Related Experiment Video
Updated: Jul 24, 2025
Surfactant Depletion Combined with Injurious Ventilation Results in a Reproducible Model of the Acute Respiratory Distress Syndrome ARDS
Published on: April 7, 2021
Artificial Intelligence-Driven Respiratory Distress Syndrome Prediction for Very Low Birth Weight Infants: Korean
Woocheol Jang1, Yong Sung Choi2, Ji Yoo Kim2
1Biomedical Engineering, Kyung Hee University, Yongin-si, Republic of Korea.
Insights
An AI model accurately predicts Respiratory Distress Syndrome (RDS) in premature infants, aiding in targeted surfactant treatment for very low birth weight newborns and preventing unnecessary interventions.
Area of Science:
- Neonatal Medicine
- Artificial Intelligence
- Predictive Analytics
Background:
- Respiratory Distress Syndrome (RDS) affects premature infants due to underdeveloped lungs and surfactant deficiency.
- The incidence of RDS correlates with the degree of prematurity.
- Current practice often involves preemptive artificial pulmonary surfactant treatment for premature infants, regardless of individual RDS likelihood.
Purpose of the Study:
- To develop an artificial intelligence (AI) model for predicting RDS in premature infants.
- To reduce unnecessary surfactant treatments by accurately identifying infants at high risk for RDS.
- To improve neonatal resuscitation preparedness for very low birth weight infants.
Main Methods:
- Utilized data from 13,087 very low birth weight infants across 76 hospitals in the Korean Neonatal Network.
- Incorporated diverse data points including infant characteristics, maternal history, pregnancy/birth details, family history, resuscitation procedures, and initial test results (blood gas, Apgar score).
- Compared 7 machine learning models, proposing a 5-layer deep neural network and an ensemble approach with 5-fold cross-validation for enhanced prediction.
Main Results:
- The ensemble 5-layer deep neural network, using the top 20 features, achieved high performance metrics: 83.03% sensitivity, 87.50% specificity, 84.07% accuracy, 85.26% balanced accuracy, and an AUC of 0.9187.
- A public web application was developed for accessible prediction of RDS in premature infants based on the validated AI model.
- The model demonstrates significant potential for clinical decision support in neonatal care.
Conclusions:
- The developed AI model offers a valuable tool for predicting RDS likelihood in premature infants, especially those of very low birth weight.
- This predictive capability can guide decisions on surfactant administration, optimizing resource allocation and patient care.
- The AI model supports enhanced preparation for neonatal resuscitation, particularly for high-risk deliveries.
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.
More Related Videos
06:15Protocol and Guidelines for Point-of-Care Lung Ultrasound in Diagnosing Neonatal Pulmonary Diseases Based on International Expert Consensus
Published on: March 6, 2019
04:56Laryngeal Mask Airway LMA Placement in a Neonatal Patient Simulator Using a Non-Inflatable Supraglottic Airway SGA
Published on: July 14, 2023
Related Concept Videos
01:23Acute Respiratory Failure-IV
01:30Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
01:19Respiratory Assessment: Purpose and Indications
Objectives and Importance:
The primary goal of respiratory assessment is to evaluate patients at early risk of clinical deterioration. Since respiratory distress often precedes other signs of declining health, breathing patterns and sounds become a...
01:29Acute Respiratory Failure-V
Ensure that patients are monitored continuously for their response to therapy, including changes in...
01:20Assessment of Ventilation I: Respiratory Rate
A Ventilation assessment is critical for monitoring a patient's health status. Respiration, one of the most accessible vital signs, provides insights into the function of numerous body systems and can indicate serious health issues, such as brainstem injuries from head trauma.
Critical Guidelines for Assessing Ventilation:
01:23Assessment of Respiration
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...