The effect of patent ductus arteriosus on pre-ductal and post-ductal perfusion index in preterm neonates

Artificial Intelligence-Based Diagnostic Support System for Patent Ductus Arteriosus in Premature Infants

Background: Patent ductus arteriosus (PDA) is a prevalent congenital heart defect in premature infants, associated with significant morbidity and mortality. Accurate and timely diagnosis of PDA is crucial, given the vulnerability of this population. Methods: We introduce an artificial intelligence (AI)-based PDA diagnostic support system designed to assist medical professionals in diagnosing PDA in premature infants. This study utilized electronic health record (EHR) data from 409 premature infants spanning a decade at Severance Children's Hospital. Our system integrates a data viewer, data analyzer, and AI-based diagnosis supporter, facilitating comprehensive data presentation, analysis, and early symptom detection. Results: The system's performance was evaluated through diagnostic tests involving medical professionals. This early detection model achieved an accuracy rate of up to 84%, enabling detection up to 3.3 days in advance. In diagnostic tests, medical professionals using the system with the AI-based diagnosis supporter outperformed those using the system without the supporter. Conclusions: Our AI-based PDA diagnostic support system offers a comprehensive solution for medical professionals to accurately diagnose PDA in a timely manner in premature infants. The collaborative integration of medical expertise and technological innovation demonstrated in this study underscores the potential of AI-driven tools in advancing neonatal diagnosis and care.

The perfusion index histograms predict patent ductus arteriosus requiring treatment in preterm infants

The impact of patent ductus arteriosus (PDA) on vital sign trends represented as histograms, and perfusion index in particular, is unknown. This study aimed to split continuously obtained PI and other vital signs before, during, and after medical treatment of PDA, into histogram bins, and determine the utility of PI and other vital sign histograms in the early prediction of hemodynamically significant PDA (hsPDA). In 34 infants at a mean gestational age of 26 ± 2.1 weeks, we prospectively collected vital signs for three different periods, 24 h before starting treatment of PDA, during PDA treatment, and 24 h after completion of the course of treatment, and confirmed PDA closure by echo. Histograms with three comparable periods were obtained from preterm infants who did not require treatment for PDA and analyzed for comparison. The duration of time spent in each histogram bin was determined for each time epoch. Episodes of low PI < 0.4 and high PI > 2 were significantly longer in duration in infants with PDA before treatment compared to those in infants with PDA during and after treatment. The arterial oxygen saturation (SpO₂) < 80% was also longer in duration in infants with PDA before compared to that in infants with PDA during and after treatment. Low PI < 0.4 correlated with most echocardiography indices of hsPDA.Conclusion: We conclude that a patent ductus arteriosus requiring treatment in preterm infants ≤ 29 weeks GA was associated with significant fluctuations between a low PI < 0.4 alternating with a high PI > 2, reflecting the dynamic nature of hsPDA shunt volume. PI variability may be an early marker of hsPDA. What is Known: • The perfusion index is a continuous underutilized parameter provided by pulse oximetry to assess the peripheral perfusion. • The perfusion index helps predict conditions with hemodynamic instability. What is New: • The perfusion index assessed as daily histogram trends can predict patent ductus arteriosus requiring treatment.