{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T12:01:17Z","timestamp":1772539277762,"version":"3.50.1"},"reference-count":34,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2021,1,17]],"date-time":"2021-01-17T00:00:00Z","timestamp":1610841600000},"content-version":"unspecified","delay-in-days":16,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Health Care Inform"],"accepted":{"date-parts":[[2020,11,27]]},"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Gastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>A machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>The potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bmjhci-2020-100245","type":"journal-article","created":{"date-parts":[[2021,1,17]],"date-time":"2021-01-17T11:55:14Z","timestamp":1610884514000},"page":"e100245","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":40,"title":["Artificial intelligence-based prediction of transfusion in the intensive care unit in patients with gastrointestinal bleeding"],"prefix":"10.1136","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9030-0071","authenticated-orcid":false,"given":"Riccardo","family":"Levi","sequence":"first","affiliation":[{"name":"Department of Electronic, Information and Bioengineering, Politecnico di Milano, Milano, Italy"}]},{"given":"Francesco","family":"Carli","sequence":"additional","affiliation":[{"name":"Department of Informatics, Universit\u00e0 degli Studi di Torino, Torino, Piemonte, Italy"}]},{"given":"Aldo Robles","family":"Ar\u00e9valo","sequence":"additional","affiliation":[{"name":"IDMEC, Instituto Superior Tecnico, Universidade de Lisboa, Lisbon, Portugal"}]},{"given":"Yuksel","family":"Altinel","sequence":"additional","affiliation":[{"name":"General Surgery Department, Istanbul Bagcilar Training and Research Hospital, Istanbul, Turkey"}]},{"given":"Daniel J","family":"Stein","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA"}]},{"given":"Matteo Maria","family":"Naldini","sequence":"additional","affiliation":[{"name":"San Raffaele Telethon Institute for Gene Therapy, Milano, Lombardia, Italy"}]},{"given":"Federica","family":"Grassi","sequence":"additional","affiliation":[{"name":"School of Medicine and Surgery, Universit\u00e0 degli Studi di Milano-Bicocca, Milano, Lombardia, Italy"}]},{"given":"Andrea","family":"Zanoni","sequence":"additional","affiliation":[{"name":"Institute of Mathematics, Ecole Polytechnique Federale de Lausanne, Lausanne, VD, Switzerland"}]},{"given":"Stan","family":"Finkelstein","sequence":"additional","affiliation":[{"name":"Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA"},{"name":"Division of Clinical Informatics, Beth Israel Deaconess Medical Center, Boston, MA, USA"}]},{"given":"Susana M","family":"Vieira","sequence":"additional","affiliation":[{"name":"IDMEC, Instituto Superior Tecnico, Universidade de Lisboa, Lisbon, Portugal"}]},{"given":"Jo\u00e3o","family":"Sousa","sequence":"additional","affiliation":[{"name":"IDMEC, Instituto Superior Tecnico, Universidade de Lisboa, Lisbon, Portugal"}]},{"given":"Riccardo","family":"Barbieri","sequence":"additional","affiliation":[{"name":"Department of Electronic, Information and Bioengineering, Politecnico di Milano, Milano, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6712-6626","authenticated-orcid":false,"given":"Leo Anthony","family":"Celi","sequence":"additional","affiliation":[{"name":"Laboratory for Computational Physiology, Harvard-MIT Division of Health Sciences and Technology, Cambridge, Massachusetts, USA"},{"name":"Division of Pulmonary Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA"}]}],"member":"239","published-online":{"date-parts":[[2021,1,17]]},"reference":[{"key":"2025072913292628000_28.1.e100245.1","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.ccc.2015.12.002","article-title":"Nonvariceal upper gastrointestinal bleeding","volume":"32","author":"Rahman","year":"2016","journal-title":"Crit Care Clin"},{"key":"2025072913292628000_28.1.e100245.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gtc.2005.08.006"},{"key":"2025072913292628000_28.1.e100245.3","doi-asserted-by":"publisher","DOI":"10.1186\/cc7160"},{"key":"2025072913292628000_28.1.e100245.4","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.cjtee.2019.04.004","article-title":"Prediction of massive transfusion in trauma patients in the surgical intensive care units (THAI-SICU study)","volume":"22","author":"Akaraborworn","year":"2019","journal-title":"Chin J Traumatol"},{"key":"2025072913292628000_28.1.e100245.5","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(00)02816-6"},{"key":"2025072913292628000_28.1.e100245.6","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1211801"},{"key":"2025072913292628000_28.1.e100245.7","doi-asserted-by":"crossref","DOI":"10.1016\/S2589-7500(19)30063-9","article-title":"Walking the tightrope of artificial intelligence guidelines in clinical practice","volume":"1","year":"2019","journal-title":"Lancet Digit Health"},{"key":"2025072913292628000_28.1.e100245.8","doi-asserted-by":"crossref","first-page":"117959721985656","DOI":"10.1177\/1179597219856564","article-title":"Critical care, critical data","volume":"10","author":"Cosgriff","year":"2019","journal-title":"Biomed Eng Comput Biol"},{"key":"2025072913292628000_28.1.e100245.9","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18391"},{"key":"2025072913292628000_28.1.e100245.10","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/j.ccc.2019.02.005","article-title":"Intensive care unit telemedicine in the era of big data, artificial intelligence, and computer clinical decision support systems","volume":"35","author":"Kindle","year":"2019","journal-title":"Crit Care Clin"},{"key":"2025072913292628000_28.1.e100245.11","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/MSPEC.2018.8482421","article-title":"Ai in the ICU: in the intensive care unit, artificial intelligence can keep Watch","volume":"55","author":"Gholami","year":"2018","journal-title":"IEEE Spectr"},{"key":"2025072913292628000_28.1.e100245.12","doi-asserted-by":"crossref","unstructured":"Ruffle JK , Farmer AD , Aziz Q . Artificial Intelligence-Assisted Gastroenterology\u2014 promises and pitfalls. Off J Am Coll Gastroenterol 2019;114.","DOI":"10.1038\/s41395-018-0268-4"},{"key":"2025072913292628000_28.1.e100245.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2007.10.003"},{"key":"2025072913292628000_28.1.e100245.14","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2007.10.037"},{"key":"2025072913292628000_28.1.e100245.15","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.ijmedinf.2012.11.017","article-title":"Reducing unnecessary lab testing in the ICU with artificial intelligence","volume":"82","author":"Cismondi","year":"2013","journal-title":"Int J Med Inform"},{"key":"2025072913292628000_28.1.e100245.16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0040297"},{"key":"2025072913292628000_28.1.e100245.17","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"key":"2025072913292628000_28.1.e100245.18","doi-asserted-by":"crossref","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative research database, a freely available multi-center database for critical care research","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci Data"},{"key":"2025072913292628000_28.1.e100245.19","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-200108001-00007"},{"key":"2025072913292628000_28.1.e100245.20","doi-asserted-by":"crossref","unstructured":"McKinney W . Data structures for statistical computing in python. proC. 9th python SCI. Conf 2010.","DOI":"10.25080\/Majora-92bf1922-00a"},{"key":"2025072913292628000_28.1.e100245.21","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.145"},{"key":"2025072913292628000_28.1.e100245.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"2025072913292628000_28.1.e100245.23","unstructured":"Pedregosa F , Varoquaux G , Gramfort A . Scikit-learn: machine learning in python. J Mach Learn Res 2011."},{"key":"2025072913292628000_28.1.e100245.24","unstructured":"Bergstra J . Distributed Asynchronous Hyperparameter Optimization [Internet]. Available: https:\/\/pypi.org\/project\/hyperopt\/ [Accessed cited 2020 May 30]."},{"key":"2025072913292628000_28.1.e100245.25","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/87.4.954"},{"key":"2025072913292628000_28.1.e100245.26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012487302797"},{"key":"2025072913292628000_28.1.e100245.27","unstructured":"Bergstra J , Yamins D , Cox DD . Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures. In: Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28. JMLR.org, 2013: p. I\u2013115\u2013I\u2013123."},{"key":"2025072913292628000_28.1.e100245.28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2025072913292628000_28.1.e100245.29","doi-asserted-by":"crossref","unstructured":"Hastie T , Tibshirani R , Friedman J . The elements of statistical learning. New York, NY: Springer New York, 2009.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"2025072913292628000_28.1.e100245.30","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil A , Caruana R . Predicting good probabilities with supervised learning. In: Proceedings of the 22nd international conference on Machine learning - ICML \u201905. New York, USA: ACM Press, 2005: 625\u201332.","DOI":"10.1145\/1102351.1102430"},{"key":"2025072913292628000_28.1.e100245.31","unstructured":"Platt J . Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 2000;10."},{"key":"2025072913292628000_28.1.e100245.32","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1016\/j.gie.2015.10.021","article-title":"Risk stratification in acute upper Gi bleeding: comparison of the AIMS65 score with the Glasgow-Blatchford and Rockall scoring systems","volume":"83","author":"Robertson","year":"2016","journal-title":"Gastrointest Endosc"},{"key":"2025072913292628000_28.1.e100245.33","doi-asserted-by":"crossref","unstructured":"Futoma J , Simons M , Panch T . The myth of generalizability in clinical research and machine learning in healthcare. Lancet Digit Heal. In Press 2020.","DOI":"10.1016\/S2589-7500(20)30186-2"},{"key":"2025072913292628000_28.1.e100245.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0300-7"}],"container-title":["BMJ Health &amp; Care Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjhci-2020-100245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T20:29:39Z","timestamp":1753820979000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatics.bmj.com\/lookup\/doi\/10.1136\/bmjhci-2020-100245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1,17]]},"published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1136\/bmjhci-2020-100245"],"URL":"https:\/\/doi.org\/10.1136\/bmjhci-2020-100245","relation":{},"ISSN":["2632-1009"],"issn-type":[{"value":"2632-1009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}