{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:21:59Z","timestamp":1785424919138,"version":"3.56.0"},"reference-count":31,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Capital\u2019s Funds for Health Improvement and Research","award":["2026-2-2102"],"award-info":[{"award-number":["2026-2-2102"]}]},{"name":"Capital\u2019s Funds for Health Improvement and Research","award":["2024-2-2102"],"award-info":[{"award-number":["2024-2-2102"]}]},{"name":"High-level Public Health Technical Personnel Construction Project of Beijing Municipal Health Commission","award":["Academic leader-03-02"],"award-info":[{"award-number":["Academic leader-03-02"]}]},{"award":["Academic leader-03-02"],"award-info":[{"award-number":["Academic leader-03-02"]}],"id":[{"id":"https:\/\/ror.org\/0374a5s68","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Children"],"abstract":"<jats:p>Background: Moderate-to-severe preterm brain injury (PBI), including intraventricular hemorrhage (IVH) and periventricular leukomalacia (PVL), remains an important cause of adverse neurodevelopmental outcomes in preterm infants. Early risk stratification using routinely collected clinical data may help prioritize surveillance in vulnerable infants. Methods: We retrospectively included 318 preterm infants admitted between 2015 and 2024 as the development cohort. Thirty-three candidate predictors derived from perinatal factors, first laboratory tests within 24 h of admission, and selected early hospitalization variables were evaluated. Seven machine-learning algorithms were developed using stratified 10 \u00d7 5 nested cross-validation with prespecified preprocessing, class-balancing, and feature-selection procedures. Candidate models were compared primarily using the mean fold-level area under the receiver operating characteristic curve (AUROC). After model selection, the finalized LightGBM model was calibrated using Platt scaling, and its pooled out-of-fold (OOF) performance was summarized. Two prespecified thresholds (Youden and high-sensitivity) were used for risk stratification. A small independent temporal cohort of 35 infants was used for preliminary external validation. Results: PBI occurred in 62\/318 infants (19.5%) in the development cohort and 6\/35 infants (17.1%) in the temporal external cohort. During candidate-model comparison, LightGBM achieved the highest mean fold-level AUROC (0.768, 95% CI 0.708\u20130.825). The finalized 14-feature LightGBM model, evaluated using pooled OOF predictions after Platt calibration, yielded an AUROC of 0.747 (95% CI 0.679\u20130.811), a PR-AUC of 0.392, and a Brier score of 0.136. At the Youden threshold (0.18), sensitivity was approximately 0.70 and specificity approximately 0.85; at the high-sensitivity threshold (0.10), sensitivity was approximately 0.95 and specificity approximately 0.50. Key predictors included ventilation status and early physiologic and laboratory indicators. In the small temporal external cohort (n = 35), the AUROC was 0.897 (95% CI 0.672\u20131.000); however, this high point estimate should not be overinterpreted because of the limited sample size, wide confidence interval, and suboptimal calibration, and should therefore be considered preliminary. Conclusions: We developed an interpretable LightGBM model using routinely available early postnatal and early hospitalization data to support risk stratification for PBI in preterm infants. The model showed moderate internal discrimination and a positive net benefit across clinically relevant thresholds. Preliminary temporal external validation in a small cohort yielded highly uncertain estimates; larger multicenter studies are needed to confirm generalizability, refine calibration, and determine the most appropriate implementation strategy before routine clinical use.<\/jats:p>","DOI":"10.3390\/children13060796","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:50:58Z","timestamp":1781157058000},"page":"796","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Developing and Validating a Machine Learning Model to Predict Brain Injury in Preterm Infants Using Multisource Data from the Early Postnatal Period"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8660-1226","authenticated-orcid":false,"given":"Pu","family":"Xu","sequence":"first","affiliation":[{"name":"Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100020, China"},{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongying","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7407-3227","authenticated-orcid":false,"given":"Peicen","family":"Zou","sequence":"additional","affiliation":[{"name":"Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100020, China"},{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglin","family":"Lu","sequence":"additional","affiliation":[{"name":"Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100020, China"},{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7890-9723","authenticated-orcid":false,"given":"Dongmiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2222-3020","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100020, China"},{"name":"Department of Neonatology, Capital Center for Children\u2019s Health, Capital Medical University, Capital Institute of Pediatrics, Beijing 100020, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1016\/S0140-6736(23)00878-4","article-title":"National, regional, and global estimates of preterm birth in 2020, with trends from 2010: A systematic analysis","volume":"402","author":"Ohuma","year":"2023","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1001\/jamapediatrics.2023.5727","article-title":"Two-year autism risk screening and 3-year developmental outcomes in very preterm infants","volume":"178","author":"Shuster","year":"2024","journal-title":"JAMA Pediatr."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s13052-023-01467-y","article-title":"Neurodevelopmental outcomes of very low birth weight preterms in preschool childhood: A prospective cohort study","volume":"49","author":"Battajon","year":"2023","journal-title":"Ital. J. Pediatr."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.wneu.2021.06.043","article-title":"Intraventricular hemorrhage in premature infants: A historical review","volume":"153","author":"Deger","year":"2021","journal-title":"World Neurosurg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1001\/jamapediatrics.2024.5998","article-title":"Occurrence and time of onset of intraventricular hemorrhage in preterm neonates: A systematic review and meta-analysis of individual patient data","volume":"179","author":"Nagy","year":"2025","journal-title":"JAMA Pediatr."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1213\/ANE.0000000000000705","article-title":"Outcomes for extremely premature infants","volume":"120","author":"Glass","year":"2015","journal-title":"Anesth. Analg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e2452883","DOI":"10.1001\/jamanetworkopen.2024.52883","article-title":"Intraventricular hemorrhage and survival, multimorbidity, and neurodevelopment","volume":"8","author":"Rees","year":"2025","journal-title":"JAMA Netw. Open"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, Y., Song, J., Zhang, X., Kang, W., Li, W., Yue, Y., Zhang, S., Xu, F., Wang, X., and Zhu, C. (2022). The impact of different degrees of intraventricular hemorrhage on mortality and neurological outcomes in very preterm infants: A prospective cohort study. Front. Neurol., 13.","DOI":"10.3389\/fneur.2022.853417"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"113600","DOI":"10.1016\/j.jpeds.2023.113600","article-title":"The impact of intraventricular hemorrhage and periventricular leukomalacia on mortality and neurodevelopmental outcome in very preterm and very low birthweight infants: A prospective population-based cohort study","volume":"262","author":"Pascal","year":"2023","journal-title":"J. Pediatr."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1136\/archdischild-2022-324457","article-title":"Change in neurodevelopmental outcomes for extremely premature infants over time: A systematic review and meta-analysis","volume":"108","author":"Kaempf","year":"2023","journal-title":"Arch. Dis. Child. Fetal Neonatal Ed."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1542\/peds.2015-0944","article-title":"Periventricular\/intraventricular hemorrhage and neurodevelopmental outcomes: A meta-analysis","volume":"136","author":"Mukerji","year":"2015","journal-title":"Pediatrics"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1093\/pch\/pxaa033","article-title":"Routine imaging of the preterm neonatal brain","volume":"25","author":"Guillot","year":"2020","journal-title":"Paediatr. Child Health"},{"key":"ref_13","first-page":"CD003311","article-title":"Cooling for newborns with hypoxic ischaemic encephalopathy","volume":"2013","author":"Jacobs","year":"2013","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/B978-0-444-64029-1.00010-2","article-title":"Neonatal encephalopathy and hypoxic\u2013ischemic encephalopathy","volume":"162","author":"Gunn","year":"2019","journal-title":"Handb. Clin. Neurol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"11113","DOI":"10.1038\/s41598-024-62033-y","article-title":"Predicting severe intraventricular hemorrhage or early death using machine learning algorithms in VLBWI of the Korean Neonatal Network Database","volume":"14","author":"Kim","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"108559","DOI":"10.1016\/j.cmpb.2024.108559","article-title":"Development and validation of an explainable model of brain injury in premature infants: A prospective cohort study","volume":"260","author":"He","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xiong, P., Wei, Y., Li, L., Kang, H., Yu, Z., Tang, H., and Pu, Y. (2025). Prediction models for intraventricular hemorrhage in very preterm infants: A systematic review. Front. Pediatr., 13.","DOI":"10.3389\/fped.2025.1605145"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3236009","article-title":"A survey of methods for explaining black box models","volume":"51","author":"Guidotti","year":"2018","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/538020a","article-title":"Can we open the black box of AI?","volume":"538","author":"Castelvecchi","year":"2016","journal-title":"Nature"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"10102","DOI":"10.1038\/s41598-025-90901-8","article-title":"Early prediction of intraventricular hemorrhage in very low birth weight infants using deep neural networks with attention in low-resource settings","volume":"15","author":"Ahmadzadeh","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Afifi, J., Ahmad, T., Guida, A., Vincer, M.J., and Stewart, S.A. (2024). Prediction of Neurodevelopmental Outcomes in Very Preterm Infants: Comparing Machine Learning Methods to Logistic Regression. Children, 11.","DOI":"10.3390\/children11121512"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10833","DOI":"10.1038\/s41598-024-61749-1","article-title":"Predicting early mortality and severe intraventricular hemorrhage in very-low birth weight preterm infants: A nationwide, multicenter study using machine learning","volume":"14","author":"Yang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hu, Y., Li, Q., Huang, Q., and Yan, L. (2025). Development and Validation of a Nomogram for Predicting Early-onset Severe Intraventricular Hemorrhage in Extremely Preterm Infants. Front. Pediatr., 13.","DOI":"10.3389\/fped.2025.1644298"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cesare, M., Nurchis, M.C., Nursing and Public Health Group, Damiani, G., and Cocchieri, A. (2025). Ranking Nursing Diagnoses by Predictive Relevance for Intensive Care Unit Transfer Risk in Adult and Pediatric Patients: A Machine Learning Approach with Random Forest. Healthcare, 13.","DOI":"10.3390\/healthcare13111339"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"23740","DOI":"10.1038\/s41598-024-74298-4","article-title":"Development of a machine learning model to identify intraventricular hemorrhage using time-series analysis in preterm infants","volume":"14","author":"Han","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1136\/archdischild-2024-327366","article-title":"Validation of a machine learning algorithm for identifying infants at risk of hypoxic ischaemic encephalopathy in a large unseen data set","volume":"110","author":"Murray","year":"2025","journal-title":"Arch. Dis. Child. Fetal Neonatal Ed."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2076","DOI":"10.1007\/s00247-025-06327-x","article-title":"Development and validation of a cranial ultrasound imaging-based deep learning model for periventricular-intraventricular haemorrhage detection and grading: A two-centre study","volume":"55","author":"Peng","year":"2025","journal-title":"Pediatr. Radiol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ashoori, M., O\u2019toole, J.M., O\u2019halloran, K.D., Naulaers, G., Thewissen, L., Miletin, J., Cheung, P.-Y., El-Khuffash, A., Van Laere, D., and Stra\u0148\u00e1k, Z. (2023). Machine learning detects intraventricular haemorrhage in extremely preterm infants. Children, 10.","DOI":"10.3390\/children10060917"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jeon, G.W., Lee, Y.S., Hahn, W.-H., and Jun, Y.H. (2024). A Predictive Model for Perinatal Brain Injury Using Machine Learning Based on Early Birth Data. Children, 11.","DOI":"10.3390\/children11111313"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.1007\/s00330-024-11028-4","article-title":"Can deep learning classify cerebral ultrasound images for the detection of brain injury in very preterm infants?","volume":"35","author":"Ahmad","year":"2025","journal-title":"Eur. Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e2349111","DOI":"10.1001\/jamanetworkopen.2023.49111","article-title":"Prediction of 2-year cognitive outcomes in very preterm infants using machine learning methods","volume":"6","author":"Bowe","year":"2023","journal-title":"JAMA Netw. Open"}],"container-title":["Children"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9067\/13\/6\/796\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:33:26Z","timestamp":1781159606000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9067\/13\/6\/796"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":31,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["children13060796"],"URL":"https:\/\/doi.org\/10.3390\/children13060796","relation":{},"ISSN":["2227-9067"],"issn-type":[{"value":"2227-9067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]}}}