Bronchopulmonary dysplasia predicted at birth by artificial intelligence
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Bronchopulmonary dysplasia predicted at birth by artificial intelligence. / Verder, Henrik; Heiring, Christian; Ramanathan, Rangasamy; Scoutaris, Nikolaos; Verder, Povl; Jessen, Torben E.; Höskuldsson, Agnar; Bender, Lars; Dahl, Marianne; Eschen, Christian; Fenger-Grøn, Jesper; Reinholdt, Jes; Smedegaard, Heidi; Schousboe, Peter.
In: Acta Paediatrica, International Journal of Paediatrics, Vol. 110, No. 2, 2021, p. 503-509.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Bronchopulmonary dysplasia predicted at birth by artificial intelligence
AU - Verder, Henrik
AU - Heiring, Christian
AU - Ramanathan, Rangasamy
AU - Scoutaris, Nikolaos
AU - Verder, Povl
AU - Jessen, Torben E.
AU - Höskuldsson, Agnar
AU - Bender, Lars
AU - Dahl, Marianne
AU - Eschen, Christian
AU - Fenger-Grøn, Jesper
AU - Reinholdt, Jes
AU - Smedegaard, Heidi
AU - Schousboe, Peter
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - bronchopulmonary dysplasia
KW - chorioamnionitis
KW - respiratory distress syndrome
KW - spectroscopy
KW - surfactant
U2 - 10.1111/apa.15438
DO - 10.1111/apa.15438
M3 - Journal article
C2 - 32569404
AN - SCOPUS:85088588965
VL - 110
SP - 503
EP - 509
JO - Acta Paediatrica
JF - Acta Paediatrica
SN - 0803-5253
IS - 2
ER -
ID: 258402613