{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T14:40:11Z","timestamp":1768488011080,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T00:00:00Z","timestamp":1683158400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T00:00:00Z","timestamp":1683158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"China PLA Scientific Key Grant","award":["20-163-12-ZT-005-003-01"],"award-info":[{"award-number":["20-163-12-ZT-005-003-01"]}]},{"name":"China Key Scientific Grant Program","award":["No. 2021YFC0122500"],"award-info":[{"award-number":["No. 2021YFC0122500"]}]},{"name":"National Science Foundation for Young Scientists of China","award":["Grant No. 82100096"],"award-info":[{"award-number":["Grant No. 82100096"]}]},{"name":"National Science Foundation for Young Scientists of Beijing","award":["Grant No. 7214254"],"award-info":[{"award-number":["Grant No. 7214254"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Multiple organ dysfunction syndrome (MODS) is one of the leading causes of death in critically ill patients. MODS is the result of a dysregulated inflammatory response that can be triggered by various causes. Owing to the lack of an effective treatment for patients with MODS, early identification and intervention are the most effective strategies. Therefore, we have developed a variety of early warning models whose prediction results can be interpreted by Kernel SHapley Additive exPlanations (Kernel-SHAP) and reversed by diverse counterfactual explanations (DiCE). So we can predict the probability of MODS 12\u00a0h in advance, quantify the risk factors, and automatically recommend relevant interventions.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We used various machine learning algorithms to complete the early risk assessment of MODS, and used a stacked ensemble to improve the prediction performance. The kernel-SHAP algorithm was used to quantify the positive and minus\u00a0factors corresponding to the individual prediction results, and finally, the DiCE method was used to automatically recommend interventions. We completed the model training and testing based on the MIMIC-III and MIMIC-IV databases, in which the sample features in the model training included the patients\u2019 vital signs, laboratory test results, test reports, and data related to the use of ventilators.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The customizable model called SuperLearner, which integrated multiple machine learning algorithms, had the highest authenticity of screening, and its Yordon index (YI), sensitivity, accuracy, and utility_score on the MIMIC-IV test set were 0.813, 0.884, 0.893, and 0.763, respectively, which were all maximum values of eleven models. The area under the curve of the deep\u2013wide neural network (DWNN) model on the MIMIC-IV test set was 0.960, and the specificity was 0.935, which were both the maximum values of all these models. The Kernel-SHAP algorithm combined with SuperLearner was used to determine the minimum value of glasgow coma scale (GCS) in the current hour (OR\u2009=\u20090.609, 95% CI\u2009 \u20090.606\u20130.612), maximum value of MODS score corresponding to GCS in the past 24\u00a0h (OR\u2009=\u20092.632, 95% CI\u20092.588\u20132.676), and maximum score of MODS corresponding to creatinine in the past 24\u00a0h (OR\u2009=\u20093.281, 95% CI\u2009 \u20093.267\u20133.295) were generally the most influential factors.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>The MODS early warning model based on machine learning algorithms has considerable application value, and the prediction efficiency of SuperLearner is superior to those of SubSuperLearner, DWNN, and other eight common machine learning models. Considering that the attribution analysis of Kernel-SHAP is a static analysis of the prediction results, we introduce the DiCE algorithm to automatically recommend <jats:italic>counterfactuals<\/jats:italic> to reverse the prediction results, which will be an important step towards the practical application of automatic MODS early intervention.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s40537-023-00719-2","type":"journal-article","created":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T16:01:53Z","timestamp":1683216113000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Early prediction of MODS interventions in the intensive care unit using machine learning"],"prefix":"10.1186","volume":"10","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Zhenjie","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Pengfei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yanhui","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Hu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Haibo","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Lixin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,4]]},"reference":[{"key":"719_CR1","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1056\/NEJM200103083441001","volume":"344","author":"GR Bernard","year":"2001","unstructured":"Bernard GR, Vincent JL, Laterre PF, et al. Efficacy and safety of recombinant human activated protein C for severe sepsis. N Engl J Med. 2001;344:699\u2013709.","journal-title":"N Engl J Med"},{"key":"719_CR2","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1378\/chest.127.3.942","volume":"127","author":"B Guidet","year":"2005","unstructured":"Guidet B, Aegerter P, Gauzit R, Meshaka P, Dreyfuss D. CUB-rea study group incidence and impact of organ dysfunction associated with sepsis. Chest. 2005;127:942\u201351.","journal-title":"Chest"},{"issue":"12","key":"719_CR3","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1177\/0885066619871452","volume":"35","author":"NM Gourd","year":"2020","unstructured":"Gourd NM, Nikitas N. Multiple organ dysfunction syndrome. J Intensive Care Med. 2020;35(12):1564\u201375. https:\/\/doi.org\/10.1177\/0885066619871452.","journal-title":"J Intensive Care Med"},{"issue":"3","key":"719_CR4","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1089\/109629600750018105","volume":"1","author":"PS Barie","year":"2000","unstructured":"Barie PS, Hydo LJ. Epidemiology of multiple organ dysfunction syndrome in critical surgical illness. Surg Infect. 2000;1(3):173\u201385.","journal-title":"Surg Infect"},{"issue":"7","key":"719_CR5","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(7):1303\u201310.","journal-title":"Crit Care Med"},{"issue":"8","key":"719_CR6","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1164\/rccm.201502-0275OC","volume":"192","author":"MM Churpek","year":"2015","unstructured":"Churpek MM, Zadravecz FJ, Winslow C, Howell MD, Edelson DP. Incidence and prognostic value of the systemic inflammatory response syndrome and organ dysfunctions in ward patients. Am J Respir Crit Care Med. 2015;192(8):958\u201364.","journal-title":"Am J Respir Crit Care Med"},{"issue":"6","key":"719_CR7","doi-asserted-by":"publisher","first-page":"R154","DOI":"10.1186\/cc5086","volume":"10","author":"VD Mayr","year":"2006","unstructured":"Mayr VD, D\u00fcnser MW, Greil V, Jochberger S, Luckner G, Ulmer H, et al. Causes of death and determinants of outcome in critically ill patients. Crit Care. 2006;10(6):R154.","journal-title":"Crit Care"},{"issue":"12","key":"719_CR8","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1177\/0885066619871452","volume":"35","author":"NM Gourd","year":"2020","unstructured":"Gourd NM, Nikitas N. Multiple organ dysfunction syndrome. J Intensive Care Med. 2020;35(12):1564\u201375.","journal-title":"J Intensive Care Med"},{"key":"719_CR9","doi-asserted-by":"publisher","first-page":"711104","DOI":"10.3389\/fped.2021.711104","volume":"9","author":"SN Bose","year":"2021","unstructured":"Bose SN, Greenstein JL, Fackler JC, Sarma SV, Winslow RL, Bembea MM. Early prediction of multiple organ dysfunction in the pediatric intensive care unit. Front Pediatr. 2021;9:711104.","journal-title":"Front Pediatr"},{"issue":"1","key":"719_CR10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1097\/01.PCC.0000149131.72248.E6","volume":"6","author":"B Goldstein","year":"2005","unstructured":"Goldstein B, Giroir B, Randolph A. International pediatric sepsis consensus conference: definitions for sepsis and organ dysfunction in pediatrics. Pediatr Crit Care Med. 2005;6(1):2\u20138.","journal-title":"Pediatr Crit Care Med"},{"issue":"1","key":"719_CR11","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1097\/PCC.0b013e31819370a9","volume":"10","author":"F Proulx","year":"2009","unstructured":"Proulx F, Joyal JS, Mariscalco MM, Leteurtre S, Leclerc F, Lacroix J. The pediatric multiple organ dysfunction syndrome. Pediatr Crit Care Med. 2009;10(1):12\u201322.","journal-title":"Pediatr Crit Care Med"},{"issue":"4","key":"719_CR12","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1378\/chest.109.4.1033","volume":"109","author":"F Proulx","year":"1996","unstructured":"Proulx F, Fayon M, Farrell CA, Lacroix J, Gauthier M. Epidemiology of sepsis and multiple organ dysfunction syndrome in children. Chest. 1996;109(4):1033\u20137.","journal-title":"Chest"},{"issue":"2","key":"719_CR13","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1097\/CCM.0000000000004145","volume":"48","author":"MA Reyna","year":"2020","unstructured":"Reyna MA, Josef CS, Jeter R, Shashikumar SP, Westover MB, Nemati S, et al. Early prediction of sepsis from clinical data: the physionet\/computing in cardiology challenge 2019. Crit Care Med. 2020;48(2):210\u20137.","journal-title":"Crit Care Med"},{"issue":"10","key":"719_CR14","doi-asserted-by":"publisher","first-page":"e884","DOI":"10.1097\/CCM.0000000000004494","volume":"48","author":"X Li","year":"2020","unstructured":"Li X, Xu X, Xie F, Xu X, Sun Y, Liu X, et al. A time-phased machine learning model for real-time prediction of sepsis in critical care. Crit Care Med. 2020;48(10):e884\u20138.","journal-title":"Crit Care Med"},{"issue":"1","key":"719_CR15","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1186\/s13054-022-04055-4.PMID:35717241;PMCID:PMC9206755","volume":"26","author":"E Karakike","year":"2022","unstructured":"Karakike E, Scicluna BP, Roumpoutsou M, Mitrou I, Karampela N, Karageorgos A, Psaroulis K, Massa E, Pitsoulis A, Chaloulis P, Pappa E, Schrijver IT, Frantzeskaki F, Lada M, Dauby N, De Bels D, Floros I, Anisoglou S, Antoniadou E, Patrani M, Vlachogianni G, Mouloudi E, Antoniadou A, Grimaldi D, Roger T, Wiersinga WJ, Tsangaris I, Giamarellos-Bourboulis EJ. Effect of intravenous clarithromycin in patients with sepsis, respiratory and multiple organ dysfunction syndrome: a randomized clinical trial. Crit Care. 2022;26(1):183. https:\/\/doi.org\/10.1186\/s13054-022-04055-4.PMID:35717241;PMCID:PMC9206755.","journal-title":"Crit Care"},{"issue":"7","key":"719_CR16","doi-asserted-by":"publisher","first-page":"e1002338","DOI":"10.1371\/journal.pmed.1002338","volume":"14","author":"J Hazeldine","year":"2017","unstructured":"Hazeldine J, Naumann DN, Toman E, Davies D, Bishop JRB, Su Z, Hampson P, Dinsdale RJ, Crombie N, Duggal NA, Harrison P, Belli A, Lord JM. Prehospital immune responses and development of multiple organ dysfunction syndrome following traumatic injury: a prospective cohort study. PLoS Med. 2017;14(7):e1002338. https:\/\/doi.org\/10.1371\/journal.pmed.1002338.","journal-title":"PLoS Med"},{"issue":"11","key":"719_CR17","doi-asserted-by":"publisher","first-page":"2046","DOI":"10.1097\/00003246-200111000-00002","volume":"29","author":"R Cook","year":"2001","unstructured":"Cook R, Cook D, Tilley J, Lee K, Marshall J, Canadian Critical Care Trials Group. Multiple organ dysfunction: baseline and serial component scores. Crit Care Med. 2001;29(11):2046\u201350. https:\/\/doi.org\/10.1097\/00003246-200111000-00002.","journal-title":"Crit Care Med"},{"key":"719_CR18","unstructured":"Liu X, Hu P, Mao Z, Kuo P, Li P, Liu C, Hu J, Li D, Cao D, Mark RG, Celi LA, Zhang Z, Zhou F. (2020). Interpretable Machine Learning Model for Early Prediction of Mortality in Elderly Patients with Multiple Organ Dysfunction Syndrome (MODS): a Multicenter Retrospective Study and Cross Validation. ArXiv, abs\/2001.10977."},{"key":"719_CR19","unstructured":"https:\/\/github.com\/MIT-LCP\/mimic-code\/tree\/main\/mimic-iii\/concepts. Accessed 16 March 2022."},{"issue":"9","key":"719_CR20","doi-asserted-by":"publisher","first-page":"E390","DOI":"10.1097\/BRS.0000000000004267","volume":"47","author":"G Fan","year":"2022","unstructured":"Fan G, Yang S, Liu H, Xu N, Chen Y, He J, et al. Machine learning-based prediction of prolonged intensive care unit stay for critical patients with spinal cord injury. Spine. 2022;47(9):E390-e398.","journal-title":"Spine"},{"issue":"12","key":"719_CR21","doi-asserted-by":"publisher","first-page":"e25442","DOI":"10.2196\/25442","volume":"22","author":"H Ko","year":"2020","unstructured":"Ko H, Chung H, Kang WS, Park C, Kim DW, Kim SE, et al. An Artificial intelligence model to predict the mortality of COVID-19 patients at hospital admission time using routine blood samples: development and validation of an ensemble model. J Med Internet Res. 2020;22(12):e25442.","journal-title":"J Med Internet Res"},{"key":"719_CR22","doi-asserted-by":"publisher","first-page":"104554","DOI":"10.1016\/j.compbiomed.2021.104554","volume":"135","author":"SK Kalagotla","year":"2021","unstructured":"Kalagotla SK, Gangashetty SV, Giridhar K. A novel Stacked Ensemble technique for prediction of diabetes. Comput Biol Med. 2021;135:104554. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104554.","journal-title":"Comput Biol Med."},{"issue":"21","key":"719_CR23","doi-asserted-by":"publisher","first-page":"6460","DOI":"10.3390\/jcm11216460","volume":"11","author":"CC Chiu","year":"2022","unstructured":"Chiu CC, Wu CM, Chien TN, Kao LJ, Li C, Jiang HL. Applying an improved stacking ensemble model to predict the mortality of ICU patients with heart failure. J Clin Med. 2022;11(21):6460. https:\/\/doi.org\/10.3390\/jcm11216460.","journal-title":"J Clin Med"},{"issue":"1","key":"719_CR24","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s12911-022-01767-z.PMID:35101003;PMCID:PMC8805397","volume":"22","author":"N Liang","year":"2022","unstructured":"Liang N, Wang C, Duan J, Xie X, Wang Y. Efficacy prediction of noninvasive ventilation failure based on the stacking ensemble algorithm and autoencoder. BMC Med Inform Decis Mak. 2022;22(1):27. https:\/\/doi.org\/10.1186\/s12911-022-01767-z.PMID:35101003;PMCID:PMC8805397.","journal-title":"BMC Med Inform Decis Mak"},{"key":"719_CR25","unstructured":"Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning; 2015: PMLR; 2015. p. 448\u2013456."},{"key":"719_CR26","doi-asserted-by":"publisher","first-page":"178392","DOI":"10.1109\/ACCESS.2019.2956859","volume":"7","author":"B Wang","year":"2019","unstructured":"Wang B, Bai Y, Yao Z, Li J, Dong W, Tu Y, et al. A multi-task neural network architecture for renal dysfunction prediction in heart failure patients with electronic health records. IEEE Access. 2019;7:178392\u2013400.","journal-title":"IEEE Access"},{"issue":"1","key":"719_CR27","doi-asserted-by":"publisher","first-page":"11730","DOI":"10.1038\/s41598-021-90000-4","volume":"11","author":"V Ardulov","year":"2021","unstructured":"Ardulov V, Martinez VR, Somandepalli K, Zheng S, Salzman E, Lord C, et al. Robust diagnostic classification via Q-learning. Sci Rep. 2021;11(1):11730.","journal-title":"Sci Rep"},{"key":"719_CR28","unstructured":"Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Advances in neural information processing systems 2017: 30."},{"key":"719_CR29","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C. \" Why should i trust you?\" Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining; 2016; 2016. p. 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"719_CR30","doi-asserted-by":"crossref","unstructured":"Ramaravind K Mothilal, Amit Sharma, and Chenhao Tan. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 607\u2013617, 2020.","DOI":"10.1145\/3351095.3372850"},{"key":"719_CR31","doi-asserted-by":"publisher","first-page":"102087","DOI":"10.1016\/j.artmed.2021.102087","volume":"117","author":"Y Jia","year":"2021","unstructured":"Jia Y, Kaul C, Lawton T, Murray-Smith R, Habli I. Prediction of weaning from mechanical ventilation using convolutional neural networks. Artif Intell Med. 2021;117:102087.","journal-title":"Artif Intell Med"},{"issue":"1","key":"719_CR32","doi-asserted-by":"publisher","first-page":"11730","DOI":"10.1038\/s41598-021-90000-4","volume":"11","author":"V Ardulov","year":"2021","unstructured":"Ardulov V, Martinez VR, Somandepalli K, Zheng S, Salzman E, Lord C, Bishop S, Narayanan S. Robust diagnostic classification via Q-learning. Sci Rep. 2021;11(1):11730. https:\/\/doi.org\/10.1038\/s41598-021-90000-4.","journal-title":"Sci Rep"},{"issue":"10","key":"719_CR33","doi-asserted-by":"publisher","first-page":"1950021","DOI":"10.1142\/S0129065719500217","volume":"29","author":"C Sun","year":"2019","unstructured":"Sun C, Cui H, Zhou W, Nie W, Wang X, Yuan Q. Epileptic seizure detection with EEG textural features and imbalanced classification based on easyensemble learning. Int J Neural Syst. 2019;29(10):1950021. https:\/\/doi.org\/10.1142\/S0129065719500217.","journal-title":"Int J Neural Syst"},{"issue":"12","key":"719_CR34","doi-asserted-by":"publisher","first-page":"4263","DOI":"10.1109\/TCYB.2016.2606104","volume":"47","author":"Q Kang","year":"2017","unstructured":"Kang Q, Chen X, Li S, Zhou M. A noise-filtered under-sampling scheme for imbalanced classification. IEEE Trans Cybern. 2017;47(12):4263\u201374. https:\/\/doi.org\/10.1109\/TCYB.2016.2606104.","journal-title":"IEEE Trans Cybern"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00719-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-023-00719-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00719-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T16:05:03Z","timestamp":1683216303000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-023-00719-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,4]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["719"],"URL":"https:\/\/doi.org\/10.1186\/s40537-023-00719-2","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,4]]},"assertion":[{"value":"25 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors read and approved the publication of the final manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"None.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"55"}}