Medical Center in Boston, Massachusetts, from 2008 to 2012. Physician or nursing notes generated within the first 48 hours of admission were used with standard machine learning methods to predict outcomes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>For the primary outcome of composite score of ICU length of stay \u22657 days or in-hospital mortality, the gradient boosting model had better performance than the logistic regression and random forest models. Nursing and physician notes achieved area under the curves (AUCs) of 0.826 and 0.796, respectively, with even better predictive power when combined (AUC, 0.839).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Models using only nursing notes more accurately predicted short-term prognosis than did models using only physician notes, but in combination, the models achieved the greatest accuracy in prediction.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Our findings demonstrate that statistical models derived from text analysis in the first 48 hours of ICU admission can predict patient outcomes. Physicians\u2019 and nurses\u2019 notes are both uniquely important in mortality prediction and combining these notes can produce a better predictive model.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocab051","type":"journal-article","created":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T20:12:38Z","timestamp":1615234358000},"page":"1660-1666","source":"Crossref","is-referenced-by-count":27,"title":["Using nursing notes to improve clinical outcome prediction in intensive care patients: A retrospective cohort study"],"prefix":"10.1093","volume":"28","author":[{"given":"Kexin","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8075-9735","authenticated-orcid":false,"given":"Tamryn F","family":"Gray","sequence":"additional","affiliation":[{"name":"Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts, USA"},{"name":"Phyllis F. Cantor Center for Research in Nursing and Patient Care Services, Dana-Farber Cancer Institute, Boston, Massachusetts, USA"},{"name":"Division of Palliative Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, Massachusetts, USA"},{"name":"Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA"}]},{"given":"Santiago","family":"Romero-Brufau","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA"},{"name":"Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"James A","family":"Tulsky","sequence":"additional","affiliation":[{"name":"Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts, USA"},{"name":"Division of Palliative Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, Massachusetts, USA"},{"name":"Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA"}]},{"given":"Charlotta","family":"Lindvall","sequence":"additional","affiliation":[{"name":"Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts, USA"},{"name":"Division of Palliative Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, Massachusetts, USA"},{"name":"Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,4,21]]},"reference":[{"issue":"7","key":"2021073020263616100_ocab051-B1","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1097\/CCM.0000000000003148","article-title":"Inclusion of unstructured clinical text improves early prediction of death or prolonged ICU stay","volume":"46","author":"Weissman","year":"2018","journal-title":"Crit Care Med"},{"issue":"1","key":"2021073020263616100_ocab051-B2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1093\/intqhc\/mzv112","article-title":"ICU physicians are unable to accurately predict length of stay at admission: A prospective study","volume":"28","author":"Nassar","year":"2016","journal-title":"Int J Qual Health Care"},{"issue":"5","key":"2021073020263616100_ocab051-B3","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1097\/01.CCM.0000126402.51524.52","article-title":"Clinician predictions of intensive care unit mortality","volume":"32","author":"Rocker","year":"2004","journal-title":"Crit Care Med"},{"issue":"2","key":"2021073020263616100_ocab051-B4","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1513\/AnnalsATS.201306-141OC","article-title":"Objective factors associated with physicians\u2019 and nurses\u2019 perceptions of intensive care unit capacity strain","volume":"11","author":"Kerlin","year":"2014","journal-title":"Ann Am Thorac Soc"},{"issue":"1","key":"2021073020263616100_ocab051-B5","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s13054-017-1609-1","article-title":"SOFA and mortality endpoints in randomized controlled trials: a systematic review and meta-regression analysis","volume":"21","author":"de Grooth","year":"2017","journal-title":"Crit Care"},{"issue":"7","key":"2021073020263616100_ocab051-B6","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction\/failure","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Med"},{"issue":"26","key":"2021073020263616100_ocab051-B7","doi-asserted-by":"crossref","first-page":"2448","DOI":"10.1056\/NEJMp1303295","article-title":"Uncertainty: the other side of prognosis","volume":"368","author":"Smith","year":"2013","journal-title":"N Engl J Med"},{"issue":"22","key":"2021073020263616100_ocab051-B8","doi-asserted-by":"crossref","first-page":"2715","DOI":"10.1200\/JCO.2012.42.4564","article-title":"Reasons why physicians do not have discussions about poor prognosis, why it matters, and what can be improved","volume":"30","author":"Mack","year":"2012","journal-title":"J Clin Oncol"},{"issue":"1","key":"2021073020263616100_ocab051-B9","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1097\/00005650-199801000-00004","article-title":"Comorbidity measures for use with administrative data","volume":"36","author":"Elixhauser","year":"1998","journal-title":"Med Care"},{"issue":"4","key":"2021073020263616100_ocab051-B10","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1097\/NCN.0b013e3181a91b58","article-title":"Exploring the ability of natural language processing to extract data from nursing narratives","volume":"27","author":"Hyun","year":"2009","journal-title":"Comput Inform Nurs"},{"issue":"2","key":"2021073020263616100_ocab051-B11","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1089\/jpm.2018.0326","article-title":"Natural language processing to assess end-of-life quality indicators in cancer patients receiving palliative surgery","volume":"22","author":"Lindvall","year":"2019","journal-title":"J Palliat Med"},{"issue":"13","key":"2021073020263616100_ocab051-B12","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1001\/jama.2013.393","article-title":"The inevitable application of big data to health care","volume":"309","author":"Murdoch","year":"2013","journal-title":"JAMA"},{"issue":"2","key":"2021073020263616100_ocab051-B13","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1177\/1460458219850323","article-title":"Predicting hospital mortality for intensive care unit patients: time-series analysis","volume":"26","author":"Awad","year":"2020","journal-title":"Health Informatics J"},{"issue":"4","key":"2021073020263616100_ocab051-B14","doi-asserted-by":"crossref","first-page":"232","DOI":"10.4258\/hir.2011.17.4.232","article-title":"A comparison of intensive care unit mortality prediction models through the use of data mining techniques","volume":"17","author":"Kim","year":"2011","journal-title":"Healthc Inform Res"},{"issue":"3","key":"2021073020263616100_ocab051-B15","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.artmed.2005.07.006","article-title":"Mortality assessment in intensive care units via adverse events using artificial neural networks","volume":"36","author":"Silva","year":"2006","journal-title":"Artif Intell Med"},{"issue":"8","key":"2021073020263616100_ocab051-B16","first-page":"50","article-title":"Clinical communication and patient safety","volume":"80","author":"Scalise","year":"2006","journal-title":"Hosp Heal Netw"},{"issue":"8","key":"2021073020263616100_ocab051-B17","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1097\/00006247-199608000-00010","article-title":"Health care focus documentation\u2014more efficient charting","volume":"27","author":"Scoates","year":"1996","journal-title":"Nurs Manage"},{"key":"2021073020263616100_ocab051-B18","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.ijmedinf.2018.02.002","article-title":"Physician nurse care: a new use of UMLS to measure professional contribution: Are we talking about the same patient a new graph matching algorithm?","volume":"113","author":"Boyd","year":"2018","journal-title":"Int J Med Inform"},{"issue":"4","key":"2021073020263616100_ocab051-B19","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1093\/jamiaopen\/ooz033","article-title":"The fifth vital sign? Nurse worry predicts inpatient deterioration within 24 hours","volume":"2","author":"Romero-Brufau","year":"2019","journal-title":"JAMIA Open"},{"issue":"4","key":"2021073020263616100_ocab051-B20","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/j.cnc.2018.07.002","article-title":"Increased nursing participation in multidisciplinary rounds to enhance communication, patient safety, and parent satisfaction","volume":"30","author":"Dittman","year":"2018","journal-title":"Crit Care Nurs Clin North Am"},{"issue":"6","key":"2021073020263616100_ocab051-B21","doi-asserted-by":"crossref","first-page":"526","DOI":"10.3109\/13561820.2014.934338","article-title":"Physician and nursing perceptions concerning interprofessional communication and collaboration","volume":"28","author":"Matziou","year":"2014","journal-title":"J Interprof Care"},{"issue":"7","key":"2021073020263616100_ocab051-B22","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1038\/sj.bjc.6603684","article-title":"Brief smoking cessation advice from practice nurses during routine cervical smear tests appointments: a cluster randomised controlled trial assessing feasibility, acceptability and potential effectiveness","volume":"96","author":"Hall","year":"2007","journal-title":"Br J Cancer"},{"issue":"3","key":"2021073020263616100_ocab051-B23","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"issue":"6","key":"2021073020263616100_ocab051-B24","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1016\/j.jpainsymman.2019.12.374","article-title":"Deep natural language processing identifies variation in care preference documentation","volume":"59","author":"Udelsman","year":"2020","journal-title":"J Pain Symptom Manage"},{"issue":"12","key":"2021073020263616100_ocab051-B25","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1093\/aje\/kwx222","article-title":"Measurement error due to patient flow in estimates of intensive care unit length of stay","volume":"186","author":"Harhay","year":"2017","journal-title":"Am J Epidemiol"},{"key":"2021073020263616100_ocab051-B26","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.jbi.2015.02.003","article-title":"Efficient and sparse feature selection for biomedical text classification via the elastic net: application to ICU risk stratification from nursing notes","volume":"54","author":"Marafino","year":"2015","journal-title":"J Biomed Inform"},{"issue":"1","key":"2021073020263616100_ocab051-B27","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1186\/s13054-015-0950-5","article-title":"Nurses\u2019 worry or concern and early recognition of deteriorating patients on general wards in acute care hospitals: a systematic review","volume":"19","author":"Douw","year":"2015","journal-title":"Crit Care"},{"issue":"3","key":"2021073020263616100_ocab051-B28","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1177\/1062860608330825","article-title":"End-of-life decision making in the intensive care unit: physician and nurse perspectives","volume":"24","author":"Westphal","year":"2009","journal-title":"Am J Med Qual"},{"issue":"2","key":"2021073020263616100_ocab051-B29","doi-asserted-by":"crossref","first-page":"430","DOI":"10.4338\/ACI-2014-01-RA-0003","article-title":"What do physicians read (and ignore) in electronic progress notes?","volume":"5","author":"Brown","year":"2014","journal-title":"Appl Clin Inform"},{"issue":"3","key":"2021073020263616100_ocab051-B30","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1136\/eb-2018-102902","article-title":"Nurses and physicians bring different perspectives to end-of-life decisions in intensive care units","volume":"21","author":"McAndrew","year":"2018","journal-title":"Evid Based Nurs"},{"issue":"4","key":"2021073020263616100_ocab051-B31","doi-asserted-by":"crossref","first-page":"e372","DOI":"10.1097\/CCM.0000000000002099","article-title":"Improving intensive care unit-based palliative care delivery: A multi-center, multidisciplinary survey of critical care clinician attitudes and beliefs","volume":"45","author":"Wysham","year":"2017","journal-title":"Crit Care Med"},{"issue":"5","key":"2021073020263616100_ocab051-B32","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1055\/s-0039-3401814","article-title":"Unsupervised machine learning of topics documented by nurses about hospitalized patients prior to a rapid-response event","volume":"10","author":"Korach","year":"2019","journal-title":"Appl Clin Inform"},{"issue":"4","key":"2021073020263616100_ocab051-B33","doi-asserted-by":"crossref","first-page":"306","DOI":"10.4037\/ajcc2013426","article-title":"Relationship between nursing documentation and patients\u2019 mortality","volume":"22","author":"Collins","year":"2013","journal-title":"Am J Crit Care"},{"issue":"1","key":"2021073020263616100_ocab051-B34","first-page":"103","article-title":"Monitoring ICU mortality risk with a long short-term memory recurrent neural network","volume":"25","author":"Yu","year":"2020","journal-title":"Pacific Symp Biocomput"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/8\/1660\/39502152\/ocab051.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/8\/1660\/39502152\/ocab051.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T23:01:31Z","timestamp":1627686091000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/8\/1660\/6242738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,21]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,4,21]]},"published-print":{"date-parts":[[2021,7,30]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab051","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,8,1]]},"published":{"date-parts":[[2021,4,21]]}}}