Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2162
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-22T10:42:29.764744Z
status: published
lens: g_space
sector: health
headline: The use of artificial intelligence in patent ductus arteriosus diagnosis and treatment: a systematic scoping review
dek: Background. Background and objectives: Patent ductus arteriosus (PDA) is a common congenital cardiac condition, especially in premature infants, and is associated with significant morbidity and mortality. Artificial intelligence (AI) has emerged as a promising tool to aid clinicians in diagnosing PDA and guiding treatment decisions amidst this uncertainty. Methods. A literature search (up to December 2025) was conducted in PubMed, Scopus, and Web of Science for peer-reviewed studies on AI (including machine lear…
gain_title: Imaging-based deep learning models for patent ductus arteriosus diagnosis and outcome prediction in preterm neonates often reached an AUC above 0.80, outperforming approaches using tabular data.
problem_title: (none)
trace_subject: (none)
gain_reading: Imaging-based deep learning models for patent ductus arteriosus diagnosis and outcome prediction in preterm neonates often reached an AUC above 0.80, outperforming approaches using tabular data.
gain_evidence: Imaging-based deep learning models generally outperformed tabular data approaches (with area under the curve often >0.80)
problem_reading: (none)
problem_evidence: (none)
quick_read: A systematic scoping review searched PubMed, Scopus, and Web of Science through December 2025 and identified seventeen studies applying AI to patent ductus arteriosus, mostly in preterm neonates. The tools focused on diagnosing the condition and predicting outcomes from clinical and echocardiographic data.

The findings matter because PDA is a common congenital heart condition tied to serious illness and death in premature infants, so earlier and more consistent decisions could help. Still, the authors' hopes for reduced variability and better outcomes are projections, and the reviewed evidence lacked external validation and data transparency.
limitation: Overall study quality was moderate, with limited external validation and data transparency, so the reported performance may not generalize and clinical benefits remain unproven.
tag: Evidence-backed gain
key_points: Seventeen studies met inclusion criteria, predominantly involving preterm neonates. | AI work mainly targeted PDA diagnosis and outcome prediction using clinical and echocardiographic data. | Imaging-based deep learning generally beat tabular-data models, with AUC often above 0.80. | Overall study quality was rated moderate. | Authors suggest PDA could serve as a model for broader medical AI use.
rundown: The review covered peer-reviewed studies of machine learning, deep learning, computer vision, and predictive analytics applied to PDA, searching three major databases up to December 2025.

Results showed that models using echocardiographic images tended to perform better than those built on tabular clinical data, though the review reports performance only in general terms.

The conclusions that AI could enable earlier detection, more consistent decisions, and individualized treatment planning are stated as potential benefits rather than measured clinical outcomes.
sources:
- peer_reviewed | The Turkish Journal of Pediatrics | https://doi.org/10.24953/turkjpediatr.2026.8122 | 2026-10-21
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

b36447d363b45fada35a52e20f6b19c20f8a05cb7ed9019040666722ff9da7a3

previous

0000000000000000000000000000000000000000000000000000000000000000