Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital

Bronchopulmonary dysplasia predicted at birth by artificial intelligence

Research output: Contribution to journalJournal articleResearchpeer-review


  1. Danish registry study showed increased incidence of paediatric haemangiomas and congenital vascular malformations from 1996 to 2015

    Research output: Contribution to journalComment/debateResearchpeer-review

  2. No long-term effect of oral stimulation on the intra-oral vacuum in healthy premature infants

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Randomised oral stimulation and exclusive breastfeeding duration in healthy premature infants

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Paediatric hepatitis B and hepatitis C virus infections: an observational study of a Danish cohort

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

AIM: To develop a fast bedside test for prediction and early targeted intervention of bronchopulmonary dysplasia (BPD) to improve the outcome.

METHODS: In a multicentre study of preterm infants with gestational age 24-31 weeks, clinical data present at birth were combined with spectral data of gastric aspirate samples taken at birth and analysed using artificial intelligence. The study was designed to develop an algorithm to predict development of BPD. The BPD definition used was the consensus definition of the US National Institutes of Health: Requirement of supplemental oxygen for at least 28 days with subsequent assessment at 36 weeks postmenstrual age.

RESULTS: Twenty-six (43%) of the 61 included infants developed BPD. Spectral data analysis of the gastric aspirates identified the most important wave numbers for classification and surfactant treatment, and birth weight and gestational age were the most important predictive clinical data. By combining these data, the resulting algorithm for early diagnosis of BPD had a sensitivity of 88% and a specificity of 91%.

CONCLUSION: A point-of-care test to predict subsequent development of BPD at birth has been developed using a new software algorithm allowing early targeted intervention of BPD which could improve the outcome.

Original languageEnglish
JournalActa paediatrica
Pages (from-to)1-7
Number of pages7
Publication statusPublished - 2020

Bibliographical note

© 2020 The Authors. Acta Paediatrica published by John Wiley & Sons Ltd on behalf of Foundation Acta Paediatrica.

    Research areas

  • Bronchopulmonary dysplasia, chorioamnionitis, respiratory distress syndrome, spectroscopy, surfactant

ID: 60131547