{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T08:22:19Z","timestamp":1787818939884,"version":"build-2784847793"},"reference-count":31,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T00:00:00Z","timestamp":1735862400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000133","name":"Agency for Healthcare Research and Quality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000133","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011485","name":"North Carolina Translational and Clinical Sciences Institute, University of North Carolina at Chapel Hill","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011485","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["accpjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Pharmacotherapy"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Fluid overload (FO) in the intensive care unit (ICU) is common, serious, and may be preventable. Intravenous medications (including administered volume) are a primary cause for FO but are challenging to evaluate as a FO predictor given the high frequency and time\u2010dependency of their use and other factors affecting FO. We sought to employ unsupervised machine learning methods to uncover medication administration patterns correlating with FO.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort study included 927 adults admitted to an ICU for \u226572\u2009h. FO was defined as a positive fluid balance \u22657% of admission body weight. After reviewing medication administration record data in 3\u2010h periods, medication exposure was categorized into clusters using principal component analysis (PCA) and Restricted Boltzmann Machine (RBM). Medication regimens of patients with and without FO were compared within clusters to assess their temporal association with FO.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      FO occurred in 127 (13.7%) of 927 included patients. Patients received a median (interquartile range) of 31(13\u201365) discrete intravenous medication administrations over the 72\u2010h period. Across all 47,803 intravenous medication administrations, 10 unique medication clusters, containing 121 to 130 medications per cluster, were identified. The mean number of Cluster 7 medications administered was significantly greater in the FO cohort compared with patients without FO (25.6 vs.10.9,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.0001). A total of 51 (40.2%) of 127 unique Cluster 7 medications were administered in more than five different 3\u2010h periods during the 72\u2010h study window. The most common Cluster 7 medications included continuous infusions, antibiotics, and sedatives\/analgesics. Addition of Cluster 7 medications to an FO prediction model including the Acute Physiologic and Chronic Health Evaluation (APACHE) II score and receipt of diuretics improved model predictiveness from an Area Under the Receiver Operation Characteristic (AUROC) curve of 0.719 to 0.741 (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.027).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Using machine learning approaches, a unique medication cluster was strongly associated with FO. Incorporation of this cluster improved the ability to predict FO compared to traditional prediction models. Integration of this approach into real\u2010time clinical applications may improve early detection of FO to facilitate timely intervention.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/phar.4642","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T07:28:50Z","timestamp":1735889330000},"page":"76-86","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised machine learning analysis to identify patterns of\n                    <scp>ICU<\/scp>\n                    medication use for fluid overload prediction"],"prefix":"10.1002","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6686-1079","authenticated-orcid":false,"given":"Kelli","family":"Henry","sequence":"first","affiliation":[{"name":"Department of Pharmacy Wellstar MCG Health  Augusta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyuan","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Statistics University of Georgia Franklin College of Arts and Sciences  Athens Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1806-0883","authenticated-orcid":false,"given":"Xianyan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Statistics University of Georgia Franklin College of Arts and Sciences  Athens Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Statistics University of Georgia Franklin College of Arts and Sciences  Athens Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1751-9012","authenticated-orcid":false,"given":"John W.","family":"Devlin","sequence":"additional","affiliation":[{"name":"Northeastern University School of Pharmacy  Boston Massachusetts USA"},{"name":"Division of Pulmonary and Critical Care Medicine Brigham and Women's Hospital  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1453-4404","authenticated-orcid":false,"given":"David J.","family":"Murphy","sequence":"additional","affiliation":[{"name":"Division of Pulmonary, Allergy, Critical Care and Sleep Medicine Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5171-8405","authenticated-orcid":false,"given":"Susan E.","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Clinical and Administrative Pharmacy University of Georgia College of Pharmacy  Athens Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6660-9749","authenticated-orcid":false,"given":"Brian","family":"Murray","sequence":"additional","affiliation":[{"name":"University of Colorado Skaggs School of Pharmacy  Aurora Colorado USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8366-4811","authenticated-orcid":false,"given":"Rishikesan","family":"Kamaleswaran","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1958-5374","authenticated-orcid":false,"given":"Amoreena","family":"Most","sequence":"additional","affiliation":[{"name":"Department of Pharmacy University of New Mexico Health System  Albuquerque New Mexico USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2020-0571","authenticated-orcid":false,"given":"Andrea","family":"Sikora","sequence":"additional","affiliation":[{"name":"Department of Clinical and Administrative Pharmacy University of Georgia College of Pharmacy  Athens Georgia USA"},{"name":"Department of Biomedical Informatics University of Colorado School of Medicine  Aurora Colorado USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the MRC\u2010ICU Investigator Team","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/ki.2009.159"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/08971900211008261"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/0897190019853979"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrc.2020.07.004"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-020-2795-9"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/ajhp\/zxab453"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/11795468221095875"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1177\/0897190021999792"},{"key":"e_1_2_11_10_1","article-title":"Improving irregular temporal modeling by integrating synthetic data to the electronic medical record using conditional GANs: a case study of fluid overload prediction in the intensive care unit","author":"Rafiei A","year":"2023","journal-title":"medRxiv"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-46735-3"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11020336"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-019-2411-z"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04437-2"},{"key":"e_1_2_11_15_1","first-page":"15562","article-title":"Cluster analysis driven by unsupervised latent feature learning of intensive care unit medications to identify novel pharmacophenotypes of critically ill patients","volume":"13","author":"Sikora A","year":"2023","journal-title":"Research Square"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2013.281053"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins GS","year":"2024","journal-title":"BMJ"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.39335.541782.AD"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.201504-187OC"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae033"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1039\/C3AY41907J"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_32"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.065"},{"key":"e_1_2_11_25_1","unstructured":"DengS.Syuand\/unsupervisedfoprediction\u2010: A time\u2010dependent unsupervised machine learning (ML) analysis was conducted to determine patterns of IV medication use associated with fo.2024<https:\/\/github.com\/SyuanD\/UnsupervisedFOPrediction\u2010git>"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-20910-4"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-020-2785-y"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0789-4"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-17091-5"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrc.2020.10.006"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-018-2301-9"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-37908-1"}],"container-title":["Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/accpjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/phar.4642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T16:49:01Z","timestamp":1761065341000},"score":1,"resource":{"primary":{"URL":"https:\/\/accpjournals.onlinelibrary.wiley.com\/doi\/10.1002\/phar.4642"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,3]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10.1002\/phar.4642"],"URL":"https:\/\/doi.org\/10.1002\/phar.4642","archive":["Portico"],"relation":{},"ISSN":["0277-0008","1875-9114"],"issn-type":[{"value":"0277-0008","type":"print"},{"value":"1875-9114","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,3]]},"assertion":[{"value":"2024-10-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}