Related Experiment Videos
Machine learning for development of an expert system to predict premature birth
L K Woolery1, J Grzymala-Busse
1School of Nursing, University of Missouri, Columbia 65211, USA.
Insights
Predicting preterm birth is crucial for infant health. Artificial intelligence, using the LERS1 machine learning program, significantly improved prediction accuracy compared to traditional methods.
Area of Science:
- Medical research
- Artificial Intelligence in Healthcare
Background:
- Preterm birth (before 37 weeks gestation) affects 8-12% of US newborns.
- High costs of neonatal care for premature infants necessitate better risk assessment.
Purpose of the Study:
- To develop and evaluate an AI-driven system for accurate preterm birth prediction.
- To improve upon existing manual prediction techniques.
Main Methods:
- Utilized a machine learning program (LERS1) with a large dataset (18,890 participants, 214 variables).
- Incorporated statistical analysis, expert verification, and a prototype expert system.
Main Results:
- Achieved prediction accuracy ranging from 53% to 90%.
- Demonstrated a substantial improvement over manual prediction techniques, which yielded 17-38% accuracy.
Conclusions:
- AI, specifically the LERS1 system, offers a highly accurate method for predicting preterm birth.
- This advancement has the potential to optimize prenatal care and resource allocation.
Abstract:
Normal pregnancy involves a term of 40 weeks gestation. Problems associated with low birthweight and prematurity continue to plague childbearing families and the healthcare system because 8-12% of all newborns in the United States deliver prior to 37 weeks gestation. The high cost of caring for premature babies increasingly treats all pregnant women as if they are 'high risk' for preterm birth. Artificial intelligence techniques used a machine learning program named LERS1 with large datasets (n = 18,890; 214 variables), statistical analysis, expert verification techniques, and a prototype expert system2 that yielded improved accuracy (53-90%) over existing manual techniques (17-38%) for predicting preterm birth.