{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:16:45Z","timestamp":1791047805330,"version":"4.1.0"},"reference-count":23,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T00:00:00Z","timestamp":1694563200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Predicting the duration of ventilation in the ICU helps in assessing the risk of ventilator-induced lung injury, ensuring sufficient oxygenation, and optimizing resource allocation. Prior models provided a prediction of total duration without distinguishing between invasive and non-invasive ventilation. This work proposes two independent gradient boosting regression models for predicting the duration of invasive and non-invasive ventilation based on commonly available ICU features. These models are trained on 2.6 million patient stays across 350 US hospitals between 2010 to 2019. The mean absolute error (MAE) for the prediction of duration was 2.08 days for invasive ventilation and 0.36 days for non-invasive ventilation. The total ventilation duration predicted by our model had MAE of 2.38 days, which outperformed the gold standard (APACHE) with MAE of 3.02 days. The feature importance analysis of the trained models showed that, for invasive ventilation, high average heart rate, diagnosis of respiratory infection and admissions from locations other than the operating room were associated with longer ventilation durations. For non-invasive ventilation, higher respiratory rates and having any GCS measurement were associated with longer durations.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000289","type":"journal-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T20:04:01Z","timestamp":1694635441000},"page":"e0000289","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["Machine learning prediction of the total duration of invasive and non-invasive ventilation During ICU Stay"],"prefix":"10.1371","volume":"2","author":[{"given":"Emma","family":"Schwager","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7867-5610","authenticated-orcid":true,"given":"Mohsen","family":"Nabian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin MacDonald","family":"French","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pam","family":"Amelung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-319X","authenticated-orcid":true,"given":"Louis","family":"Atallah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omar","family":"Badawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"issue":"11","key":"pdig.0000289.ref001","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.4187\/respcare.05073","article-title":"The Impact of Ventilator-Associated Events in Critically Ill Subjects With Prolonged Mechanical Ventilation","volume":"62","author":"H Kobayashi","year":"2017","journal-title":"Respir Care"},{"issue":"10","key":"pdig.0000289.ref002","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1136\/thorax.55.10.819","article-title":"Incidence and causes of non-invasive mechanical ventilation failure after initial success","volume":"55","author":"M Moretti","year":"2000","journal-title":"Thorax"},{"key":"pdig.0000289.ref003","doi-asserted-by":"crossref","first-page":"8885464","DOI":"10.1155\/2020\/8885464","article-title":"Risk Factors Associated with Late Failure of Noninvasive Ventilation in Patients with Chronic Obstructive Pulmonary Disease","volume":"2020","author":"T Chen","year":"2020","journal-title":"Can Respir J"},{"issue":"2","key":"pdig.0000289.ref004","doi-asserted-by":"crossref","first-page":"1602426","DOI":"10.1183\/13993003.02426-2016","article-title":"Official ERS\/ATS clinical practice guidelines: noninvasive ventilation for acute respiratory failure","volume":"50","author":"B Rochwerg","year":"2017","journal-title":"Eur Respir J"},{"issue":"2","key":"pdig.0000289.ref005","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1164\/rccm.200706-893OC","article-title":"Evolution of mechanical ventilation in response to clinical research","volume":"177","author":"A Esteban","year":"2008","journal-title":"Am J Respir Crit Care Med"},{"issue":"10","key":"pdig.0000289.ref006","doi-asserted-by":"crossref","first-page":"2517","DOI":"10.1097\/01.CCM.0000240233.01711.D9","article-title":"Intensive care unit length of stay: Benchmarking based on Acute Physiology and Chronic Health Evaluation (APACHE) IV*","volume":"34","author":"JE Zimmerman","year":"2006","journal-title":"Crit Care Med"},{"issue":"2","key":"pdig.0000289.ref007","first-page":"469","article-title":"Predicting the duration of mechanical ventilation","volume":"110","author":"MG Seneff","year":"1996","journal-title":"The importance of disease and patient characteristics. Chest"},{"issue":"8","key":"pdig.0000289.ref008","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1001\/jama.2016.0291","article-title":"Epidemiology, Patterns of Care, and Mortality for Patients With Acute Respiratory Distress Syndrome in Intensive Care Units in 50 Countries","volume":"315","author":"G Bellani","year":"2016","journal-title":"JAMA"},{"issue":"5","key":"pdig.0000289.ref009","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.1378\/chest.11-0718","article-title":"Benchmark Data From More Than 240,000 Adults That Reflect the Current Practice of Critical Care in the United States","volume":"140","author":"CM Lilly","year":"2011","journal-title":"Chest"},{"issue":"17","key":"pdig.0000289.ref010","doi-asserted-by":"crossref","first-page":"3824","DOI":"10.3390\/jcm10173824","article-title":"Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning","volume":"10","author":"M Sayed","year":"2021","journal-title":"J Clin Med"},{"issue":"1","key":"pdig.0000289.ref011","doi-asserted-by":"crossref","first-page":"5925","DOI":"10.1038\/s41598-023-33159-2","article-title":"Prediction prolonged mechanical ventilation in trauma patients of the intensive care unit according to initial medical factors: a machine learning approach","volume":"13","author":"M Vali","year":"2023","journal-title":"Sci Rep"},{"key":"pdig.0000289.ref012","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.hrtlng.2022.11.005","article-title":"Developing an explainable machine learning model to predict the mechanical ventilation duration of patients with ARDS in intensive care units","volume":"58","author":"Z Wang","year":"2023","journal-title":"Heart Lung"},{"issue":"11","key":"pdig.0000289.ref013","doi-asserted-by":"crossref","first-page":"e1176","DOI":"10.1097\/CCM.0000000000005133","article-title":"Where Is Acute Physiology and Chronic Health Evaluation V?","volume":"49","author":"ES Ringle","year":"2021","journal-title":"Crit Care Med"},{"issue":"5","key":"pdig.0000289.ref014","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1097\/01.CCM.0000215112.84523.F0","article-title":"Acute Physiology and Chronic Health Evaluation (APACHE) IV: hospital mortality assessment for today\u2019s critically ill patients","volume":"34","author":"JE Zimmerman","year":"2006","journal-title":"Crit Care Med"},{"issue":"3","key":"pdig.0000289.ref015","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1097\/CCM.0000000000005750","article-title":"Improving ICU Risk Predictive Models Through Automation Designed for Resiliency Against Documentation Bias","volume":"51","author":"X Liu","year":"2023","journal-title":"Crit Care Med"},{"key":"pdig.0000289.ref016","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [Internet]. New York, NY, USA: Association for Computing Machinery; 2016 [cited 2022 Jul 26]. p. 785\u201394. (KDD \u201816). https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"pdig.0000289.ref017","unstructured":"Lundberg SM, Erion GG, Lee SI. Consistent Individualized Feature Attribution for Tree Ensembles. ArXiv180203888 Cs Stat [Internet]. 2018 Feb 11 [cited 2019 Oct 15]; http:\/\/arxiv.org\/abs\/1802.03888."},{"issue":"3","key":"pdig.0000289.ref018","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1001\/jama.287.3.345","article-title":"Characteristics and outcomes in adult patients receiving mechanical ventilation: a 28-day international study","volume":"287","author":"A Esteban","year":"2002","journal-title":"JAMA"},{"issue":"1","key":"pdig.0000289.ref019","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1164\/ajrccm.157.1.9604014","article-title":"Ventilator-induced Lung Injury","volume":"157","author":"D Dreyfuss","year":"1998","journal-title":"Am J Respir Crit Care Med"},{"issue":"22","key":"pdig.0000289.ref020","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.1056\/NEJMra1208707","article-title":"Ventilator-induced lung injury","volume":"369","author":"AS Slutsky","year":"2013","journal-title":"N Engl J Med"},{"issue":"1","key":"pdig.0000289.ref021","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s40635-017-0121-x","article-title":"Personalizing mechanical ventilation according to physiologic parameters to stabilize alveoli and minimize ventilator induced lung injury (VILI)","volume":"5","author":"GF Nieman","year":"2017","journal-title":"Intensive Care Med Exp"},{"issue":"3","key":"pdig.0000289.ref022","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1177\/1479972316687100","article-title":"APACHE II score cannot predict successful weaning from prolonged mechanical ventilation","volume":"14","author":"A Rojek-Jarmu\u0142a","year":"2017","journal-title":"Chron Respir Dis"},{"key":"pdig.0000289.ref023","unstructured":"Lundberg S, Lee SI. A Unified Approach to Interpreting Model Predictions [Internet]. arXiv; 2017 [cited 2023 Mar 22]. http:\/\/arxiv.org\/abs\/1705.07874."}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T20:04:11Z","timestamp":1694635451000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000289"}},"subtitle":[],"editor":[{"given":"Nadav","family":"Rappoport","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,9,13]]},"references-count":23,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,9,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000289","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,13]]}}}