{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:29:30Z","timestamp":1754152170523,"version":"3.41.2"},"reference-count":18,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T00:00:00Z","timestamp":1753056000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec018\">\n<jats:title>Objectives<\/jats:title>\n<jats:p>Predicting optimal coagulation control using heparin in intensive care units (ICUs) remains a significant challenge. This study aimed to develop a machine learning (ML) model to predict activated partial thromboplastin time (aPTT) in ICU patients receiving unfractionated heparin for anticoagulation and to identify key predictive factors.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec019\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Data were obtained from the Tokushukai Medical Database, covering six hospitals with ICUs in Japan, collected between 2018 and 2022. The study included 945 ICU patients who received unfractionated heparin. The dataset comprised both static and dynamic features, which were used to construct and train ML models. Models were developed to predict aPTT following initial and multiple heparin doses. Model performance was evaluated using the area under the receiver operating characteristic curve (ROC AUC), area under the precision\u2013recall curve (PR AUC), precision, recall, F1 score, and accuracy. SHAP analysis was conducted to determine key predictive factors.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec020\">\n<jats:title>Results<\/jats:title>\n<jats:p>The random forest model demonstrated the highest predictive performance, with ROC AUC values of 0.707 for the first infusion and 0.732 for multiple infusions. Corresponding PR AUC values were 0.539 and 0.551. Despite moderate overall predictive performance, the model exhibited high precision (0.585 for the first infusion and 0.589 for multiple infusions), indicating effectiveness in correctly identifying true positive cases. However, recall and F1 scores were lower, suggesting that some cases, particularly in sub-therapeutic and supra-therapeutic ranges, may have been missed. Incorporating time-series data, such as vital signs, provided only marginal improvements in performance.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec021\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>ML models demonstrated moderate performance in predicting aPTT following heparin infusion in ICU patients, with the random forest model achieving the highest classification accuracy. Although the models effectively identified true positive cases, their overall predictive performance remained limited, necessitating further refinement. The inclusion of static and dynamic features did not significantly enhance model accuracy. Future studies should explore additional factors to improve predictive models for optimizing individualized anticoagulation management in ICUs.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0328709","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T17:30:01Z","timestamp":1753119001000},"page":"e0328709","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Analysis of aPTT predictors after unfractionated heparin administration in intensive care units using machine learning models"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8987-0103","authenticated-orcid":true,"given":"Tadashi","family":"Kamio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaru","family":"Ikegami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Megumi","family":"Mizuno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seiichiro","family":"Ishii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hayato","family":"Tajima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihito","family":"Machida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2262-1898","authenticated-orcid":true,"given":"Kiyomitsu","family":"Fukaguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"issue":"5","key":"pone.0328709.ref001","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1001\/archinte.163.5.621","article-title":"Challenges to the effective use of unfractionated heparin in the hospitalized management of acute thrombosis","volume":"163","author":"EM Hylek","year":"2003","journal-title":"Arch Intern Med"},{"key":"pone.0328709.ref002","doi-asserted-by":"crossref","DOI":"10.1177\/1076029618798944","article-title":"Time in the therapeutic range for assessing anticoagulation quality in patients receiving continuous unfractionated heparin","volume":"24","author":"C Ting","year":"2018","journal-title":"Clin Appl Thromb Hemost"},{"issue":"9","key":"pone.0328709.ref003","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1007\/s00134-014-3406-5","article-title":"A data-driven approach to optimized medication dosing: a focus on heparin","volume":"40","author":"MM Ghassemi","year":"2014","journal-title":"Intensive Care Med"},{"issue":"6","key":"pone.0328709.ref004","article-title":"Toward optimal heparin dosing by comparing multiple machine learning methods: retrospective study","volume":"8","author":"L Su","year":"2020","journal-title":"JMIR Med Inform"},{"issue":"5","key":"pone.0328709.ref005","article-title":"A clinical prediction model to predict heparin treatment outcomes and provide dosage recommendations: development and validation study","volume":"23","author":"D Li","year":"2021","journal-title":"J Med Internet Res"},{"issue":"10","key":"pone.0328709.ref006","article-title":"A recurrent neural network model for predicting activated partial thromboplastin time after treatment with heparin: retrospective study","volume":"10","author":"SD Boie","year":"2022","journal-title":"JMIR Med Inform"},{"issue":"11","key":"pone.0328709.ref007","doi-asserted-by":"crossref","first-page":"4124","DOI":"10.1111\/bcp.14852","article-title":"Systematic review of machine learning models for personalised dosing of heparin","volume":"87","author":"N Falconer","year":"2021","journal-title":"Br J Clin Pharmacol"},{"issue":"7","key":"pone.0328709.ref008","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1177\/08850666231166349","article-title":"Dynamic prediction of patient outcomes in the intensive care unit: a scoping review of the state-of-the-art","volume":"38","author":"L Lapp","year":"2023","journal-title":"J Intensive Care Med"},{"issue":"11","key":"pone.0328709.ref009","doi-asserted-by":"crossref","first-page":"2146","DOI":"10.3390\/healthcare10112146","article-title":"Real-World Outcomes of Systemic Therapy in Japanese Patients with Cancer (Tokushukai REAl-World Data Project: TREAD): Study Protocol for a Nationwide Cohort Study","volume":"10","author":"R Shimoyama","year":"2022","journal-title":"Healthcare (Basel)"},{"issue":"1","key":"pone.0328709.ref010","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s13017-020-00303-6","article-title":"Association of pre-operative chronic kidney disease and acute kidney injury with in-hospital outcomes of emergency colorectal surgery: a cohort study","volume":"15","author":"K Miyake","year":"2020","journal-title":"World J Emerg Surg"},{"issue":"3","key":"pone.0328709.ref011","doi-asserted-by":"crossref","first-page":"623","DOI":"10.14309\/ajg.0000000000003050","article-title":"Timing of direct oral anticoagulants resumption following colorectal endoscopic submucosal dissection: a nationwide study in Japan","volume":"120","author":"C Ichita","year":"2024","journal-title":"Am J Gastroenterol"},{"issue":"1","key":"pone.0328709.ref012","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s10916-008-9220-2","article-title":"Impact of the Japanese diagnosis procedure combination-based payment system in Japan","volume":"34","author":"K Wang","year":"2010","journal-title":"J Med Syst"},{"issue":"8","key":"pone.0328709.ref013","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1093\/ndt\/gfy011","article-title":"Seasonality of acute kidney injury incidence and mortality among hospitalized patients","volume":"33","author":"M Iwagami","year":"2018","journal-title":"Nephrol Dial Transplant"},{"issue":"1","key":"pone.0328709.ref014","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1309\/N7RA-D6XN-9EQX-ABJ9","article-title":"Use of the activated partial thromboplastin time for heparin monitoring","volume":"115","author":"MA Smythe","year":"2001","journal-title":"Am J Clin Pathol"},{"issue":"24","key":"pone.0328709.ref015","doi-asserted-by":"crossref","first-page":"2994","DOI":"10.1161\/01.CIR.103.24.2994","article-title":"Guide to anticoagulant therapy: Heparin\u00a0: a statement for healthcare professionals from the American Heart Association","volume":"103","author":"American Heart Association","year":"2001","journal-title":"Circulation"},{"key":"pone.0328709.ref016","doi-asserted-by":"crossref","DOI":"10.1177\/1076029619833480","article-title":"Derivation and validation of age- and body mass index-adjusted weight-based unfractionated heparin dosing","volume":"25","author":"JW Schurr","year":"2019","journal-title":"Clin Appl Thromb Hemost"},{"issue":"23","key":"pone.0328709.ref017","first-page":"1805","article-title":"Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges","volume":"38","author":"BA Goldstein","year":"2017","journal-title":"Eur Heart J"},{"issue":"7","key":"pone.0328709.ref018","article-title":"Artificial intelligence algorithm for predicting mortality of patients with acute heart failure","volume":"14","author":"J-M Kwon","year":"2019","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T17:30:08Z","timestamp":1753119008000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328709"}},"subtitle":[],"editor":[{"given":"Elvan","family":"Wiyarta","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,7,21]]},"references-count":18,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0328709","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2025,7,21]]}}}