{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T02:58:36Z","timestamp":1787626716030,"version":"build-2736575974"},"reference-count":33,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"German Ministry of Education and Research, BMBF","award":["#01ZZ2005"],"award-info":[{"award-number":["#01ZZ2005"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The objective of this retrospective study is to compare three learning approaches for blood transfusion (BT) prediction after intensive care unit (ICU) admission: local learning (LL), federated learning (FL), and centralized learning (CL) across five ICU databases (eICU Collaborative Research Database, Medical Information Mart for Intensive Care IV, High-Resolution Intensive Care Unit Dataset, Amsterdam University Medical Center Database, University Hospital of Augsburg).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>As machine learning model we used XGBoost and included 15 clinical variables. The prediction task consists of a 3-h observation window, followed by a 2-h prediction window. We evaluated the models using internal and external validation with area under the receiver-operator curve, area under the precision-recall curve, PPV, Brier score and F1 score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>CL consistently outperformed FL and LL in both internal validation (AUPRC range: 0.73\u20130.95 (CL) vs 0.63\u20130.96 (FL) and 0.69\u20130.96 (LL)) and external validation (AUPRC range: 0.61\u20130.89 (CL) vs 0.45\u20130.91 (FL) and 0.37\u20130.90 (LL)). FL showed variable performance across datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The complexity of the multivariable clinical prediction of BTs may create substantial challenges for FL effectiveness, particularly under high data heterogeneity conditions that are common in healthcare.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261428383","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T13:10:19Z","timestamp":1777122619000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting blood transfusion after ICU admission in five databases: A comparison of three machine learning paradigms"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3107-1619","authenticated-orcid":false,"given":"Johanna","family":"Schwinn","sequence":"first","affiliation":[{"name":"University Hospital of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0121-0160","authenticated-orcid":false,"given":"Seyedmostafa","family":"Sheikhalishahi","sequence":"additional","affiliation":[{"name":"University Hospital of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthaeus","family":"Morhart","sequence":"additional","affiliation":[{"name":"University Hospital of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I\u00f1aki","family":"Soto Rey","sequence":"additional","affiliation":[{"name":"University Hospital of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Simon","sequence":"additional","affiliation":[{"name":"University of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6722-766X","authenticated-orcid":false,"given":"Mathias","family":"Kaspar","sequence":"additional","affiliation":[{"name":"University Hospital of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ludwig Christian","family":"Hinske","sequence":"additional","affiliation":[{"name":"University Hospital of Augsburg"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,4,25]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.34133\/hds.0197"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01506-3"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02800-z"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1111\/trf.15935"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.4258\/hir.2022.28.4.364"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2020-100245"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02830-7"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102124"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2024.101419"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI240529"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Faltys M Zimmermann M Lyu X et al. HiRID a high time-resolution ICU dataset 2021. DOI:10.13026\/323R-NK04. URL: https:\/\/physionet.org\/content\/hirid\/.","DOI":"10.13026\/323R-NK04"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000004916"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.20737"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-018-2018-9"},{"key":"e_1_3_3_19_2","first-page":"1273","volume-title":"Artificial intelligence and statistics","author":"McMahan B","year":"2017","unstructured":"McMahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics. PMLR, 2017, pp.1273\u20131282."},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_21_2","unstructured":"Mehrjou A Soleymani A Buchholz A et al. Federated learning in multi-center critical care research: A systematic case study using the eICU database 2022. http:\/\/arxiv.org\/abs\/2204.09328. ArXiv:2204.09328 [cs stat]."},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.11.292"},{"key":"e_1_3_3_23_2","unstructured":"Beutel DJ Topal T Mathur A et al. Flower: a friendly federated learning research framework 2022. http:\/\/arxiv.org\/abs\/2007.14390. ArXiv:2007.14390 [cs stat]."},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1111\/trf.17582"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.2196\/24207"},{"key":"e_1_3_3_26_2","first-page":"57","volume-title":"Comparative federated analytics of blood transfused patients in five ICU databases: using Kullback-Leibler divergenceGood evaluation-better digital health: proceedings of the EFMI special topic conference 2025","author":"Schwinn J","unstructured":"Schwinn J, Sheikhalishahi S, Morhart M, et al. Comparative federated analytics of blood transfused patients in five ICU databases: using Kullback-Leibler divergence. In: Good evaluation-better digital health: proceedings of the EFMI special topic conference 2025, pp.57\u201361: IOS Press."},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom59178.2023.00082"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000117"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Zhao Y Li M Lai L et al. Federated learning with non-IID data 2018. DOI:10.48550\/arXiv.1806.00582. http:\/\/arxiv.org\/abs\/1806.00582. ArXiv:1806.00582 [cs].","DOI":"10.48550\/arXiv.1806.00582"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00489-2"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30186-2"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1111\/trf.15864"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102549"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261428383","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261428383","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261428383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:14Z","timestamp":1777398974000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261428383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":33,"alternative-id":["10.1177\/20552076261428383"],"URL":"https:\/\/doi.org\/10.1177\/20552076261428383","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261428383"}}