{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:19:59Z","timestamp":1790767199076,"version":"4.1.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T00:00:00Z","timestamp":1780099200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":67,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Health Commission of Jilin Province","award":["2025WS-KA031"],"award-info":[{"award-number":["2025WS-KA031"]}]},{"DOI":"10.13039\/501100011789","name":"Department of Science and Technology of Jilin Province","doi-asserted-by":"crossref","award":["YDZJ202601ZYTS678"],"award-info":[{"award-number":["YDZJ202601ZYTS678"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100011789","name":"Department of Science and Technology of Jilin Province","doi-asserted-by":"crossref","award":["YDZJ202502CXJD064"],"award-info":[{"award-number":["YDZJ202502CXJD064"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018684","name":"National Health Commission of the People's Republic of China","doi-asserted-by":"crossref","award":["Ji Cai She Zhi [2025] No. 284"],"award-info":[{"award-number":["Ji Cai She Zhi [2025] No. 284"]}],"id":[{"id":"10.13039\/501100018684","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Peripherally inserted central catheters (PICCs) are widely used vascular access devices in intensive care, yet thrombotic complications remain a significant clinical concern. Traditional risk assessment tools fail to capture the complex, non-linear interactions among thrombosis risk factors in critically ill patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort study, conducted in adherence to TRIPOD\u2009+\u2009AI guidelines, developed and compared five machine learning models for predicting PICC-associated thrombotic complications using data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. A total of 8,145 PICC insertions from 6,376 patients were analyzed, with 29 predictor variables spanning demographics, coagulation parameters, hematologic indices, renal function, vital signs, comorbidities, and treatment variables. Synthetic Minority Over-sampling Technique (SMOTE) addressed class imbalance (16.88% event rate), applied exclusively to the training set after the train-test split. Hyperparameters were optimized via five-fold cross-validated grid search.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Random Forest achieved the best discriminative performance (AUC-ROC 0.809, 95% CI: 0.780\u20130.838, bootstrap\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u20092,000), significantly outperforming all other models on DeLong\u2019s test (all\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&lt;\u20090.01); its calibration slope of 1.369 indicated mild underconfidence. Decision curve analysis confirmed net clinical benefit for the three tree-based ensembles across threshold probabilities of approximately 1\u201350%. Feature importance analysis identified prior thrombosis history as the dominant predictor, followed by coagulation parameters and hematologic indices. Sensitivity analyses using patient-clustered data splitting, multiple imputation (m\u2009=\u20095, Rubin\u2019s rules), first-PICC-only subsets, and a no-prior-thrombosis subgroup confirmed the robustness of the primary findings.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>These findings support the development of machine learning-based clinical decision support tools for individualized thrombosis risk stratification in critical care settings. The completed TRIPOD\u2009+\u2009AI checklist is provided as Additional file 1.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-026-03607-w","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T18:23:14Z","timestamp":1780165394000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning prediction of PICC-associated thrombotic complications in critically ill patients"],"prefix":"10.1186","volume":"26","author":[{"given":"Liyan","family":"Xia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengying","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"3607_CR1","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1016\/j.amjmed.2015.01.027","volume":"128","author":"N Fallouh","year":"2015","unstructured":"Fallouh N, McGuirk HM, Flanders SA, Chopra V. Peripherally inserted central catheter-associated deep vein thrombosis: a narrative review. Am J Med. 2015;128:722\u201338. https:\/\/doi.org\/10.1016\/j.amjmed.2015.01.027.","journal-title":"Am J Med"},{"key":"3607_CR2","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1111\/jocn.12227","volume":"23","author":"XL Yi","year":"2014","unstructured":"Yi XL, Chen J, Li J, Feng L, Wang Y, Zhu JA, et al. Risk factors associated with PICC-related upper extremity venous thrombosis in cancer patients. J Clin Nurs. 2014;23:837\u201343. https:\/\/doi.org\/10.1111\/jocn.12227.","journal-title":"J Clin Nurs"},{"issue":"9","key":"3607_CR3","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1016\/j.amjmed.2015.03.028","volume":"128","author":"MT Greene","year":"2015","unstructured":"Greene MT, Flanders SA, Woller SC, Bernstein SJ, Chopra V. The association between PICC use and venous thromboembolism in upper and lower extremities. Am J Med. 2015;128(9):986\u201393. https:\/\/doi.org\/10.1016\/j.amjmed.2015.03.028.","journal-title":"Am J Med"},{"key":"3607_CR4","doi-asserted-by":"publisher","first-page":"e19409","DOI":"10.1097\/MD.0000000000019409","volume":"99","author":"G Wang","year":"2020","unstructured":"Wang G, Li Y, Wu C, Guo L, Hao L, Liao H, Xiao X, Liu S, Luo L. The clinical features and related factors of PICC-related upper extremity asymptomatic venous thrombosis in cancer patients: a prospective study. Med (Baltim). 2020;99:e19409. https:\/\/doi.org\/10.1097\/MD.0000000000019409.","journal-title":"Med (Baltim)"},{"key":"3607_CR5","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/S0140-6736(13)60592-9","volume":"382","author":"V Chopra","year":"2013","unstructured":"Chopra V, Anand S, Hickner A, Buist M, Rogers MAM, Saint S, Flanders SA. Risk of venous thromboembolism associated with peripherally inserted central catheters: a systematic review and meta-analysis. Lancet. 2013;382:311\u201325. https:\/\/doi.org\/10.1016\/S0140-6736(13)60592-9.","journal-title":"Lancet"},{"key":"3607_CR6","doi-asserted-by":"publisher","first-page":"107602962211440","DOI":"10.1177\/10760296221144041","volume":"29","author":"A Bahl","year":"2023","unstructured":"Bahl A, Alsbrooks K, Gala S, Hoerauf K. Symptomatic deep vein thrombosis associated with peripherally inserted central catheters of different diameters: a systematic review and meta-analysis. Clin Appl Thromb Hemost. 2023;29:10760296221144041. https:\/\/doi.org\/10.1177\/10760296221144041.","journal-title":"Clin Appl Thromb Hemost"},{"key":"3607_CR7","doi-asserted-by":"publisher","first-page":"1347297","DOI":"10.3389\/fonc.2024.1347297","volume":"14","author":"X Wang","year":"2024","unstructured":"Wang X, He Y, Chu J, Xu J. Risk factors analysis and the establishment of nomogram prediction model for PICC-related venous thrombosis in patients with lymphoma. Front Oncol. 2024;14:1347297. https:\/\/doi.org\/10.3389\/fonc.2024.1347297.","journal-title":"Front Oncol"},{"key":"3607_CR8","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1378\/chest.10-0154","volume":"138","author":"RS Evans","year":"2010","unstructured":"Evans RS, Sharp JH, Linford LH, Lloyd JF, Tripp JS, Jones JP, Woller SC, Stevens SM, Elliott CG, Weaver LK. Risk of symptomatic DVT associated with peripherally inserted central catheters. Chest. 2010;138:803\u201310. https:\/\/doi.org\/10.1378\/chest.10-0154.","journal-title":"Chest"},{"key":"3607_CR9","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1093\/jjco\/hyae055","volume":"54","author":"F Meng","year":"2024","unstructured":"Meng F, Fan S, Guo L, Jia Z, Chang H, Liu F. Incidence and risk factors of PICC-related thrombosis in breast cancer: a meta-analysis. Jpn J Clin Oncol. 2024;54:863\u201372. https:\/\/doi.org\/10.1093\/jjco\/hyae055.","journal-title":"Jpn J Clin Oncol"},{"key":"3607_CR10","doi-asserted-by":"publisher","first-page":"483","DOI":"10.6004\/jnccn.2024.0046","volume":"22","author":"MB Streiff","year":"2024","unstructured":"Streiff MB, Holmstrom B, Angelini D, Ashrani A, Buckner T, Diep R, Fertrin KY, Fogerty AE, Crestani NG, Gangaraju R, et al. Cancer-associated venous thromboembolic disease, version 2.2024, NCCN clinical practice guidelines in oncology. J Natl Compr Canc Netw. 2024;22:483\u2013506. https:\/\/doi.org\/10.6004\/jnccn.2024.0046.","journal-title":"J Natl Compr Canc Netw"},{"key":"3607_CR11","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.disamonth.2005.02.003","volume":"51","author":"JA Caprini","year":"2005","unstructured":"Caprini JA. Thrombosis risk assessment as a guide to quality patient care. Dis Mon. 2005;51:70\u20138. https:\/\/doi.org\/10.1016\/j.disamonth.2005.02.003.","journal-title":"Dis Mon"},{"key":"3607_CR12","doi-asserted-by":"crossref","unstructured":"Gennatas ED, Chen JH. Artificial intelligence in medicine: past, present, and future. In: Xing L, Giger ML, Min JK, editors. Artificial intelligence in medicine: technical basis and clinical applications. Academic Press ; 2021. p. 3\u201318.","DOI":"10.1016\/B978-0-12-821259-2.00001-6"},{"key":"3607_CR13","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25:44\u201356. https:\/\/doi.org\/10.1038\/s41591-018-0300-7.","journal-title":"Nat Med"},{"key":"3607_CR14","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1111\/jocn.15171","volume":"29","author":"D Tschannen","year":"2020","unstructured":"Tschannen D, Anderson C. The pressure injury predictive model: a framework for hospital-acquired pressure injuries. J Clin Nurs. 2020;29:1398\u2013421. https:\/\/doi.org\/10.1111\/jocn.15171.","journal-title":"J Clin Nurs"},{"key":"3607_CR15","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","volume":"46","author":"S Nemati","year":"2018","unstructured":"Nemati S, Holder A, Razmi F, Stanley MD, Clifford GD, Buchman TG. An interpretable machine learning model for accurate prediction of sepsis in the ICU. Crit Care Med. 2018;46:547\u201353. https:\/\/doi.org\/10.1097\/CCM.0000000000002936.","journal-title":"Crit Care Med"},{"key":"3607_CR16","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev N, Glorot X, Rae JW, Zielinski M, Askham H, Saraiva A, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572:116\u20139. https:\/\/doi.org\/10.1038\/s41586-019-1390-1.","journal-title":"Nature"},{"key":"3607_CR17","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1111\/jth.12549","volume":"12","author":"V Chopra","year":"2014","unstructured":"Chopra V, Ratz D, Kuhn L, Lopus T, Lee A, Krein S. Peripherally inserted central catheter-related deep vein thrombosis: contemporary patterns and predictors. J Thromb Haemost. 2014;12:847\u201354. https:\/\/doi.org\/10.1111\/jth.12549.","journal-title":"J Thromb Haemost"},{"key":"3607_CR18","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, et al. TRIPOD + AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. https:\/\/doi.org\/10.1136\/bmj-2023-078378.","journal-title":"BMJ"},{"key":"3607_CR19","doi-asserted-by":"publisher","DOI":"10.13026\/kpb9-mt58","author":"A Johnson","year":"2024","unstructured":"Johnson A, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, et al. MIMIC-IV (version 3.1). PhysioNet. 2024. https:\/\/doi.org\/10.13026\/kpb9-mt58.","journal-title":"PhysioNet"},{"key":"3607_CR20","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321\u201357. https:\/\/doi.org\/10.1613\/jair.953.","journal-title":"J Artif Intell Res"},{"key":"3607_CR21","doi-asserted-by":"publisher","first-page":"507","DOI":"10.52202\/068431-0037","volume":"35","author":"L Grinsztajn","year":"2022","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G. Why do tree-based models still outperform deep learning on typical tabular data? Adv Neural Inf Process Syst. 2022;35:507\u201320.","journal-title":"Adv Neural Inf Process Syst"},{"key":"3607_CR22","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837\u201345. https:\/\/doi.org\/10.2307\/2531595.","journal-title":"Biometrics"},{"key":"3607_CR23","doi-asserted-by":"publisher","unstructured":"Youden WJ. Index for rating diagnostic tests. Cancer. 1950;3:32\u20135. https:\/\/doi.org\/10.1002\/1097-0142(1950)3:1%3C32::AID-CNCR2820030106%3E3.0.CO;2-3.","DOI":"10.1002\/1097-0142(1950)3:1%3C32::AID-CNCR2820030106%3E3.0.CO;2-3"},{"key":"3607_CR24","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","volume":"26","author":"AJ Vickers","year":"2006","unstructured":"Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models. Med Decis Mak. 2006;26:565\u201374. https:\/\/doi.org\/10.1177\/0272989X06295361.","journal-title":"Med Decis Mak"},{"key":"3607_CR25","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","volume":"380","author":"A Rajkomar","year":"2019","unstructured":"Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380:1347\u201358. https:\/\/doi.org\/10.1056\/NEJMra1814259.","journal-title":"N Engl J Med"},{"key":"3607_CR26","doi-asserted-by":"publisher","first-page":"109030","DOI":"10.1016\/j.thromres.2024.05.003","volume":"239","author":"Z Hu","year":"2024","unstructured":"Hu Z, He R, Zhao Y, Luo M, Fan Y, Li J. Risk assessment models for PICC-related venous thrombosis in adult patients with cancer: a network meta-analysis. Thromb Res. 2024;239:109030. https:\/\/doi.org\/10.1016\/j.thromres.2024.05.003.","journal-title":"Thromb Res"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-026-03607-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03607-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03607-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:48:16Z","timestamp":1785883696000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12911-026-03607-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3607"],"URL":"https:\/\/doi.org\/10.1186\/s12911-026-03607-w","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,30]]},"assertion":[{"value":"16 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Ethical approval for the MIMIC-IV database was obtained from the Institutional Review Board of Beth Israel Deaconess Medical Center (approval number: 2001P001699). Informed consent was waived due to the retrospective nature and use of de-identified data. This secondary analysis required no additional approval. All procedures complied with the MIMIC-IV data use agreement and relevant regulations.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"287"}}