Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format text download EPUB
file format pdf download PDF
side by side viewer icon HTML

Abstract

Introduction

This meta-analysis aimed to evaluate the diagnostic performance of Machine Learning (ML) models for early prediction of bronchopulmonary dysplasia (BPD) in preterm infants, addressing the need for timely risk stratification.

Methods

Systematic searches of PubMed, Embase, and other databases identified 9 eligible studies (12,755 infants). Data were extracted and pooled using bivariate generalized linear mixed models. Study quality was assessed QUADAS-2.

Results

ML models demonstrated high accuracy (pooled sensitivity: 0.81, specificity: 0.85, AUC: 0.90). Multimodal models and ensemble algorithms (., Random Forest) outperformed single-modality approaches. Models using data from the first 7 postnatal days achieved superior performance compared to those using data from day 28.

Discussion

ML enables ultra-early BPD prediction, preceding conventional diagnosis by weeks. Heterogeneity in data modalities and validation strategies highlights the need for standardized reporting.

Conclusion

ML-based BPD prediction shows promise for clinical translation but requires prospective validation and cost-effectiveness analysis.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056421036250806053617
2025-08-08
2025-10-29

  • From This Site

    /content/journals/cmir/10.2174/0115734056421036250806053617
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056421036.html?itemId=/content/journals/cmir/10.2174/0115734056421036250806053617&mimeType=html&fmt=ahah

References

  1. DankharaN. HollaI. RamaraoS. Kalikkot ThekkeveeduR. Bronchopulmonary dysplasia: Pathogenesis and pathophysiology.J. Clin. Med.20231213420710.3390/jcm1213420737445242
     [Google Scholar]
  2. ThébaudB. GossK.N. LaughonM. WhitsettJ.A. AbmanS.H. SteinhornR.H. AschnerJ.L. DavisP.G. McGrath-MorrowS.A. SollR.F. JobeA.H. Bronchopulmonary dysplasia.Nat. Rev. Dis. Primers2019517810.1038/s41572‑019‑0127‑731727986
     [Google Scholar]
  3. MoreiraA. NoronhaM. JoyJ. BierwirthN. TarrielaA. NaqviA. ZoreticS. JonesM. MarottaA. ValadieT. BrickJ. WinterC. PorterM. DeckerI. BruschettiniM. AhujaS.K. Rates of bronchopulmonary dysplasia in very low birth weight neonates: A systematic review and meta-analysis.Respir. Res.202425121910.1186/s12931‑024‑02850‑x38790002
     [Google Scholar]
  4. Lardón-FernándezM. UberosJ. Molina-OyaM. Narbona-LópezE. Epidemiological factors involved in the development of bronchopulmonary dysplasia in very low birth-weight preterm infants.Minerva Pediatr.2017691424910.23736/S0026‑4946.16.04215‑825715027
     [Google Scholar]
  5. TengM. WuT.J. JingX. DayB.W. PritchardK.A.Jr NaylorS. TengR.J. Temporal dynamics of oxidative stress and inflammation in bronchopulmonary dysplasia.Int. J. Mol. Sci.202425181014510.3390/ijms25181014539337630
     [Google Scholar]
  6. HolzfurtnerL. ShahzadT. DongY. RekersL. SeltingA. StaudeB. LauerT. SchmidtA. RivettiS. ZimmerK.P. BehnkeJ. BellusciS. EhrhardtH. When inflammation meets lung development—an update on the pathogenesis of bronchopulmonary dysplasia.Mol. Cell Pediatr.202291710.1186/s40348‑022‑00137‑z35445327
     [Google Scholar]
  7. NorthwayW.H.Jr RosanR.C. PorterD.Y. Pulmonary disease following respirator therapy of hyaline-membrane disease. Bronchopulmonary dysplasia.N. Engl. J. Med.1967276735736810.1056/NEJM1967021627607015334613
     [Google Scholar]
  8. JianM. HeS. LiuY. LiuX. GuiJ. ZhengM. FengB. ZhangX. LiuC. The high-risk factors of different severities of bronchopulmonary dysplasia (BPD) based on the national institute of child health and human development (NICHD) diagnosis criteria in 2018.J. Bras. Pneumol.2021475e2021012510.36416/1806‑3756/e2021012534614093
     [Google Scholar]
  9. ThomasJ.M. SudhadeviT. BasaP. HaA.W. NatarajanV. HarijithA. The role of sphingolipid signaling in oxidative lung injury and pathogenesis of bronchopulmonary dysplasia.Int. J. Mol. Sci.2022233125410.3390/ijms2303125435163176
     [Google Scholar]
  10. Kalikkot ThekkeveeduR. GuamanM.C. ShivannaB. Bronchopulmonary dysplasia: A review of pathogenesis and pathophysiology.Respir. Med.201713217017710.1016/j.rmed.2017.10.01429229093
     [Google Scholar]
  11. LalC.V. AmbalavananN. Genetic predisposition to bronchopulmonary dysplasia.Semin. Perinatol.201539858459110.1053/j.semperi.2015.09.00426471063
     [Google Scholar]
  12. GlaserK. JensenE.A. WrightC.J. Prevention of inflammatory disorders in the preterm neonate: An update with a special focus on bronchopulmonary dysplasia.Neonatology2024121563664510.1159/00053930338870912
     [Google Scholar]
  13. AvanzoM. StancanelloJ. PirroneG. DrigoA. ReticoA. The evolution of artificial intelligence in medical imaging: From computer science to machine and deep learning.Cancers20241621370210.3390/cancers1621370239518140
     [Google Scholar]
  14. VerderH. HeiringC. RamanathanR. ScoutarisN. VerderP. JessenT.E. HöskuldssonA. BenderL. DahlM. EschenC. Fenger-GrønJ. ReinholdtJ. SmedegaardH. SchousboeP. Bronchopulmonary dysplasia predicted at birth by artificial intelligence.Acta Paediatr.2021110250350910.1111/apa.1543832569404
     [Google Scholar]
  15. MontagnaS. MagnoD. FerrettiS. StellutiM. GonaA. DionisiC. SimonazziG. MartiniS. CorvagliaL. AcetiA. Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables.Pediatr. Pulmonol.202459123400340910.1002/ppul.2721639150150
     [Google Scholar]
  16. ChouHY LinYC HsiehSY Deep learning model for prediction of bronchopulmonary dysplasia in preterm infants using chest radiographs.J. Imaging Inform. Med.20243752063207310.1007/s10278‑024‑01050‑938499706
     [Google Scholar]
  17. LeiJ. SunT. JiangY. WuP. FuJ. ZhangT. McGrathE. Risk identification of bronchopulmonary dysplasia in premature infants based on machine learning.Front Pediatr.2021971935210.3389/fped.2021.71935234485204
     [Google Scholar]
  18. LeighR.M. PhamA. RaoS.S. VoraF.M. HouG. KentC. RodriguezA. NarangA. TanJ.B.C. ChouF.S. Machine learning for prediction of bronchopulmonary dysplasia-free survival among very preterm infants.BMC Pediatr.202222154210.1186/s12887‑022‑03602‑w36100848
     [Google Scholar]
  19. KhurshidF. CooH. KhalilA. MessihaJ. TingJ.Y. WongJ. ShahP.S. Comparison of multivariable logistic regression and machine learning models for predicting bronchopulmonary dysplasia or death in very preterm infants.Front Pediatr.2021975977610.3389/fped.2021.75977634950616
     [Google Scholar]
  20. ZhangX. YanB. JiangZ. LuoY. Machine learning identification of neutrophil extracellular trap-related genes as potential biomarkers and therapeutic targets for bronchopulmonary dysplasia.Int. J. Mol. Sci.2025267323010.3390/ijms2607323040244055
     [Google Scholar]
  21. DaiD. ChenH. DongX. ChenJ. MeiM. LuY. YangL. WuB. CaoY. WangJ. ZhouW. QianL. Bronchopulmonary dysplasia predicted by developing a machine learning model of genetic and clinical information.Front. Genet.20211268907110.3389/fgene.2021.68907134276789
     [Google Scholar]
  22. LuoL. LuoF. WuC. ZhangH. JiangQ. HeS. LiW. ZhangW. ChengY. YangP. LiZ. LiM. BaoY. JiangF. Identification of potential biomarkers in the peripheral blood of neonates with bronchopulmonary dysplasia using WGCNA and machine learning algorithms.Medicine20241034e3708310.1097/MD.000000000003708338277517
     [Google Scholar]
  23. WhitingP.F. RutjesA.W.S. WestwoodM.E. MallettS. DeeksJ.J. ReitsmaJ.B. LeeflangM.M.G. SterneJ.A.C. BossuytP.M.M. QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies.Ann. Intern. Med.2011155852953610.7326/0003‑4819‑155‑8‑201110180‑0000922007046
     [Google Scholar]
  24. EhrenkranzR.A. WalshM.C. VohrB.R. JobeA.H. WrightL.L. FanaroffA.A. WrageL.A. PooleK. Validation of the National Institutes of Health consensus definition of bronchopulmonary dysplasia.Pediatrics200511661353136010.1542/peds.2005‑024916322158
     [Google Scholar]
  25. AlThuwayneeO.F. KimS.W. NajemadenM.A. AyddaA. BalogunA.L. FayyadhM.M. ParkH.J. Demystifying uncertainty in PM10 susceptibility mapping using variable drop-off in extreme-gradient boosting (XGB) and random forest (RF) algorithms.Environ. Sci. Pollut. Res. Int.20212832435444356610.1007/s11356‑021‑13255‑433834339
     [Google Scholar]
  26. WangJ. GongX. ChenH. ZhongW. ChenY. ZhouY. ZhangW. HeY. LouM. Causative classification of ischemic stroke by the machine learning algorithm random forests.Front. Aging Neurosci.20221478863710.3389/fnagi.2022.78863735493925
     [Google Scholar]
  27. ZhuR. WangY. LiuJ.X. DaiL.Y. IPCARF: Improving lncRNA-disease association prediction using incremental principal component analysis feature selection and a random forest classifier.BMC Bioinformatics202122117510.1186/s12859‑021‑04104‑933794766
     [Google Scholar]
  28. QamarS. ÖbergR. MalyshevD. AnderssonM. A hybrid CNN-Random Forest algorithm for bacterial spore segmentation and classification in TEM images.Sci. Rep.20231311875810.1038/s41598‑023‑44212‑537907463
     [Google Scholar]
  29. QiX. WangS. FangC. JiaJ. LinL. YuanT. Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants.Redox Biol.20257910347010.1016/j.redox.2024.10347039700695
     [Google Scholar]
  30. SadaeiH.J. LoguercioS. Shafiei NeyestanakM. TorkamaniA. PrilutskyD. Zoish: A novel feature selection approach leveraging shapley additive values for machine learning applications in healthcare.Pac. Symp. Biocomput.2024298195[J].38160271
     [Google Scholar]
  31. TsayS.F. ChangC.Y. Shueh HungS. SuJ.Y. KuoC.Y. MuP.F. Pain prediction model based on machine learning and SHAP values for elders with dementia in Taiwan.Int. J. Med. Inform.202418810547510.1016/j.ijmedinf.2024.10547538743995
     [Google Scholar]
  32. O’SullivanC. TsaiD.H.T. WuI.C.Y. BoselliE. HughesC. PadmanabhanD. HsiaY. Machine learning applications on neonatal sepsis treatment: A scoping review.BMC Infect. Dis.202323144110.1186/s12879‑023‑08409‑337386442
     [Google Scholar]
  33. CollinsG.S. ReitsmaJ.B. AltmanD.G. MoonsK.G.M. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement.Ann. Intern. Med.20151621556310.7326/M14‑069725560714
     [Google Scholar]
  34. MoonsK.G.M. AltmanD.G. ReitsmaJ.B. IoannidisJ.P.A. MacaskillP. SteyerbergE.W. VickersA.J. RansohoffD.F. CollinsG.S. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): Explanation and elaboration.Ann. Intern. Med.20151621W1W7310.7326/M14‑069825560730
     [Google Scholar]
  35. TaoL.Y. LiuJ. ZengL. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis.Zhonghua Yi Xue Za Zhi201898443556356010.3760/cma.j.issn.0376‑2491.2018.44.00230486570
     [Google Scholar]
  36. JensenE.A. LaughonM.M. DeMauroS.B. CottenC.M. DoB. CarloW.A. WatterbergK.L. Contributions of the NICHD neonatal research network to the diagnosis, prevention, and treatment of bronchopulmonary dysplasia.Semin. Perinatol.202246715163810.1016/j.semperi.2022.15163836085059
     [Google Scholar]
  37. KinkorM. SchneiderJ. SulthanaF. Noel-MacdonnellJ. CunaA. A comparison of the 2022 versus 2011 national institute of child health and human development web-based risk estimator for bronchopulmonary dysplasia.Journal of Pediatrics: Clinical Practice20241420012910.1016/j.jpedcp.2024.20012939629201
     [Google Scholar]
  38. KatzT.A. van KaamA.H. ZuithoffN.P.A. MugieS.M. BeugerS. BlokG.J. van KempenA.A.M.W. van LaerhovenH. LuttermanC.A.M. RijpertM. SchieringI.A. RanN.C. VisserF. van StraatenE. Aarnoudse-MoensC.S.H. van Wassenaer-LeemhuisA.G. OnlandW. Association between bronchopulmonary dysplasia severity and its risk factors and long-term outcomes in three definitions: A historical cohort study.Arch. Dis. Child. Fetal Neonatal Ed.20251101515610.1136/archdischild‑2024‑32693138897634
     [Google Scholar]
  39. LiJ. XuH. Comparisons of two definitions of bronchopulmonary dysplasia for the premature infants.Pediatr. Pulmonol.202257121722310.1002/ppul.2573934687285
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056421036250806053617
Loading
Clinical and Imaging Data-based Machine Learning for Early Diagnosis of Bronchopulmonary Dysplasia: A Meta-analysis
Curr. Med. Imaging 21, E15734056421036 (2025); https://doi.org/10.2174/0115734056421036250806053617
/content/journals/cmir/10.2174/0115734056421036250806053617
/content/journals/cmir/10.2174/0115734056421036250806053617
Loading

Data & Media loading...

Supplements

Supplementary material is available on the publisher's website along with the published article.

file format download Download

  • Article Type:     Research Article
Keyword(s): Bronchopulmonary dysplasia; Clinical and imaging data; ELBW; Machine learning; Meta-analysis; Validation strategies; VLBW

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test