Artificial Intelligence–Driven Respiratory Distress Syndrome Prediction for Very Low Birth Weight Infants: Korean Multicenter Prospective Cohort Study

Jang, Woocheol; Choi, Yong Sung; Kim, Jiyoo; Yon, Dong Keon; Lee, Young Joo; Chung, Sung-Hoon; Kim, Chaeyoung; Lee, Jin-Seok

doi:10.2196/47612

Cited by 5 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be explained by the fact that there are several reasons for endotracheal intubation of preterm infants immediately after birth, including resuscitation and the provision of invasive mechanical ventilation [2], as well as surfactant administration [6]. Interestingly, in an artificial intelligence model developed to predict RDS in very low birth weight infants, tracheal intubation at the initial resuscitation ranked last with respect to importance among the various maternal and perinatal-neonatal features evaluated [34]. Still, surfactant is currently recommended in intubated preterm infants, whether intubation was deemed necessary as part of initial stabilization or at any time to promote early extubation [6,33].…”

Section: Clinical Parameters To Prognosticate Surfactant Replacement ...mentioning

confidence: 99%

Gastric Fluid Metabolomics Predicting the Need for Surfactant Replacement Therapy in Very Preterm Infants Results of a Case–Control Study

Besiri,

Begou,

Lallas

et al. 2024

Metabolites

View full text Add to dashboard Cite

Respiratory distress syndrome (RDS) is a major morbidity of prematurity. In this case–control study, we prospectively evaluated whether untargeted metabolomic analysis (gas chromatography–mass spectrometry) of the gastric fluid could predict the need for surfactant in very preterm neonates. 43 infants with RDS necessitating surfactant (cases) were compared with 30 infants who were not treated with surfactant (controls). Perinatal–neonatal characteristics were recorded. Significant differences in gastric fluid metabolites (L-proline, L-glycine, L-threonine, acetyl-L-serine) were observed between groups, but none could solely predict surfactant administration with high accuracy. Univariate analysis revealed significant predictors of surfactant administration involving gastric fluid metabolites (L-glycine, acetyl-L-serine) and clinical parameters (gestational age, Apgar scores, intubation in the delivery room). Multivariable models were constructed for significant clinical variables as well as for the combination of clinical variables and gastric fluid metabolites. The AUC value of the first model was 0.69 (95% CI 0.57–0.81) and of the second, 0.76 (95% CI 0.64–0.86), in which acetyl-L-serine and intubation in the delivery room were found to be significant predictors of surfactant therapy. This investigation adds to the current knowledge of biomarkers in preterm neonates with RDS, but further research is required to assess the predictive value of gastric fluid metabolomics in this field.

show abstract

Section: Clinical Parameters To Prognosticate Surfactant Replacement ...mentioning

confidence: 99%

Gastric Fluid Metabolomics Predicting the Need for Surfactant Replacement Therapy in Very Preterm Infants Results of a Case–Control Study

Besiri,

Begou,

Lallas

et al. 2024

Metabolites

View full text Add to dashboard Cite

show abstract

NeoCLIP: A Self-Supervised Foundation Model for the Interpretation of Neonatal Radiographs

Huang,

Sharma,

Palepu

et al. 2024

Preprint

View full text Add to dashboard Cite

ImportanceArtificial intelligence (AI) based on deep learning has shown promise in adult and pediatric populations in the interpretation of medical imaging to make important diagnostic and management recommendations. However, there has been little work developing new AI methods for neonatal populations.ObjectiveTo develop a novel, deep contrastive learning model to predict a comprehensive set of pathologies from radiographs relevant to neonatal intensive care.Design, Setting, and ParticipantsWe identified a retrospective cohort of infants who obtained a radiograph while admitted to a large neonatal intensive care unit in Boston, MA from January 2008 to December 2023. After collecting radiographs with corresponding reports and relevant demographics for all subjects, we randomized the cohort into three sets: training (80%), validation (10%), and test (10%).InterventionsWe developed a deep learning model, NeoCLIP, to identify 15 unique pathologies and 5 medical devices relevant to neonatal intensive care on plain film radiographs. The pathologies were automatically extracted from radiology reports using a custom pipeline based on large language models.Main Outcomes and MeasuresWe compared the performance of our model, as defined by AUROC, against various baseline methods.ResultsWe identified 4,629 infants which were randomized into the training (3,731 infants), validation (419 infants), and test (479 infants) sets. In total, we collected 20,154 radiographs with a corresponding 15,795 reports. The AUROC of our model was greater than all baseline methods for every radiographic finding other than portal venous gas. The addition of demographics improved the AUROC of our model for all findings, but the difference was not statistically significant.Conclusions and RelevanceNeoCLIP successfully identified a broad set of pathologies and medical devices on neonatal radiographs, outperforming similar models developed for adult populations. This represents the first such application of advanced AI methodologies to interpret neonatal radiographs.

show abstract

Artificial Intelligence–Driven Respiratory Distress Syndrome Prediction for Very Low Birth Weight Infants: Korean Multicenter Prospective Cohort Study

Jang¹,

Choi²,

Kim³

et al. 2023

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

Background Respiratory distress syndrome (RDS) is a disease that commonly affects premature infants whose lungs are not fully developed. RDS results from a lack of surfactant in the lungs. The more premature the infant is, the greater is the likelihood of having RDS. However, even though not all premature infants have RDS, preemptive treatment with artificial pulmonary surfactant is administered in most cases. Objective We aimed to develop an artificial intelligence model to predict RDS in premature infants to avoid unnecessary treatment. Methods In this study, 13,087 very low birth weight infants who were newborns weighing less than 1500 grams were assessed in 76 hospitals of the Korean Neonatal Network. To predict RDS in very low birth weight infants, we used basic infant information, maternity history, pregnancy/birth process, family history, resuscitation procedure, and test results at birth such as blood gas analysis and Apgar score. The prediction performances of 7 different machine learning models were compared, and a 5-layer deep neural network was proposed in order to enhance the prediction performance from the selected features. An ensemble approach combining multiple models from the 5-fold cross-validation was subsequently developed. Results Our proposed ensemble 5-layer deep neural network consisting of the top 20 features provided high sensitivity (83.03%), specificity (87.50%), accuracy (84.07%), balanced accuracy (85.26%), and area under the curve (0.9187). Based on the model that we developed, a public web application that enables easy access for the prediction of RDS in premature infants was deployed. Conclusions Our artificial intelligence model may be useful for preparations for neonatal resuscitation, particularly in cases involving the delivery of very low birth weight infants, as it can aid in predicting the likelihood of RDS and inform decisions regarding the administration of surfactant.

show abstract

Artificial Intelligence–Driven Respiratory Distress Syndrome Prediction for Very Low Birth Weight Infants: Korean Multicenter Prospective Cohort Study

Cited by 5 publications

References 48 publications

Gastric Fluid Metabolomics Predicting the Need for Surfactant Replacement Therapy in Very Preterm Infants Results of a Case–Control Study

Gastric Fluid Metabolomics Predicting the Need for Surfactant Replacement Therapy in Very Preterm Infants Results of a Case–Control Study

NeoCLIP: A Self-Supervised Foundation Model for the Interpretation of Neonatal Radiographs

Artificial Intelligence–Driven Respiratory Distress Syndrome Prediction for Very Low Birth Weight Infants: Korean Multicenter Prospective Cohort Study

Contact Info

Product

Resources

About