# Neonatal supraventricular tachycardia: current diagnostic approaches and emerging technologies

## TL;DR

This review discusses current and emerging diagnostic methods for neonatal supraventricular tachycardia, focusing on the potential of new technologies like AI and wearable sensors.

## Contribution

The paper introduces a framework for integrating emerging technologies into neonatal SVT diagnosis while emphasizing the need for neonate-specific validation.

## Key findings

- Traditional diagnostic methods like ECG face challenges in neonates due to signal quality and intermittent capture.
- AI models show over 90% accuracy in broader pediatric populations but require neonatal-specific validation.
- Emerging technologies like deep learning and wearable sensors offer potential improvements in diagnostic timing and accuracy.

## Abstract

Neonatal supraventricular tachycardia (SVT) represents the most common pathological tachyarrhythmia in the neonatal period, with an incidence of 1:250–1000 live births. This review synthesizes current diagnostic methodologies and explores the potential of emerging technological innovations. Traditional modalities, including 12-lead electrocardiography (ECG) and ambulatory monitoring, remain foundational but face limitations regarding signal quality and intermittent capture in neonates. Emerging technologies—specifically deep learning algorithms, biocompatible wearable sensors, and non-contact sensing modalities—offer promising avenues to enhance detection. While AI models in broader pediatric cohorts have reported diagnostic accuracies exceeding 90%, neonatal-specific validation remains a critical need. This review discusses the integration of these tools into clinical workflows, highlighting potential improvements in diagnostic timing while addressing persistent technical, regulatory, and ethical barriers. We provide a framework for clinicians navigating this evolving landscape, emphasizing the need for rigorous validation of new technologies in the unique neonatal population.