{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T19:20:40Z","timestamp":1790968840155,"version":"4.1.0"},"reference-count":40,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T00:00:00Z","timestamp":1582588800000},"content-version":"unspecified","delay-in-days":24,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Veterans General Hospitals and the University System of Taiwan Joint Research Program","award":["VGHUST108-G2-4-2"],"award-info":[{"award-number":["VGHUST108-G2-4-2"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2020,1,22]]},"published-print":{"date-parts":[[2020,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Current mortality prediction models used in the intensive care unit (ICU) have a limited role for specific diseases such as influenza, and we aimed to establish an explainable machine learning (ML) model for predicting mortality in critically ill influenza patients using a real-world severe influenza data set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Study design<\/jats:title>\n                    <jats:p>A cross-sectional retrospective multicentre study in Taiwan<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Eight medical centres in Taiwan.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>A total of 336 patients requiring ICU-admission for virology-proven influenza at eight hospitals during an influenza epidemic between October 2015 and March 2016.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>We employed extreme gradient boosting (XGBoost) to establish the prediction model, compared the performance with logistic regression (LR) and random forest (RF), demonstrated the feature importance categorised by clinical domains, and used SHapley Additive exPlanations (SHAP) for visualised interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The data set contained 76 features of the 336 patients with severe influenza. The severity was apparently high, as shown by the high Acute Physiology and Chronic Health Evaluation II score (22, 17 to 29) and pneumonia severity index score (118, 88 to 151). XGBoost model (area under the curve (AUC): 0.842; 95% CI 0.749 to 0.928) outperformed RF (AUC: 0.809; 95% CI 0.629 to 0.891) and LR (AUC: 0.701; 95% CI 0.573 to 0.825) for predicting 30-day mortality. To give clinicians an intuitive understanding of feature exploitation, we stratified features by the clinical domain. The cumulative feature importance in the fluid balance domain, ventilation domain, laboratory data domain, demographic and symptom domain, management domain and severity score domain was 0.253, 0.113, 0.177, 0.140, 0.152 and 0.165, respectively. We further used SHAP plots to illustrate associations between features and 30-day mortality in critically ill influenza patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We used a real-world data set and applied an ML approach, mainly XGBoost, to establish a practical and explainable mortality prediction model in critically ill influenza patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2019-033898","type":"journal-article","created":{"date-parts":[[2020,2,26]],"date-time":"2020-02-26T06:15:27Z","timestamp":1582697727000},"page":"e033898","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":97,"title":["Using a machine learning approach to predict mortality in critically ill influenza patients: a cross-sectional retrospective multicentre study in Taiwan"],"prefix":"10.1136","volume":"10","author":[{"given":"Chien-An","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen-Chun","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, National Chung Hsing University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinn-Jye","family":"Liang","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care, Department of Internal Medicine, China Medical University Hospital, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Chien","family":"Wang","sequence":"additional","affiliation":[{"name":"Division of Chest Medicine, Department of Internal Medicine, National Taiwan University Hospital, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Feng","family":"Fang","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan"},{"name":"Department of Respiratory Care, Chang Gung University of Science and Technology, Chiayi, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chau-Chyun","family":"Sheu","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care Medicine, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan"},{"name":"School of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wann-Cherng","family":"Perng","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuang-Yao","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Chest Medicine, Taipei Veterans General Hospital, Taipei, Taiwan"},{"name":"Institute of Emergency and Critical Care Medicine, School of Medicine, National Yang-Ming University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuo-Chin","family":"Kao","sequence":"additional","affiliation":[{"name":"Department of Thoracic Medicine, Chang Gung Memorial Hospital, Taoyuan, Taiwan"},{"name":"Department of Respiratory Therapy, Chang Gung University College of Medicine, Taoyuan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chieh-Liang","family":"Wu","sequence":"additional","affiliation":[{"name":"Center for Quality Management, Taichung Veterans General Hospital, Taichung, Taiwan"},{"name":"Division of Chest, Department of Internal Medicine, Taichung Veterans General Hospital, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chwei-Shyong","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, National Chung Hsing University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Yen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9631-8934","authenticated-orcid":false,"given":"Wen-Cheng","family":"Chao","sequence":"additional","affiliation":[{"name":"Division of Chest, Department of Internal Medicine, Taichung Veterans General Hospital, Taichung, Taiwan"},{"name":"Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2020,2,25]]},"reference":[{"key":"2025121407295943000_10.2.e033898.1","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201504-0781OC"},{"key":"2025121407295943000_10.2.e033898.2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2014.5804"},{"key":"2025121407295943000_10.2.e033898.3","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1007\/s00101-011-1942-8","article-title":"[Scoring systems in intensive care medicine : principles, models, application and limits]","volume":"60","author":"Fleig","year":"2011","journal-title":"Anaesthesist"},{"key":"2025121407295943000_10.2.e033898.4","doi-asserted-by":"publisher","DOI":"10.1186\/cc8204"},{"key":"2025121407295943000_10.2.e033898.5","doi-asserted-by":"publisher","DOI":"10.1378\/chest.07-3061"},{"key":"2025121407295943000_10.2.e033898.6","first-page":"1042","article-title":"Severity scores in respiratory intensive care: APACHE II predicted mortality better than saps II","volume":"40","author":"Del Bufalo","year":"1995","journal-title":"Respir Care"},{"key":"2025121407295943000_10.2.e033898.7","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-198608000-00028"},{"key":"2025121407295943000_10.2.e033898.8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-0691.2011.03736.x"},{"key":"2025121407295943000_10.2.e033898.9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0046816","article-title":"Severity of influenza A 2009 (H1N1) pneumonia is underestimated by routine prediction rules. results from a prospective, population-based study","volume":"7","author":"Bjarnason","year":"2012","journal-title":"PLoS One"},{"key":"2025121407295943000_10.2.e033898.10","doi-asserted-by":"crossref","first-page":"R209","DOI":"10.1186\/cc13017","article-title":"Development of the post cardiac surgery (POCAS) prognostic score","volume":"17","author":"Tamayo","year":"2013","journal-title":"Crit Care"},{"key":"2025121407295943000_10.2.e033898.11","first-page":"13","article-title":"Comparison of six outcome prediction models in an adult burn population in a developing country","volume":"30","author":"Salehi","year":"2017","journal-title":"Ann Burns Fire Disasters"},{"key":"2025121407295943000_10.2.e033898.12","doi-asserted-by":"publisher","DOI":"10.1111\/j.1572-0241.2006.00856.x"},{"key":"2025121407295943000_10.2.e033898.13","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199701233360402"},{"key":"2025121407295943000_10.2.e033898.14","unstructured":"FluNet . Global influenza surveillance and response system, world Health organization, 2016. Available: http:\/\/www.who.int\/influenza\/gisrs_laboratory\/flunet\/en\/"},{"key":"2025121407295943000_10.2.e033898.15","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.jfma.2018.06.010","article-title":"First tidal volume greater than 8 mL\/kg is associated with increased mortality in complicated influenza infection with acute respiratory distress syndrome","volume":"118","author":"Chan","year":"2019","journal-title":"J Formos Med Assoc"},{"key":"2025121407295943000_10.2.e033898.16","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0190952","article-title":"Association of day 4 cumulative fluid balance with mortality in critically ill patients with influenza: a multicenter retrospective cohort study in Taiwan","volume":"13","author":"Chao","year":"2018","journal-title":"PLoS One"},{"key":"2025121407295943000_10.2.e033898.17","unstructured":"Taiwan national infectious disease statistics system: Taiwan centers for disease control,, 2016. Available: http:\/\/nidss.cdc.gov.tw\/en\/"},{"key":"2025121407295943000_10.2.e033898.18","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0b013e318267636e"},{"key":"2025121407295943000_10.2.e033898.19","first-page":"703","article-title":"Knowledge-analytics synergy in clinical decision support","volume":"180","author":"Slonim","year":"2012","journal-title":"Stud Health Technol Inform"},{"key":"2025121407295943000_10.2.e033898.20","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.7797"},{"key":"2025121407295943000_10.2.e033898.21","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201409-1598OC"},{"key":"2025121407295943000_10.2.e033898.22","doi-asserted-by":"publisher","DOI":"10.1177\/0885066608329850"},{"key":"2025121407295943000_10.2.e033898.23","doi-asserted-by":"publisher","DOI":"10.1136\/thx.2009.134072"},{"key":"2025121407295943000_10.2.e033898.24","first-page":"94305","article-title":"Importance sampled learning ensembles","volume":"4","author":"Friedman","year":"2003","journal-title":"J Mach Learn Res"},{"key":"2025121407295943000_10.2.e033898.25","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on knowledge discovery and data mining, ACM, New York 2016:785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"2025121407295943000_10.2.e033898.26","unstructured":"Lundberg S , Lee S-I . A unified approach to interpreting model predictions. arXiv:170507874v2 2018."},{"key":"2025121407295943000_10.2.e033898.27","doi-asserted-by":"publisher","DOI":"10.1016\/S1532-0464(03)00034-0"},{"key":"2025121407295943000_10.2.e033898.28","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1016\/S0031-3203(02)00121-8","article-title":"Attribute bagging: improving accuracy of classifier ensembles by using random feature subsets","volume":"36","author":"Bryll","year":"2003","journal-title":"Pattern Recognit"},{"key":"2025121407295943000_10.2.e033898.29","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2025121407295943000_10.2.e033898.30","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1111\/acem.12876","article-title":"Prediction of in-hospital mortality in emergency department patients with sepsis: a local big data-driven, machine learning approach","volume":"23","author":"Taylor","year":"2016","journal-title":"Acad Emerg Med"},{"key":"2025121407295943000_10.2.e033898.31","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0169772","article-title":"A comparison of a machine learning model with EuroSCORE II in predicting mortality after elective cardiac surgery: a decision curve analysis","volume":"12","author":"Allyn","year":"2017","journal-title":"PLoS One"},{"key":"2025121407295943000_10.2.e033898.32","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0174708","article-title":"Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning","volume":"12","author":"Horng","year":"2017","journal-title":"PLoS One"},{"key":"2025121407295943000_10.2.e033898.33","first-page":"623","article-title":"Machine learning and deep analytics for biocomputing: call for better explainability","volume":"23","author":"Petkovic","year":"2018","journal-title":"Pac Symp Biocomput"},{"key":"2025121407295943000_10.2.e033898.34","doi-asserted-by":"crossref","first-page":"216","DOI":"10.21037\/atm.2018.05.32","article-title":"Opening the black box of neural networks: methods for interpreting neural network models in clinical applications","volume":"6","author":"Zhang","year":"2018","journal-title":"Ann Transl Med"},{"key":"2025121407295943000_10.2.e033898.35","unstructured":"Tan HF , Hooker G , Wells MT . Tree space prototypes: another look at making tree ensembles interpretable. arXiv:161107115v 2016."},{"key":"2025121407295943000_10.2.e033898.36","doi-asserted-by":"crossref","unstructured":"Guidotti R , Monreale A , Turini F , et al . A survey of methods for explaining black box models. arXiv:180201933v3 2018.","DOI":"10.1145\/3236009"},{"key":"2025121407295943000_10.2.e033898.37","unstructured":"Pedersen TL MB . Lime: local interpretable Model-Agnostic explanations 2018."},{"key":"2025121407295943000_10.2.e033898.38","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1111\/irv.12499","article-title":"Estimating the burden of seasonal influenza in Spain from surveillance of mild and severe influenza disease, 2010-2016","volume":"12","author":"Oliva","year":"2018","journal-title":"Influenza Other Respir Viruses"},{"key":"2025121407295943000_10.2.e033898.39","doi-asserted-by":"crossref","first-page":"S52","DOI":"10.1093\/cid\/civ089","article-title":"Estimates of the demand for mechanical ventilation in the United States during an influenza pandemic","volume":"60 Suppl 1","author":"Meltzer","year":"2015","journal-title":"Clin Infect Dis"},{"key":"2025121407295943000_10.2.e033898.40","doi-asserted-by":"crossref","first-page":"S9","DOI":"10.1093\/cid\/civ090","article-title":"Using results from infectious disease modeling to improve the response to a potential H7N9 influenza pandemic","volume":"60 Suppl 1","author":"Rasmussen","year":"2015","journal-title":"Clin Infect Dis"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2019-033898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T15:30:12Z","timestamp":1765726212000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2019-033898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,2,25]]},"published-print":{"date-parts":[[2020,2]]}},"alternative-id":["10.1136\/bmjopen-2019-033898"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2019-033898","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}