{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T06:27:02Z","timestamp":1786602422896,"version":"build-2736575974"},"reference-count":19,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pediatr."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate a machine learning\u2013based model for predicting the risk of peripherally inserted central catheter (PICC)\u2013associated bloodstream infection (CRBSI) in preterm infants.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This retrospective multicenter study included 151 preterm infants with CRBSI and 302 matched controls from a tertiary hospital (2017\u20132024), randomly divided into a training set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009317) and an internal validation set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009136). An additional 96 cases from four tertiary hospitals were used for external validation. Eight significant predictors identified by univariate analysis were used to construct five models: Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF). Model performance was evaluated using the area under the curve (AUC), accuracy, precision, recall, and F1 score. The Shapley Additive Explanations (SHAP) was applied for model interpretation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Eight variables were identified as key predictors, including puncture duration, catheterized vein, duration and frequency of mechanical ventilation, catheter dwell time, fetal distress, hypoalbuminemia, and antibiotic use within 24\u2005h after birth. Infection rates increased markedly with prolonged puncture duration (6% for &amp;lt; 30\u2005min vs 78% for 30\u201360\u2005min vs 93% for &amp;gt;60\u2005min) and catheter dwell time (21% for &amp;lt;14 days vs 32% for 14\u201321 days vs 47% for &amp;gt;21 days). Femoral vein catheterization showed the highest infection rate (82%). In the internal validation set, the AUCs of LR, XGBoost, DT, SVM, and RF were 0.89, 0.86, 0.87, 0.88, and 0.95, respectively; in the external validation set, they were 0.89, 0.88, 0.87, 0.93, and 0.96. The RF model achieved the highest accuracy in both internal (0.91) and external (0.90) validation sets, while SVM showed the highest external accuracy (0.92). Precision ranged from 0.79 to 0.89, recall from 0.27 to 0.31, and F1 scores from 0.42 to 0.45. SHAP analysis showed that puncture duration was the most important predictor, followed by catheterized vein and mechanical ventilation\u2013related variables.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The RF model demonstrated superior performance in predicting CRBSI risk in preterm infants with PICC placement. This model may facilitate early identification of high-risk patients and support clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fped.2026.1838914","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T05:32:05Z","timestamp":1786599125000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of a machine learning-based risk prediction model for PICC-associated bloodstream infections in preterm infants: a retrospective multicenter study"],"prefix":"10.3389","volume":"14","author":[{"given":"Ruiqing","family":"Song","sequence":"first","affiliation":[{"name":"Department of Neonatal Intensive Care, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhirui","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neonatal Intensive Care, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denghui","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Neonatal Intensive Care, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomin","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Neonatal Intensive Care, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingxi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neonatal Intensive Care, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junge","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Nursing, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Nursing, The Third Affiliated Hospital of Zhengzhou University","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"987512","DOI":"10.3389\/fped.2022.987512","article-title":"A review of neonatal peripherally inserted central venous catheters in extremely or very low birthweight infants based on a 3-year clinical practice: complication incidences and risk factors","volume":"10","author":"Wu","year":"2022","journal-title":"Front Pediatr"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e77904","DOI":"10.7759\/cureus.77904","article-title":"Utilization of peripherally inserted central catheters in neonates within the neonatal intensive care unit: a decadal single-center study","volume":"17","author":"Fu","year":"2025","journal-title":"Cureus"},{"key":"B3","doi-asserted-by":"publisher","first-page":"218","DOI":"10.34172\/aim.2023.33","article-title":"Complications and related risk factors of peripherally inserted central catheters in neonates: a historical cohort study","volume":"26","author":"Razavinejad","year":"2023","journal-title":"Arch Iran Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s10354-022-00952-z","article-title":"Umbilical venous catheter- and peripherally inserted central catheter-associated complications in preterm infants with birth weight<1250\u2005g: results from a survey in Austria and Germany","volume":"173","author":"Hess","year":"2023","journal-title":"Wien Med Wochenschr"},{"key":"B5","doi-asserted-by":"publisher","first-page":"141","DOI":"10.7499\/j.issn.1008-8830.2109147","article-title":"Analysis of risk factors for peripherally inserted central catheter-associated bloodstream infection in children","volume":"24","author":"Xu","year":"2022","journal-title":"Chin J Contemp Pediatr"},{"key":"B6","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1017\/ice.2016.55","article-title":"Limiting the number of lumens in peripherally inserted central catheters to improve outcomes and reduce cost: a simulation study","volume":"37","author":"Ratz","year":"2016","journal-title":"Infect Control Hosp Epidemiol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.ajic.2011.03.014","article-title":"Length of stay and charges associated with healthcare-acquired bloodstream infections","volume":"40","author":"AL-Rawajfah","year":"2012","journal-title":"Am J Infect Control"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e18494","DOI":"10.1097\/MD.0000000000018494","article-title":"Early mortality attributable to PICC-lines in 4 public hospitals of Marseille from 2010 to 2016","volume":"99","author":"Bessis","year":"2020","journal-title":"Medicine (Baltimore)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1080\/10408363.2020.1857681","article-title":"Potential value and impact of data mining and machine learning in clinical diagnostics","volume":"58","author":"Saberi-Karimian","year":"2021","journal-title":"Crit Rev Clin Lab Sci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"6679512","DOI":"10.1155\/2021\/6679512","article-title":"Involvement of machine learning tools in healthcare decision making","volume":"2021","author":"Jayatilake","year":"2021","journal-title":"J Healthc Eng"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1253\/circj.CJ-20-1121","article-title":"Clinical application of machine learning-based artificial intelligence in the diagnosis, prediction, and classification of cardiovascular diseases","volume":"85","author":"Shu","year":"2021","journal-title":"Circ J"},{"key":"B12","doi-asserted-by":"publisher","first-page":"104679","DOI":"10.1016\/j.ijmedinf.2021.104679","article-title":"Potential applications and performance of machine learning techniques and algorithms in clinical practice: a systematic review","volume":"159","author":"Nwanosike","year":"2022","journal-title":"Int J Med Inform"},{"key":"B13","first-page":"141","article-title":"Risk factors for peripherally inserted central catheterization-associated bloodstream infection in neonates","volume":"24","author":"Xu","year":"2022","journal-title":"Chin J Contemp Pediatr"},{"key":"B14","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1086\/651303","article-title":"Use of central venous catheter and peripheral venous catheter as risk factors for nosocomial bloodstream infection in very-low-birth-weight infants","volume":"31","author":"Geffers","year":"2010","journal-title":"Infect Control Hosp Epidemiol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e162","DOI":"10.1093\/cid\/cir257","article-title":"Guidelines for the prevention of intravascular catheter-related infections","volume":"52","author":"O'Grady","year":"2011","journal-title":"Clin Infect Dis"},{"key":"B16","first-page":"349","volume-title":"Health Statistics","author":"Li","year":"2016"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.12102\/j.issn.1009-6493.2024.12.007","article-title":"Development of a frailty risk prediction model for elderly patients with chronic heart failure based on machine learning","volume":"38","author":"Hai","year":"2024","journal-title":"Nurs Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/03772063.2022.2108916","article-title":"An effective chronic disease prediction using multi-objective firefly optimisation random forest algorithm","volume":"70","author":"Kavi Priya","year":"2022","journal-title":"IETE J Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"432","DOI":"10.3969\/j.issn.1007-953X.2020.04.024","article-title":"Application and comparison of machine learning algorithms in disease risk prediction","volume":"23","author":"Huang","year":"2020","journal-title":"Chin Health Res"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1838914\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T05:32:13Z","timestamp":1786599133000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1838914\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":19,"alternative-id":["10.3389\/fped.2026.1838914"],"URL":"https:\/\/doi.org\/10.3389\/fped.2026.1838914","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"article-number":"1838914"}}