{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T23:37:28Z","timestamp":1777678648777,"version":"3.51.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009712","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000}}],"reference-count":27,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2021,12,21]],"date-time":"2021-12-21T00:00:00Z","timestamp":1640044800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["RAPID2031195."],"award-info":[{"award-number":["RAPID2031195."]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1T32GM136577"],"award-info":[{"award-number":["1T32GM136577"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joseph and Helen Pardoll Scholarship for MSTP Students"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    Hypoxemia is a significant driver of mortality and poor clinical outcomes in conditions such as brain injury and cardiac arrest in critically ill patients, including COVID-19 patients. Given the host of negative clinical outcomes attributed to hypoxemia, identifying patients likely to experience hypoxemia would offer valuable opportunities for early and thus more effective intervention. We present SWIFT (\n                    <jats:underline>S<\/jats:underline>\n                    pO\n                    <jats:sub>2<\/jats:sub>\n                    <jats:underline>W<\/jats:underline>\n                    aveform\n                    <jats:underline>I<\/jats:underline>\n                    CU\n                    <jats:underline>F<\/jats:underline>\n                    orecasting\n                    <jats:underline>T<\/jats:underline>\n                    echnique), a deep learning model that predicts blood oxygen saturation (SpO\n                    <jats:sub>2<\/jats:sub>\n                    ) waveforms 5 and 30 minutes in the future using only prior SpO\n                    <jats:sub>2<\/jats:sub>\n                    values as inputs. When tested on novel data, SWIFT predicts more than 80% and 60% of hypoxemic events in critically ill and COVID-19 patients, respectively. SWIFT also predicts SpO\n                    <jats:sub>2<\/jats:sub>\n                    waveforms with average MSE below .0007. SWIFT predicts both occurrence and magnitude of potential hypoxemic events 30 minutes in the future, allowing it to be used to inform clinical interventions, patient triaging, and optimal resource allocation. SWIFT may be used in clinical decision support systems to inform the management of critically ill patients during the COVID-19 pandemic and beyond.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1009712","type":"journal-article","created":{"date-parts":[[2021,12,21]],"date-time":"2021-12-21T13:50:33Z","timestamp":1640094633000},"page":"e1009712","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["SWIFT: A deep learning approach to prediction of hypoxemic events in critically-Ill patients using SpO2 waveform prediction"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-6511","authenticated-orcid":true,"given":"Akshaya V.","family":"Annapragada","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6193-7134","authenticated-orcid":true,"given":"Joseph L.","family":"Greenstein","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1077-4010","authenticated-orcid":true,"given":"Sanjukta N.","family":"Bose","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5190-6481","authenticated-orcid":true,"given":"Bradford D.","family":"Winters","sequence":"additional","affiliation":[]},{"given":"Sridevi V.","family":"Sarma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1719-1651","authenticated-orcid":true,"given":"Raimond L.","family":"Winslow","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2021,12,21]]},"reference":[{"key":"pcbi.1009712.ref001","doi-asserted-by":"crossref","unstructured":"SRLF Trial Group. Hypoxemia in the ICU: prevalence, treatment, and outcome. Ann Intensive Care [Internet]. 2018 Aug 13 [cited 2020 Dec 13];8. Available from: https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC6089859\/","DOI":"10.1186\/s13613-018-0424-4"},{"issue":"5","key":"pcbi.1009712.ref002","first-page":"297","article-title":"Hypoxia and surgical patients\u2014prevention and treatment of an unnecessary cause of morbidity and mortality.","volume":"46","author":"L Strachan","year":"2001","journal-title":"J R Coll Surg Edinb."},{"key":"pcbi.1009712.ref003","article-title":"Severe Covid-19.","author":"DA Berlin","year":"2020","journal-title":"N Engl J Med"},{"key":"pcbi.1009712.ref004","article-title":"Mechanical Ventilation Supply and Options for the COVID-19 Pandemic: Leveraging All Available Resources for a Limited Resource in a Crisis.","author":"M Dar","year":"2020","journal-title":"Ann Am Thorac Soc."},{"issue":"9","key":"pcbi.1009712.ref005","doi-asserted-by":"crossref","first-page":"e1121","DOI":"10.1016\/S2214-109X(20)30287-4","article-title":"Pulse oximetry in low-resource settings during the COVID-19 pandemic","volume":"8","author":"N Starr","year":"2020","journal-title":"Lancet Glob Health"},{"issue":"4","key":"pcbi.1009712.ref006","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1088\/0967-3334\/35\/4\/639","article-title":"Evaluating predictions of critical oxygen desaturation events.","volume":"35","author":"H Elmoaqet","year":"2014","journal-title":"Physiol Meas."},{"key":"pcbi.1009712.ref007","article-title":"Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning.","author":"G Erion","year":"2017","journal-title":"ArXiv171200563 Cs Stat"},{"issue":"2","key":"pcbi.1009712.ref008","doi-asserted-by":"crossref","first-page":"e0198921","DOI":"10.1371\/journal.pone.0198921","article-title":"Using machine learning models to predict oxygen saturation following ventilator support adjustment in critically ill children: A single center pilot study.","volume":"14","author":"S Ghazal","year":"2019","journal-title":"PloS One"},{"issue":"10","key":"pcbi.1009712.ref009","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"SM Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"issue":"1","key":"pcbi.1009712.ref010","doi-asserted-by":"crossref","first-page":"6085","DOI":"10.1038\/s41598-018-24271-9","article-title":"Recurrent Neural Networks for Multivariate Time Series with Missing Values.","volume":"8","author":"Z Che","year":"2018","journal-title":"Sci Rep."},{"issue":"7","key":"pcbi.1009712.ref011","doi-asserted-by":"crossref","first-page":"e0218942","DOI":"10.1371\/journal.pone.0218942","article-title":"Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory.","volume":"14","author":"Y-W Lin","year":"2019","journal-title":"PLOS ONE."},{"key":"pcbi.1009712.ref012","article-title":"Learning to Diagnose with LSTM Recurrent Neural Networks.","author":"ZC Lipton","year":"2017","journal-title":"ArXiv151103677 Cs"},{"issue":"1","key":"pcbi.1009712.ref013","doi-asserted-by":"crossref","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative Research Database, a freely available multi-center database for critical care research.","volume":"5","author":"TJ Pollard","year":"2018","journal-title":"Sci Data."},{"issue":"3","key":"pcbi.1009712.ref014","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/cid\/ciq076","article-title":"Oxygen saturations less than 92% are associated with major adverse events in outpatients with pneumonia: a population-based cohort study","volume":"52","author":"SR Majumdar","year":"2011","journal-title":"Clin Infect Dis Off Publ Infect Dis Soc Am"},{"issue":"1","key":"pcbi.1009712.ref015","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1186\/s12916-020-01735-2","article-title":"Considerations for target oxygen saturation in COVID-19 patients: are we under-shooting?","volume":"18","author":"N Shenoy","year":"2020","journal-title":"BMC Med."},{"key":"pcbi.1009712.ref016","unstructured":"World Health Organization. Pulse Oximetry Training Manual. 2011."},{"issue":"2","key":"pcbi.1009712.ref017","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1183\/20734735.038612","article-title":"Pulse oximetry in low-resource settings.","volume":"9","author":"LJ Herbert","year":"2012","journal-title":"Breathe."},{"issue":"1","key":"pcbi.1009712.ref018","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s13643-020-01326-5","article-title":"The prevalence of hypoxemia among pediatric and adult patients presenting to healthcare facilities in low- and middle-income countries: protocol for a systematic review and meta-analysis.","volume":"9","author":"F Lam","year":"2020","journal-title":"Syst Rev."},{"key":"pcbi.1009712.ref019","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.smhl.2018.07.002","article-title":"Reducing Pulse Oximetry False Alarms Without Missing Life-Threatening Events.","volume":"10","author":"H Nguyen","year":"2018","journal-title":"Smart Health Amst Neth."},{"issue":"1","key":"pcbi.1009712.ref020","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1097\/CCM.0000000000002803","article-title":"Technological Distractions (Part 2): A Summary of Approaches to Manage Clinical Alarms With Intent to Reduce Alarm Fatigue.","volume":"46","author":"BD Winters","year":"2018","journal-title":"Crit Care Med."},{"issue":"4","key":"pcbi.1009712.ref021","doi-asserted-by":"crossref","first-page":"378","DOI":"10.4037\/NCI.0b013e3182a903f9","article-title":"Alarm fatigue: a patient safety concern.","volume":"24","author":"S Sendelbach","year":"2013","journal-title":"AACN Adv Crit Care."},{"issue":"25","key":"pcbi.1009712.ref022","doi-asserted-by":"crossref","first-page":"2477","DOI":"10.1056\/NEJMc2029240","article-title":"Racial Bias in Pulse Oximetry Measurement","volume":"383","author":"MW Sjoding","year":"2020","journal-title":"N Engl J Med"},{"key":"pcbi.1009712.ref023","doi-asserted-by":"crossref","first-page":"56","DOI":"10.25080\/Majora-92bf1922-00a","article-title":"Data Structures for Statistical Computing in Python","author":"W. McKinney","year":"2010","journal-title":"Proc 9th Python Sci Conf."},{"issue":"7825","key":"pcbi.1009712.ref024","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"issue":"85","key":"pcbi.1009712.ref025","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python.","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res."},{"key":"pcbi.1009712.ref026","volume":"19","author":"M Abadi","journal-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems."},{"key":"pcbi.1009712.ref027","unstructured":"Chollet F. Keras [Internet]. 2015. Available from: \\url{https:\/\/keras.io}"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009712","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T13:41:33Z","timestamp":1641390093000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009712"}},"subtitle":[],"editor":[{"given":"Benjamin","family":"Althouse","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,12,21]]},"references-count":27,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009712","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.02.25.21252234","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,21]]}}}