Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables.
artificial intelligence
bronchopulmonary dysplasia
machine learning
preterm infant
Journal
Pediatric pulmonology
ISSN: 1099-0496
Titre abrégé: Pediatr Pulmonol
Pays: United States
ID NLM: 8510590
Informations de publication
Date de publication:
16 Aug 2024
16 Aug 2024
Historique:
revised:
01
08
2024
received:
12
05
2024
accepted:
05
08
2024
medline:
16
8
2024
pubmed:
16
8
2024
entrez:
16
8
2024
Statut:
aheadofprint
Résumé
Prematurity is the strongest predictor of bronchopulmonary dysplasia (BPD). Most previous studies investigated additional risk factors by conventional statistics, while the few studies applying artificial intelligence, and specifically machine learning (ML), for this purpose were mainly targeted to the predictive ability of specific interventions. This study aimed to apply ML to identify, among routinely collected data, variables predictive of BPD, and to compare these variables with those identified through conventional statistics. Very preterm infants were recruited; antenatal, perinatal, and postnatal clinical data were collected. A BPD prediction model was built using conventional statistics, and nine supervised ML algorithms were applied for the same purpose: the results of the best-performing model were described and compared with those of conventional statistics. Both conventional statistics and ML identified the degree of immaturity (low gestational age and/or birth weight), need for mechanical ventilation, and absent or reversed end diastolic flow (AREDF) in the umbilical arteries as risk factors for BPD. Each of the two approaches also identified additional potentially predictive clinical variables. ML algorithms might be useful to integrate conventional statistics in identifying novel risk factors, in addition to prematurity, for the development of BPD in very preterm infants. Specifically, the identification of AREDF status as an independent risk factor for BPD by both conventional statistics and ML highlights the opportunity to include detailed antenatal information in clinical predictive models for neonatal diseases.
Sections du résumé
BACKGROUND
BACKGROUND
Prematurity is the strongest predictor of bronchopulmonary dysplasia (BPD). Most previous studies investigated additional risk factors by conventional statistics, while the few studies applying artificial intelligence, and specifically machine learning (ML), for this purpose were mainly targeted to the predictive ability of specific interventions. This study aimed to apply ML to identify, among routinely collected data, variables predictive of BPD, and to compare these variables with those identified through conventional statistics.
METHODS
METHODS
Very preterm infants were recruited; antenatal, perinatal, and postnatal clinical data were collected. A BPD prediction model was built using conventional statistics, and nine supervised ML algorithms were applied for the same purpose: the results of the best-performing model were described and compared with those of conventional statistics.
RESULTS
RESULTS
Both conventional statistics and ML identified the degree of immaturity (low gestational age and/or birth weight), need for mechanical ventilation, and absent or reversed end diastolic flow (AREDF) in the umbilical arteries as risk factors for BPD. Each of the two approaches also identified additional potentially predictive clinical variables.
CONCLUSION
CONCLUSIONS
ML algorithms might be useful to integrate conventional statistics in identifying novel risk factors, in addition to prematurity, for the development of BPD in very preterm infants. Specifically, the identification of AREDF status as an independent risk factor for BPD by both conventional statistics and ML highlights the opportunity to include detailed antenatal information in clinical predictive models for neonatal diseases.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : None
Informations de copyright
© 2024 The Author(s). Pediatric Pulmonology published by Wiley Periodicals LLC.
Références
Duijts L, van Meel ER, Moschino L, et al. European respiratory society guideline on long‐term management of children with bronchopulmonary dysplasia. Eur Respir J. 2020;55:1900788.
Thébaud B, Goss KN, Laughon M, et al. Bronchopulmonary dysplasia. Nat Rev Dis Primers. 2019;5(1):78.
Abiramalatha T, Ramaswamy VV, Bandyopadhyay T, et al. Interventions to prevent bronchopulmonary dysplasia in preterm neonates: an umbrella review of systematic reviews and meta‐analyses. JAMA Pediatrics. 2022;176(5):502‐516.
Laughon MM, Langer JC, Bose CL, et al. Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants. Am J Respir Crit Care Med. 2011;183(12):1715‐1722.
Greenberg RG, McDonald SA, Laughon MM, et al. Online clinical tool to estimate risk of bronchopulmonary dysplasia in extremely preterm infants. Arch Disease Childhood Fetal Neonat Ed. 2022;107(6):638‐643.
Jensen EA, Dysart K, Gantz MG, et al. The diagnosis of bronchopulmonary dysplasia in very preterm infants an evidence‐based approach. Am J Respir Crit Care Med. 2019;200(6):751‐759.
Patel M, Sandhu J, Chou FS. Developing a machine learning‐based tool to extend the usability of the NICHD BPD outcome estimator to the Asian population. PLoS One. 2022;17:e0272709.
McAdams RM, Kaur R, Sun Y, Bindra H, Cho SJ, Singh H. Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review. J Perinatol. 2022;42(12):1561‐1575.
Chioma R, Sbordone A, Patti ML, Perri A, Vento G, Nobile S. Applications of artificial intelligence in neonatology. Appl Sci. 2023;13:3211.
Dai D, Chen H, Dong X, et al. Bronchopulmonary dysplasia predicted by developing a machine learning model of genetic and clinical information. Front Genet. 2021;12:1‐10.
Verder H, Heiring C, Ramanathan R, et al. Bronchopulmonary dysplasia predicted at birth by artificial intelligence. Acta Paediatr. 2021;110(2):503‐509.
Xing W, He W, Li X, et al. Early severity prediction of BPD for premature infants from chest X‐ray images using deep learning: A study at the 28th day of oxygen inhalation. Comput Methods Programs Biomed. 2022;221:106869.
Leigh RM, Pham A, Rao SS, et al. Machine learning for prediction of bronchopulmonary dysplasia‐free survival among very preterm infants. BMC Pediatr. 2022;22(1):542.
Wu TY, Lin WT, Chen YJ, Chang YS, Lin CH, Lin YJ. Machine learning to predict late respiratory support in preterm infants: a retrospective cohort study. Sci Rep. 2023;13(1):2839.
Kostekci YE, Bakırarar B, Okulu E, Erdeve O, Atasay B, Arsan S. An early prediction model for estimating bronchopulmonary dysplasia in preterm infants. Neonatology. 2023;120:709‐717.
Beam K, Sharma P, Levy P, Beam AL. Artificial intelligence in the neonatal intensive care unit: the time is now. J Perinatol. 2024;44(1):131‐135.
Bertino E, Di Nicola P, Varalda A, Occhi L, Giuliani F, Coscia A. Neonatal growth charts. J Matern Fetal Neonatal Med. 2012;25(suppl 1):67‐69.
Higgins RD, Jobe AH, Koso‐Thomas M, et al. Bronchopulmonary dysplasia: executive summary of a workshop. J Pediatr. 2018;197:300‐308.
Sweet DG, Carnielli VP, Greisen G, et al. European consensus guidelines on the management of respiratory distress syndrome: 2022 update. Neonatology. 2023;120(1):3‐23.
Inder TE, Perlman JM, Volpe JJ. Preterm IVH/posthemorrhagic hydrocephalus. In Volpe's Neurology of the Newborn. 6th ed. Elsevier; 2018;637‐698.
Chiang MF, Quinn GE, Fielder AR, et al. International classification of retinopathy of prematurity, third edition. Ophthalmology. 2021;128(10):e51‐e68.
Walsh MC, Kliegman RM. Necrotizing enterocolitis: treatment based on staging criteria. Pediatr Clin North Am. 1986;33(1):179‐201.
The Global Health Network. INTERGROWTH 21st. Standards and Tools. https://intergrowth21.com/intergrowth-21st-applications-calculators
Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit‐learn: machine learning in python. J Mach Learn Res. 2011;12:2825‐2830.
Raschka S, Mirjalili V. Python Machine Learning, 3rd Ed. Packt Publishing; 2019.
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic Minority Over‐sampling Technique. 2002.
Topol EJ. High‐performance medicine: the convergence of human and artificial intelligence. Nature Med. 2019;25(1):44‐56.
Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nature Med. 2022;28(1):31‐38.
Han R, Acosta JN, Shakeri Z, Ioannidis JPA, Topol EJ, Rajpurkar P. Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review. Lancet Digital Health. 2024;6(5):e367‐e373.
Lin C‐S, Liu W‐T, Tsai D‐J, et al. AI‐enabled electrocardiography alert intervention and all‐cause mortality: a pragmatic randomized clinical trial. Nature Med. 2024;30:1461‐1470.
Piccialli F, Somma VD, Giampaolo F, Cuomo S, Fortino G. A survey on deep learning in medicine: why, how and when? Information Fusion. 2021;66:111‐137.
Shah M, Jain D, Prasath S, Dufendach K. Artificial intelligence in bronchopulmonary dysplasia‐current research and unexplored frontiers. Pediatr Res. 2023;93(2):287‐290.
Morsing E, Brodszki J, Thuring A, Maršál K. Infant outcome after active management of early‐onset fetal growth restriction with absent or reversed umbilical artery blood flow. Ultrasound Obstet Gynecol. 2021;57(6):931‐941.
Lees CC, Stampalija T, Baschat AA, et al. ISUOG practice guidelines: diagnosis and management of small‐for‐gestational‐age fetus and fetal growth restriction. Ultrasound Obstet Gynecol. 2020;56(2):298‐312.
Della Gatta AN, Aceti A, Spinedi SF, et al. Neurodevelopmental outcomes of very preterm infants born following early foetal growth restriction with absent end‐diastolic umbilical flow. Eur J Pediatr. 2023;182(10):4467‐4476.
Kernbach JM, Staartjes VE. Foundations of machine learning‐based clinical prediction modeling: part II—Generalization and overfitting. Acta Neurochir Suppl. 2022;134:15‐21.
Kwok TC, Henry C, Saffaran S, et al. Application and potential of artificial intelligence in neonatal Medicine. Semin Fetal Neonat Med. 2022;27(5):101346.
Shepherd EG, Clouse BJ, Hasenstab KA, et al. Infant pulmonary function testing and phenotypes in severe bronchopulmonary dysplasia. Pediatrics. 2018;141(5):e20173350.
Sullivan BA, Kausch SL, Fairchild KD. Artificial and human intelligence for early identification of neonatal sepsis. Pediatr Res. 2023;93(2):350‐356.
Ramaswamy VV, de Almeida MF, Dawson JA, et al. Maintaining normal temperature immediately after birth in late preterm and term infants: a systematic review and meta‐analysis. Resuscitation. 2022;180:81‐98.
Mohamed SOO, Ahmed SMI, Khidir RJY, et al. Outcomes of neonatal hypothermia among very low birth weight infants: a meta‐analysis. Matern Health Neonatol Perinatol. 2021;7(1):14.