{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T22:27:16Z","timestamp":1791930436365,"version":"4.3.4"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002380","name":"Hanyang University","doi-asserted-by":"publisher","award":["\u00a0"],"award-info":[{"award-number":["\u00a0"]}],"id":[{"id":"10.13039\/501100002380","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pediatr."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The aim of this study is to develop an enhanced machine learning-based prediction models for bronchopulmonary dysplasia (BPD) and its severity through a two-stage approach integrated with the duration of respiratory support (RSd) using prenatal and early postnatal variables from a nationwide very low birth weight (VLBW) infant cohort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We included 16,384 VLBW infants admitted to the neonatal intensive care unit (<jats:italic>N<\/jats:italic>ICU) of the Korean Neonatal Network (KNN), a nationwide VLBW infant registry (2013\u20132020). Overall, 45 prenatal and early perinatal clinical variables were selected. A multilayer perceptron (MLP)-based network analysis, which was recently introduced to predict diseases in preterm infants, was used for modeling and a stepwise approach. Additionally, we applied a complementary MLP network and established new BPD prediction models (PMbpd). The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC) values. The Shapley method was used to determine the contribution of each variable.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We included 11,177 VLBW infants (3,724 without BPD (BPD 0), 3,383 with mild BPD (BPD 1), 1,375 with moderate BPD (BPD 2), and 2,695 with severe BPD (BPD 3) cases). Compared to conventional machine learning (ML) models, our PMbpd and two-stage PMbpd with RSd (TS-PMbpd) model outperformed both binary (0 vs. 1,2,3; 0,1 vs. 2,3; 0,1,2 vs. 3) and each severity (0 vs. 1 vs. 2 vs. 3) prediction (AUROC\u2009=\u20090.895 and 0.897, 0.824 and 0.825, 0.828 and 0.823, 0.783, and 0.786, respectively). GA, birth weight, and patent ductus arteriosus (PDA) treatment were significant variables for the occurrence of BPD. Birth weight, low blood pressure, and intraventricular hemorrhage were significant for BPD \u22652, birth weight, low blood pressure, and PDA ligation for BPD \u22653. GA, birth weight, and pulmonary hypertension were the principal variables that predicted BPD severity in VLBW infants.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>We developed a new two-stage ML model reflecting crucial BPD indicators (RSd) and found significant clinical variables for the early prediction of BPD and its severity with high predictive accuracy. Our model can be used as an adjunctive predictive model in the practical NICU field.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fped.2023.1155921","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T04:34:40Z","timestamp":1686630880000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Two-stage learning-based prediction of bronchopulmonary dysplasia in very low birth weight infants: a nationwide cohort study"],"prefix":"10.3389","volume":"11","author":[{"given":"Jae Kyoon","family":"Hwang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dae Hyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Yoon","family":"Na","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joonhyuk","family":"Son","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoon Ju","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donggoo","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Ryul","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae Hyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun-Kyung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,6,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1038\/jp.2015.124","article-title":"Respiratory morbidity, lung function and fitness assessment after bronchopulmonary dysplasia","volume":"35","author":"Praprotnik","year":"2015","journal-title":"J Perinatol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/s41572-019-0127-7","article-title":"Bronchopulmonary dysplasia","volume":"5","author":"Thebaud","year":"2019","journal-title":"Nat Rev Dis Primers"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e81","DOI":"10.3346\/jkms.2021.36.e81","article-title":"The prediction of bronchopulmonary dysplasia in very low birth weight infants through clinical indicators within 1 hour of delivery","volume":"36","author":"Shim","year":"2021","journal-title":"J Korean Med Sci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.jpeds.2018.01.043","article-title":"Bronchopulmonary dysplasia: executive summary of a workshop","volume":"197","author":"Higgins","year":"2018","journal-title":"J Pediatr"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e20172719","DOI":"10.1542\/peds.2017-2719","article-title":"Cognitive development and quality of life associated with BPD in 10-year-olds born preterm","volume":"141","author":"Sriram","year":"2018","journal-title":"Pediatrics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1164\/ajrccm.163.7.2011060","article-title":"Bronchopulmonary dysplasia","volume":"163","author":"Jobe","year":"2001","journal-title":"Am J Respir Crit Care Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"856159","DOI":"10.3389\/fped.2022.856159","article-title":"Prediction models for bronchopulmonary dysplasia in preterm infants: a systematic review","volume":"10","author":"Peng","year":"2022","journal-title":"Front Pediatr"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1038\/s41390-022-02451-8","article-title":"Bronchopulmonary dysplasia prediction models: a systematic review and meta-analysis with validation","author":"Kwok","year":"2023","journal-title":"Pediatr Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"349","DOI":"10.3389\/fped.2020.00349","article-title":"Prediction of bronchopulmonary dysplasia in preterm infants using postnatal risk factors","volume":"8","author":"Ding","year":"2020","journal-title":"Front Pediatr"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1097\/CCM.0000000000003891","article-title":"A machine learning algorithm to predict severe sepsis and septic shock: development, implementation, and impact on clinical practice","volume":"47","author":"Giannini","year":"2019","journal-title":"Crit Care Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"22353","DOI":"10.1038\/s41598-021-01640-5","article-title":"Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort","volume":"11","author":"Na","year":"2021","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"12112","DOI":"10.1038\/s41598-022-16273-5","article-title":"Development of artificial neural networks for early prediction of intestinal perforation in preterm infants","volume":"12","author":"Son","year":"2022","journal-title":"Sci Rep"},{"key":"B13","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1542\/peds.2009-2959","article-title":"Neonatal outcomes of extremely preterm infants from the NICHD neonatal research network","volume":"126","author":"Stoll","year":"2010","journal-title":"Pediatrics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.clp.2015.08.006","article-title":"Mechanical ventilation and bronchopulmonary dysplasia","volume":"42","author":"Keszler","year":"2015","journal-title":"Clin Perinatol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e226","DOI":"10.1542\/neo.21-4-e226","article-title":"Ventilation strategies in severe bronchopulmonary dysplasia","volume":"21","author":"Gibbs","year":"2020","journal-title":"Neoreviews"},{"key":"B16","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/s0022-3476(83)80366-7","article-title":"Relationship of cerebral intraventricular hemorrhage and early childhood neurologic handicaps","volume":"103","author":"Papile","year":"1983","journal-title":"J Pediatr"},{"key":"B17","doi-asserted-by":"publisher","first-page":"5600","DOI":"10.1038\/s41598-020-62595-7","article-title":"The association of pregnancy-induced hypertension with bronchopulmonary dysplasia\u2014a retrospective study based on the Korean neonatal network database","volume":"10","author":"Shin","year":"2020","journal-title":"Sci Rep"},{"key":"B18","author":"Kingma","year":""},{"key":"B19","author":"Clevert","year":""},{"key":"B20","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"B21","first-page":"448","author":"Ioffe","year":"2015"},{"key":"B22","author":"Rozemberczki","year":""},{"key":"B23","author":"Lundberg","year":""},{"key":"B24","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/j.clp.2012.06.014","article-title":"Predictors of bronchopulmonary dysplasia","volume":"39","author":"Trembath","year":"2012","journal-title":"Clin Perinatol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"e0258328","DOI":"10.1371\/journal.pone.0258328","article-title":"Risk factors and prognosis in very low birth\u00a0weight infants treated for hypotension during the first postnatal week from the Korean neonatal network","volume":"16","author":"Song","year":"2021","journal-title":"PLoS One"},{"key":"B26","doi-asserted-by":"publisher","first-page":"11206","DOI":"10.1038\/s41598-021-90769-4","article-title":"Early pulmonary hypertension is a risk factor for bronchopulmonary dysplasia-associated late pulmonary hypertension in extremely preterm infants","volume":"11","author":"Kim","year":"2021","journal-title":"Sci Rep"},{"key":"B27","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1007\/s12519-022-00635-0","article-title":"Risk factors and\u00a0machine learning prediction models for bronchopulmonary dysplasia severity\u00a0in the Chinese population","volume":"19","author":"He","year":"2023","journal-title":"World J Pediatr"},{"key":"B28","author":"Hariharan","year":"2015"},{"key":"B29","author":"Lin","year":"2016"},{"key":"B30","doi-asserted-by":"publisher","first-page":"100360","DOI":"10.1016\/j.imu.2020.100360","article-title":"A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest x-ray images based on the concatenation of Xception and ResNet50V2","volume":"19","author":"Rahimzadeh","year":"2020","journal-title":"Inform Med Unlocked"},{"key":"B31","doi-asserted-by":"publisher","first-page":"n1974","DOI":"10.1136\/bmj.n1974","article-title":"Diagnosis and management of bronchopulmonary dysplasia","volume":"375","author":"Gilfillan","year":"2021","journal-title":"Br Med J"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2023.1155921\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T04:34:44Z","timestamp":1686630884000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2023.1155921\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,13]]},"references-count":31,"alternative-id":["10.3389\/fped.2023.1155921"],"URL":"https:\/\/doi.org\/10.3389\/fped.2023.1155921","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,13]]},"article-number":"1155921"}}