{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:43:36Z","timestamp":1780602216494,"version":"3.54.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T00:00:00Z","timestamp":1672272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T00:00:00Z","timestamp":1672272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Science and Technology Commission of Shanghai Municipality","award":["19JC1420101"],"award-info":[{"award-number":["19JC1420101"]}]},{"name":"the Science and Technology Commission of Shanghai Municipality","award":["19JC1420101"],"award-info":[{"award-number":["19JC1420101"]}]},{"name":"Shanghai Municipal Science and Technology Major Project, the ZHANGJIANG LAB","award":["2018SHZDZX01"],"award-info":[{"award-number":["2018SHZDZX01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>We aimed to develop an early warning system for real-time sepsis prediction in the ICU by machine learning methods, with tools for interpretative analysis of the predictions. In particular, we focus on the deployment of the system in a target medical center with small historical samples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Light Gradient Boosting Machine (LightGBM) and multilayer perceptron (MLP) were trained on Medical Information Mart for Intensive Care (MIMIC-III) dataset and then finetuned on the private Historical Database of local Ruijin Hospital (HDRJH) using transfer learning technique. The Shapley Additive Explanations (SHAP) analysis was employed to characterize the feature importance in the prediction inference. Ultimately, the performance of the sepsis prediction system was further evaluated in the real-world study in the ICU of the target Ruijin Hospital.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The datasets comprised 6891 patients from MIMIC-III, 453 from HDRJH, and 67 from Ruijin real-world data. The area under the receiver operating characteristic curves (AUCs) for LightGBM and MLP models derived from MIMIC-III were 0.98\u2009\u2212\u20090.98 and 0.95\u2009\u2212\u20090.96 respectively on MIMIC-III dataset, and, in comparison, 0.82\u2009\u2212\u20090.86 and 0.84\u2009\u2212\u20090.87 respectively on HDRJH, from 1 to \u20095\u00a0h preceding. After transfer learning and ensemble learning, the AUCs of the final ensemble model were enhanced to 0.94\u2009\u2212\u20090.94 on HDRJH and to 0.86\u2009\u2212\u20090.9 in the real-world study in the ICU of the target Ruijin Hospital. In addition, the SHAP analysis illustrated the importance of age, antibiotics, net balance, and ventilation for sepsis prediction, making the model interpretable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our machine learning model allows accurate real-time prediction of sepsis within 5-h preceding. Transfer learning can effectively improve the feasibility to deploy the prediction model in the target cohort, and ameliorate the model performance for external validation. SHAP analysis indicates that the role of antibiotic usage and fluid management needs further investigation. We argue that our system and methodology have the potential to improve ICU management by helping medical practitioners identify at-sepsis-risk patients and prepare for timely diagnosis and intervention.<\/jats:p>\n                    <jats:p>\n                      <jats:italic>Trial registration<\/jats:italic>\n                      : NCT05088850 (retrospectively registered).\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-022-02090-3","type":"journal-article","created":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T06:02:43Z","timestamp":1672293763000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Transferability and interpretability of the sepsis prediction models in the intensive care unit"],"prefix":"10.1186","volume":"22","clinical-trial-number":[{"clinical-trial-number":"nct05088850","registry":"10.18810\/clinical-trials-gov"}],"author":[{"given":"Qiyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranran","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ChihChe","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiming","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dechang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongping","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaling","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlian","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoqing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,29]]},"reference":[{"key":"2090_CR1","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/S0140-6736(18)30696-2","volume":"392","author":"M Cecconi","year":"2018","unstructured":"Cecconi M, Evans L, Levy M, Rhodes A. Sepsis and septic shock. Lancet. 2018;392:75\u201387. https:\/\/doi.org\/10.1016\/S0140-6736(18)30696-2.","journal-title":"Lancet"},{"key":"2090_CR2","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1001\/jama.2016.0287","volume":"315","author":"M Singer","year":"2016","unstructured":"Singer M, Deutschman CS, Seymour CW, et al. The third international consensus definitions for sepsis and septic shock (Sepsis-3). JAMA. 2016;315:801\u201310. https:\/\/doi.org\/10.1001\/jama.2016.0287.","journal-title":"JAMA"},{"key":"2090_CR3","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1097\/00003246-200107000-00002","volume":"29","author":"DC Angus","year":"2001","unstructured":"Angus DC, Linde-Zwirble WT, Lidicker J, Clermont G, Carcillo J, Pinsky MR. Epidemiology of severe sepsis in the United States: Analysis of incidence, outcome, and associated costs of care. Crit Care Med. 2001;29:1303\u201310. https:\/\/doi.org\/10.1097\/00003246-200107000-00002.","journal-title":"Crit Care Med"},{"key":"2090_CR4","doi-asserted-by":"publisher","first-page":"1690","DOI":"10.1097\/CCM.0000000000003310","volume":"46","author":"PE Marik","year":"2018","unstructured":"Marik PE, Farkas JD. The changing paradigm of sepsis: early diagnosis, early antibiotics, early pressors, and early adjuvant treatment. Crit Care Med. 2018;46:1690\u20132. https:\/\/doi.org\/10.1097\/CCM.0000000000003310.","journal-title":"Crit Care Med"},{"key":"2090_CR5","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1097\/CCM.0000000000003260","volume":"46","author":"MR Filbin","year":"2018","unstructured":"Filbin MR, Lynch J, Gillingham TD, et al. Presenting symptoms independently predict mortality in septic shock: Importance of a previously unmeasured confounder. Crit Care Med. 2018;46:1592\u20139. https:\/\/doi.org\/10.1097\/CCM.0000000000003260.","journal-title":"Crit Care Med"},{"key":"2090_CR6","doi-asserted-by":"publisher","first-page":"299ra122","DOI":"10.1126\/scitranslmed.aab3719","volume":"7","author":"KE Henry","year":"2015","unstructured":"Henry KE, Hager DN, Pronovost PJ, Saria S. A targeted real-time early warning score (TREWScore) for septic shock. Sci Transl Med. 2015;7:299ra122. https:\/\/doi.org\/10.1126\/scitranslmed.aab3719.","journal-title":"Sci Transl Med"},{"key":"2090_CR7","doi-asserted-by":"publisher","first-page":"101820","DOI":"10.1016\/j.artmed.2020.101820","volume":"104","author":"SM Lauritsen","year":"2020","unstructured":"Lauritsen SM, Kal\u00f8r ME, Kongsgaard EL, et al. Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artif Intell Med. 2020;104:101820. https:\/\/doi.org\/10.1016\/j.artmed.2020.101820.","journal-title":"Artif Intell Med"},{"key":"2090_CR8","doi-asserted-by":"publisher","first-page":"e5909","DOI":"10.2196\/medinform.5909","volume":"4","author":"T Desautels","year":"2016","unstructured":"Desautels T, Calvert J, Hoffman J, et al. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Med Inform. 2016;4:e5909. https:\/\/doi.org\/10.2196\/medinform.5909.","journal-title":"JMIR Med Inform"},{"key":"2090_CR9","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","volume":"46","author":"S Nemati","year":"2018","unstructured":"Nemati S, Holder A, Razmi F, Stanley MD, Clifford GD, Buchman TG. An interpretable machine learning model for accurate prediction of sepsis in the ICU. Crit Care Med. 2018;46:547. https:\/\/doi.org\/10.1097\/CCM.0000000000002936.","journal-title":"Crit Care Med"},{"key":"2090_CR10","first-page":"2","volume":"106","author":"M Moor","year":"2019","unstructured":"Moor M, Horn M, Rieck B, Roqueiro D, Borgwardt K. Early recognition of sepsis with Gaussian process temporal convolutional networks and dynamic time warping. Mach Learn Healthc Conf PMLR. 2019;106:2\u201326.","journal-title":"Mach Learn Healthc Conf PMLR"},{"key":"2090_CR11","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.compbiomed.2019.04.027","volume":"109","author":"C Barton","year":"2019","unstructured":"Barton C, Chettipally U, Zhou Y, et al. Evaluation of a machine learning algorithm for up to 48-hour advance prediction of sepsis using six vital signs. Comput Biol Med. 2019;109:79\u201384. https:\/\/doi.org\/10.1016\/j.compbiomed.2019.04.027.","journal-title":"Comput Biol Med"},{"key":"2090_CR12","doi-asserted-by":"publisher","first-page":"105816","DOI":"10.1016\/j.cmpb.2020.105816","volume":"198","author":"T Asuroglu","year":"2021","unstructured":"Asuroglu T, Ogul H. A deep learning approach for sepsis monitoring via severity score estimation. Comput Methods Programs Biomed. 2021;198:105816. https:\/\/doi.org\/10.1016\/j.cmpb.2020.105816.","journal-title":"Comput Methods Programs Biomed"},{"key":"2090_CR13","doi-asserted-by":"publisher","first-page":"e0251248","DOI":"10.1371\/journal.pone.0251248","volume":"16","author":"M Rosnati","year":"2021","unstructured":"Rosnati M, Fortuin V. MGP-AttTCN: an interpretable machine learning model for the prediction of sepsis. PLoS ONE. 2021;16:e0251248. https:\/\/doi.org\/10.1371\/journal.pone.0251248.","journal-title":"PLoS ONE"},{"issue":"9","key":"2090_CR14","doi-asserted-by":"publisher","first-page":"e28000","DOI":"10.2196\/28000","volume":"5","author":"I Persson","year":"2021","unstructured":"Persson I, \u00d6stling A, Arlbrandt M, S\u00f6derberg J, Becedas D. A machine learning sepsis prediction algorithm for intended intensive care unit use (NAVOY Sepsis): proof-of-concept study. JMIR Form Res. 2021;5(9):e28000. https:\/\/doi.org\/10.2196\/28000.","journal-title":"JMIR Form Res"},{"key":"2090_CR15","doi-asserted-by":"publisher","first-page":"e000158","DOI":"10.1136\/bmjoq-2017-000158","volume":"6","author":"A McCoy","year":"2017","unstructured":"McCoy A, Das R. Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units. BMJ Open Qual. 2017;6:e000158. https:\/\/doi.org\/10.1136\/bmjoq-2017-000158.","journal-title":"BMJ Open Qual"},{"key":"2090_CR16","doi-asserted-by":"publisher","first-page":"e000234","DOI":"10.1136\/bmjresp-2017-000234","volume":"4","author":"DW Shimabukuro","year":"2017","unstructured":"Shimabukuro DW, Barton CW, Feldman MD, Mataraso SJ, Das R. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res. 2017;4:e000234. https:\/\/doi.org\/10.1136\/bmjresp-2017-000234.","journal-title":"BMJ Open Respir Res"},{"issue":"4","key":"2090_CR17","doi-asserted-by":"publisher","first-page":"e285","DOI":"10.1097\/CCM.0000000000004236","volume":"48","author":"K-J Cho","year":"2020","unstructured":"Cho K-J, Kwon O, Kwon J-m, Lee Y, Park H, Jeon K-H, et al. Detecting patient deterioration using artificial intelligence in a rapid response system. Crit Care Med. 2020;48(4):e285.","journal-title":"Crit Care Med"},{"issue":"1","key":"2090_CR18","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.jclinepi.2014.09.007","volume":"68","author":"GC Siontis","year":"2015","unstructured":"Siontis GC, Tzoulaki I, Castaldi PJ, Ioannidis JP. External validation of new risk prediction models is infrequent and reveals worse prognostic discrimination. J Clin Epidemiol. 2015;68(1):25\u201334. https:\/\/doi.org\/10.1016\/j.jclinepi.2014.09.007.","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"2090_CR19","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1177\/0885066615585951","volume":"32","author":"J Lee","year":"2017","unstructured":"Lee J, Maslove DM. Customization of a severity of illness score using local electronic medical record data. J Intensive Care Med. 2017;32(1):38\u201347. https:\/\/doi.org\/10.1177\/0885066615585951.","journal-title":"J Intensive Care Med"},{"issue":"1","key":"2090_CR20","doi-asserted-by":"publisher","first-page":"e017833","DOI":"10.1136\/bmjopen-2017-017833","volume":"8","author":"Q Mao","year":"2018","unstructured":"Mao Q, Jay M, Hoffman JL, Calvert J, Barton C, Shimabukuro D, et al. Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ Open. 2018;8(1):e017833. https:\/\/doi.org\/10.1136\/bmjopen-2017-017833.","journal-title":"BMJ Open"},{"issue":"4","key":"2090_CR21","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.annemergmed.2020.11.007","volume":"77","author":"G Wardi","year":"2021","unstructured":"Wardi G, Carlile M, Holder A, Shashikumar S, Hayden SR, Nemati S. Predicting progression to septic shock in the emergency department using an externally generalizable machine-learning algorithm. Ann Emerg Med. 2021;77(4):395\u2013406. https:\/\/doi.org\/10.1016\/j.annemergmed.2020.11.007.","journal-title":"Ann Emerg Med"},{"key":"2090_CR22","doi-asserted-by":"publisher","first-page":"100196","DOI":"10.1016\/j.patter.2020.100196","volume":"2","author":"D Zhang","year":"2021","unstructured":"Zhang D, Yin C, Hunold KM, Jiang X, Caterino JM, Zhang P. An interpretable deep-learning model for early prediction of sepsis in the emergency department. Patterns. 2021;2:100196. https:\/\/doi.org\/10.1016\/j.patter.2020.100196.","journal-title":"Patterns"},{"key":"2090_CR23","doi-asserted-by":"publisher","first-page":"103876","DOI":"10.1016\/j.jbi.2021.103876","volume":"121","author":"I Gandin","year":"2021","unstructured":"Gandin I, Scagnetto A, Romani S, Barbati G. Interpretability of time-series deep learning models: a study in cardiovascular patients admitted to Intensive care unit. J Biomed Inform. 2021;121:103876. https:\/\/doi.org\/10.1016\/j.jbi.2021.103876.","journal-title":"J Biomed Inform"},{"key":"2090_CR24","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1136\/bmj.g7594","volume":"162","author":"GS Collins","year":"2015","unstructured":"Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. Ann Intern Med. 2015;162:55\u201363. https:\/\/doi.org\/10.1136\/bmj.g7594.","journal-title":"Ann Intern Med"},{"key":"2090_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson AE, Pollard TJ, Shen L, et al. MIMIC-III, a freely accessible critical care database. Sci Data. 2016;3:1\u20139. https:\/\/doi.org\/10.1038\/sdata.2016.35.","journal-title":"Sci Data"},{"key":"2090_CR26","doi-asserted-by":"publisher","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. 2016. p. 785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2090_CR27","first-page":"3146","volume":"30","author":"G Ke","year":"2017","unstructured":"Ke G, Meng Q, Finley T, et al. Lightgbm: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017;30:3146\u201354.","journal-title":"Adv Neural Inf Process Syst"},{"key":"2090_CR28","unstructured":"Lundberg S, Lee SI. A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems. 2017. p. 4768\u201377"},{"key":"2090_CR29","doi-asserted-by":"publisher","DOI":"10.1101\/2022.07.06.22277188","author":"Q Chen","year":"2022","unstructured":"Chen Q, Li R, Lin C, et al. SEPRES: sepsis prediction via the clinical data integration system in the ICU. medRxiv. 2022. https:\/\/doi.org\/10.1101\/2022.07.06.22277188.","journal-title":"medRxiv"},{"key":"2090_CR30","doi-asserted-by":"publisher","first-page":"871","DOI":"10.2169\/internalmedicine.51.6951","volume":"51","author":"T Kenzaka","year":"2012","unstructured":"Kenzaka T, Okayama M, Kuroki S, et al. Importance of vital signs to the early diagnosis and severity of sepsis: association between vital signs and sequential organ failure assessment score in patients with sepsis. Intern Med. 2012;51:871\u20136. https:\/\/doi.org\/10.2169\/internalmedicine.51.6951.","journal-title":"Intern Med"},{"key":"2090_CR31","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.thromres.2019.07.002","volume":"181","author":"T Matsubara","year":"2019","unstructured":"Matsubara T, Yamakawa K, Umemura Y, et al. Significance of plasma fibrinogen level and antithrombin activity in sepsis: a multicenter cohort study using a cubic spline model. Thromb Res. 2019;181:17\u201323. https:\/\/doi.org\/10.1016\/j.thromres.2019.07.002.","journal-title":"Thromb Res"},{"key":"2090_CR32","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.1016\/j.ajem.2016.07.058","volume":"34","author":"E Brotfain","year":"2016","unstructured":"Brotfain E, Koyfman L, Toledano R, et al. Positive fluid balance as a major predictor of clinical outcome of patients with sepsis\/septic shock after ICU discharge. Am J Emerg Med. 2016;34:2122\u20136. https:\/\/doi.org\/10.1016\/j.ajem.2016.07.058.","journal-title":"Am J Emerg Med"},{"key":"2090_CR33","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1097\/01.CCM.0000194535.82812.BA","volume":"34","author":"GS Martin","year":"2006","unstructured":"Martin GS, Mannino DM, Moss M. The effect of age on the development and outcome of adult sepsis. Crit Care Med. 2006;34:15\u201321. https:\/\/doi.org\/10.1097\/01.CCM.0000194535.82812.BA.","journal-title":"Crit Care Med"},{"key":"2090_CR34","doi-asserted-by":"publisher","first-page":"e100109","DOI":"10.1136\/bmjhci-2019-100109","volume":"27","author":"H Burdick","year":"2020","unstructured":"Burdick H, Pino E, Gabel-Comeau D, et al. Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: A prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals. BMJ Health Care Inform. 2020;27:e100109. https:\/\/doi.org\/10.1136\/bmjhci-2019-100109.","journal-title":"BMJ Health Care Inform"},{"key":"2090_CR35","doi-asserted-by":"publisher","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","volume":"128","author":"MA Morid","year":"2021","unstructured":"Morid MA, Borjali A, Del Fiol G. A scoping review of transfer learning research on medical image analysis using ImageNet. Comput Biol Med. 2021;128:104115. https:\/\/doi.org\/10.1016\/j.compbiomed.2020.104115.","journal-title":"Comput Biol Med"},{"key":"2090_CR36","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3390\/bios11040127","volume":"11","author":"K-K Tseng","year":"2021","unstructured":"Tseng K-K, Wang C, Huang Y-F, Chen G-R, Yung K-L, Ip W-H. Cross-domain transfer learning for pcg diagnosis algorithm. Biosensors. 2021;11:127. https:\/\/doi.org\/10.3390\/bios11040127.","journal-title":"Biosensors"},{"key":"2090_CR37","doi-asserted-by":"publisher","first-page":"e2219776","DOI":"10.1001\/jamanetworkopen.2022.19776","volume":"5","author":"K Liu","year":"2022","unstructured":"Liu K, Zhang X, Chen W, et al. Development and validation of a personalized model with transfer learning for acute kidney injury risk estimation using electronic health records. JAMA Netw Open. 2022;5:e2219776. https:\/\/doi.org\/10.1001\/jamanetworkopen.2022.19776.","journal-title":"JAMA Netw Open"},{"key":"2090_CR38","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1038\/s41746-021-00536-y","volume":"4","author":"H Chen","year":"2021","unstructured":"Chen H, Lundberg SM, Erion G, Kim JH, Lee S-I. Forecasting adverse surgical events using self-supervised transfer learning for physiological signals. NPJ Digit Med. 2021;4:167. https:\/\/doi.org\/10.1038\/s41746-021-00536-y.","journal-title":"NPJ Digit Med"},{"key":"2090_CR39","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.amjsurg.2020.08.032","volume":"222","author":"T-L Lin","year":"2021","unstructured":"Lin T-L, Dhillon NK, Conde G, et al. Early positive fluid balance is predictive for venous thromboembolism in critically ill surgical patients. Am J Surg. 2021;222:220\u20136. https:\/\/doi.org\/10.1016\/j.amjsurg.2020.08.032.","journal-title":"Am J Surg"},{"key":"2090_CR40","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1186\/s13054-015-1035-1","volume":"19","author":"PM Klein Klouwenberg","year":"2015","unstructured":"Klein Klouwenberg PM, Cremer OL, van Vught LA, et al. Likelihood of infection in patients with presumed sepsis at the time of intensive care unit admission: a cohort study. Crit Care. 2015;19:319. https:\/\/doi.org\/10.1186\/s13054-015-1035-1.","journal-title":"Crit Care"},{"key":"2090_CR41","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1038\/nm.2729","volume":"18","author":"JS Ayres","year":"2012","unstructured":"Ayres JS, Trinidad NJ, Vance RE. Lethal inflammasome activation by a multidrug-resistant pathobiont upon antibiotic disruption of the microbiota. Nat Med. 2012;18:799\u2013806. https:\/\/doi.org\/10.1038\/nm.2729.","journal-title":"Nat Med"},{"key":"2090_CR42","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/s00134-019-05520-5","volume":"45","author":"JF Timsit","year":"2019","unstructured":"Timsit JF, Bassetti M, Cremer O, et al. Rationalizing antimicrobial therapy in the ICU: a narrative review. Intensive Care Med. 2019;45:172\u201389. https:\/\/doi.org\/10.1007\/s00134-019-05520-5.","journal-title":"Intensive Care Med"},{"key":"2090_CR43","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1186\/s13054-014-0480-6","volume":"18","author":"CE Luyt","year":"2014","unstructured":"Luyt CE, Br\u00e9chot N, Trouillet JL, Chastre J. Antibiotic stewardship in the intensive care unit. Crit Care. 2014;18:480. https:\/\/doi.org\/10.1186\/s13054-014-0480-6.","journal-title":"Crit Care"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-02090-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-022-02090-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-02090-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T06:03:48Z","timestamp":1672293828000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-022-02090-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,29]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["2090"],"URL":"https:\/\/doi.org\/10.1186\/s12911-022-02090-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.05.13.21256281","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,29]]},"assertion":[{"value":"27 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study protocol complies with the Declaration of Helsinki, as revised in 2013, and was approved by the Ruijin Hospital Ethics Committee (No. 2020 [140]). Written informed consent was obtained from individual or guardian participants.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"343"}}