Related Experiment Video
Updated: Oct 13, 2025
A Rat Model of Mild Intrauterine Hypoperfusion with Microcoil Stenosis
Published on: January 7, 2018
Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low
Jae Yoon Na1, Dongkyun Kim2, Amy M Kwon3
1Department of Pediatrics, Hanyang University College of Medicine, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea.
Insights
Artificial intelligence (AI) analysis accurately identified risk factors for symptomatic patent ductus arteriosus (sPDA) in very low birth weight infants. AI, particularly ensemble methods, outperformed traditional analysis in predicting sPDA.
Area of Science:
- Neonatology
- Medical Informatics
- Pediatric Cardiology
Background:
- Patent ductus arteriosus (PDA) is common in preterm infants, associated with high mortality and comorbidities.
- Current risk factor studies for PDA often use small sample sizes, limiting generalizability.
- Therapeutic strategies for PDA vary, highlighting the need for better risk identification.
Purpose of the Study:
- To compare artificial intelligence (AI) analysis with conventional methods for identifying symptomatic PDA (sPDA) risk factors.
- To evaluate the performance of AI algorithms in predicting sPDA in very low birth weight (VLBW) infants.
- To leverage a large nationwide dataset for robust risk factor analysis.
Main Methods:
- Nationwide cohort study of 8369 very low birth weight (VLBW) infants.
- Categorization into symptomatic PDA (sPDA) and non-symptomatic PDA (nPDA) groups.
- Analysis of 47 perinatal risk factors using multiple logistic regression and five AI algorithms (including ensemble methods).
Main Results:
- AI analysis demonstrated higher accuracy and better performance in identifying sPDA risk factors compared to conventional methods.
- Ensemble AI methods exhibited the best performance in predicting sPDA.
- The study successfully combined a large registry database with AI for improved prediction.
Conclusions:
- AI techniques, especially ensemble methods, offer superior performance in identifying risk factors for sPDA in VLBW infants.
- Combining large-scale data with AI enhances the accuracy of PDA prediction.
- This approach can inform clinical decision-making and improve outcomes for VLBW infants with PDA.
Abstract:
Despite the many comorbidities and high mortality rate in preterm infants with patent ductus arteriosus (PDA), therapeutic strategies vary depending on the clinical setting, and most studies of the related risk factors are based on small sample populations. We aimed to compare the performance of artificial intelligence (AI) analysis with that of conventional analysis to identify risk factors associated with symptomatic PDA (sPDA) in very low birth weight infants. This nationwide cohort study included 8369 very low birth weight (VLBW) infants. The participants were divided into an sPDA group and an asymptomatic PDA or spontaneously close PDA (nPDA) group. The sPDA group was further divided into treated and untreated subgroups. A total of 47 perinatal risk factors were collected and analyzed. Multiple logistic regression was used as a standard analytic tool, and five AI algorithms were used to identify the factors associated with sPDA. Combining a large database of risk factors from nationwide registries and AI techniques achieved higher accuracy and better performance of the PDA prediction tasks, and the ensemble methods showed the best performances.
