{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T02:12:08Z","timestamp":1768011128364,"version":"3.49.0"},"reference-count":27,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T00:00:00Z","timestamp":1575936000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Acta Paediatrica"],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Aim<\/jats:title><jats:p>The role of machine learning on clinical documentation for predictive outcomes remains undefined. We aimed to compare three neural networks on inpatient providers\u2019 notes to predict mortality in neonatal hypoxic\u2010ischaemic encephalopathy (HIE).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Using Children's Hospitals Neonatal Database, non\u2010anomalous neonates with HIE treated with therapeutic hypothermia were identified at a single\u2010centre. Data were linked with the initial seven days of documentation. Exposures were derived using the databases and applying convolutional and two recurrent neural networks. The primary outcome was mortality. The predictive accuracy and performance measures for models were determined.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The cohort included 52 eligible infants. Most infants survived (n\u00a0=\u00a036, 69%) and 23 had severe HIE (44%). Neural networks performed above baseline and differed in their median accuracy for predicting mortality (<jats:italic>P<\/jats:italic>\u00a0=\u00a0.0001): recurrent models with long short\u2010term memory 69% (25<jats:sup>th<\/jats:sup>, 75<jats:sup>th<\/jats:sup> percentile\u00a065, 73%) and gated\u2010recurrent model units 65% (62, 69%) and convolutional 72% (64, 96%). Convolutional networks\u2019 median specificity was 81% (72, 97%).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The neural network models demonstrated fundamental validity in predicting mortality using inpatient provider documentation. Convolutional models had high specificity for (excluding) mortality in neonatal HIE. These findings provide a platform for future model training and ultimately tool development to assist clinicians in patient assessments and risk stratifications.<\/jats:p><\/jats:sec>","DOI":"10.1111\/apa.15109","type":"journal-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T02:48:27Z","timestamp":1574650107000},"page":"1346-1353","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Machine learning mortality classification in clinical documentation with increased accuracy in visual\u2010based analyses"],"prefix":"10.1111","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1894-0044","authenticated-orcid":false,"given":"Susan M.","family":"Slattery","sequence":"first","affiliation":[{"name":"Stanley Manne Children\u2019s Research Institute Chicago IL USA"},{"name":"Feinberg School of Medicine Northwestern University Chicago IL USA"},{"name":"Department of Paediatrics Ann &amp; Robert H. Lurie Children\u2019s Hospital of Chicago Chicago IL USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9244-2321","authenticated-orcid":false,"given":"Daniel C.","family":"Knight","sequence":"additional","affiliation":[{"name":"McCormick School of Engineering Evanston IL USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6061-220X","authenticated-orcid":false,"given":"Debra E.","family":"Weese\u2010Mayer","sequence":"additional","affiliation":[{"name":"Stanley Manne Children\u2019s Research Institute Chicago IL USA"},{"name":"Feinberg School of Medicine Northwestern University Chicago IL USA"},{"name":"Department of Paediatrics Ann &amp; Robert H. Lurie Children\u2019s Hospital of Chicago Chicago IL USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3979-0738","authenticated-orcid":false,"given":"William A.","family":"Grobman","sequence":"additional","affiliation":[{"name":"Stanley Manne Children\u2019s Research Institute Chicago IL USA"},{"name":"Feinberg School of Medicine Northwestern University Chicago IL USA"},{"name":"Department of Obstetrics and Gynaecology Feinberg School of Medicine Chicago IL USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5028-473X","authenticated-orcid":false,"given":"Doug C.","family":"Downey","sequence":"additional","affiliation":[{"name":"McCormick School of Engineering Evanston IL USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3363-9663","authenticated-orcid":false,"given":"Karna","family":"Murthy","sequence":"additional","affiliation":[{"name":"Stanley Manne Children\u2019s Research Institute Chicago IL USA"},{"name":"Feinberg School of Medicine Northwestern University Chicago IL USA"},{"name":"Department of Paediatrics Ann &amp; Robert H. Lurie Children\u2019s Hospital of Chicago Chicago IL USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,12,10]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy098"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1"},{"key":"e_1_2_10_4_1","unstructured":"AczonM LedbetterD HoL et al.Dynamic Mortality Risk Predictions in Pediatric Critical Care Using Recurrent Neural Networks. arXiv e\u2010prints [serial. online].2017;https:\/\/ui.adsabs.harvard.edu\/abs\/2017arXiv170106675A"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.08.015"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy122"},{"key":"e_1_2_10_7_1","unstructured":"ChungJ GulcehreC ChoK BengioY.Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv e\u2010prints [serial. online].2014;https:\/\/ui.adsabs.harvard.edu\/abs\/2014arXiv1412.3555C"},{"key":"e_1_2_10_8_1","unstructured":"LiptonZC BerkowitzJ ElkanC.A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv e\u2010prints [serial. online].2015;https:\/\/ui.adsabs.harvard.edu\/abs\/2015arXiv150600019L"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"LiX WuX.Constructing Long Short\u2010Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition. arXiv e\u2010prints [serial. online].2014;https:\/\/ui.adsabs.harvard.edu\/abs\/2014arXiv1410.4281L","DOI":"10.1109\/ICASSP.2015.7178826"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"2","key":"e_1_2_10_11_1","first-page":"361","article-title":"Using recurrent neural network models for early detection of heart failure onset","volume":"24","author":"Choi E","year":"2017","journal-title":"JAMIA"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooy061"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2700722"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2017-020124"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/jp.2014.26"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/jp.2014.190"},{"issue":"76","key":"e_1_2_10_18_1","first-page":"e1","article-title":"Intercenter Cost Variation for Perinatal Hypoxic\u2010Ischemic Encephalopathy in the Era of Therapeutic Hypothermia","volume":"173","author":"Massaro AN","year":"2016","journal-title":"J Pediatr"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2012.02.047"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.siny.2014.10.006"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-6773.2005.00444.x"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.09.008"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.07.006"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.06.010"},{"key":"e_1_2_10_26_1","unstructured":"RazavianN MarcusJ SontagD.Multi\u2010task Prediction of Disease Onsets from Longitudinal Lab Tests. arXiv e\u2010prints [serial. online].2016;https:\/\/ui.adsabs.harvard.edu\/abs\/2016arXiv160800647R"},{"key":"e_1_2_10_27_1","first-page":"473","article-title":"Bidirectional RNN for medical event detection in electronic health records","volume":"2016","author":"Jagannatha AN","year":"2016","journal-title":"Proc Conf"},{"key":"e_1_2_10_28_1","unstructured":"SureshH HuntN JohnsonA CeliLA SzolovitsP GhassemiM.Clinical Intervention Prediction and Understanding using Deep Networks. arXiv e\u2010prints [serial. online].2017;https:\/\/ui.adsabs.harvard.edu\/abs\/2017arXiv170508498S"}],"container-title":["Acta Paediatrica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/apa.15109","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/apa.15109","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/apa.15109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T03:05:55Z","timestamp":1693969555000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/apa.15109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,10]]},"references-count":27,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["10.1111\/apa.15109"],"URL":"https:\/\/doi.org\/10.1111\/apa.15109","archive":["Portico"],"relation":{},"ISSN":["0803-5253","1651-2227"],"issn-type":[{"value":"0803-5253","type":"print"},{"value":"1651-2227","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,10]]},"assertion":[{"value":"2019-07-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-11-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-12-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}