https://scholars.lib.ntu.edu.tw/handle/123456789/512185
標題: | Using a machine learning approach to predict mortality in critically ill influenza patients: A cross-sectional retrospective multicentre study in Taiwan | 作者: | Hu C.-A. Chen C.-M. Fang Y.-C. Liang S.-J. HAO-CHIEN WANG Fang W.-F. Sheu C.-C. Perng W.-C. Yang K.-Y. Kao K.-C. Wu C.-L. Tsai C.-S. Lin M.-Y. Chao W.-C. |
關鍵字: | adult intensive & critical care; adult intensive & critical care; infectious diseases & infestations; information technology; thoracic medicine | 公開日期: | 2020 | 出版社: | BMJ Publishing Group | 卷: | 10 | 期: | 2 | 起(迄)頁: | e033898 | 來源出版物: | BMJ Open | 摘要: | 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. Study design A cross-sectional retrospective multicentre study in Taiwan Setting Eight medical centres in Taiwan. Participants 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. Primary and secondary outcome measures 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. Results 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. Conclusions 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. ? Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85080140146&doi=10.1136%2fbmjopen-2019-033898&partnerID=40&md5=7a905074e3be48a34fa65f259939b578 https://scholars.lib.ntu.edu.tw/handle/123456789/512185 |
ISSN: | 2044-6055 | DOI: | 10.1136/bmjopen-2019-033898 | SDG/關鍵字: | hypertensive factor; oseltamivir; steroid; adult; aged; APACHE; Article; comorbidity; critically ill patient; cross-sectional study; demography; disease severity; extracorporeal oxygenation; female; fluid balance; hemodialysis; human; infection complication; influenza; intensive care unit; laboratory test; logistic regression analysis; lung ventilation; machine learning; major clinical study; male; mortality; mortality rate; outcome assessment; Pneumonia Severity Index; positive end expiratory pressure; prediction; random forest; real time polymerase chain reaction; retrospective study; sedation; survival prediction; symptom; Taiwan; virus culture; critical illness; hospital mortality; influenza; middle aged; theoretical model; Adult; Critical Illness; Cross-Sectional Studies; Female; Hospital Mortality; Humans; Influenza, Human; Machine Learning; Male; Middle Aged; Models, Theoretical; Outcome Assessment, Health Care; Retrospective Studies; Taiwan |
顯示於: | 醫學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。