HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals
Researchers have developed HRVConformer, a novel deep learning model designed to classify neonatal hypoxic-ischemic encephalopathy (HIE) using heart rate signals. This architecture combines convolutional layers for local feature extraction with Transformer attention mechanisms for global context, processing raw heart rate data end-to-end. Trained on a large dataset, HRVConformer achieved an AUC of 83.23% and 74.56% accuracy on a test set, outperforming existing baseline models and offering a promising advancement for automated HIE assessment. AI
IMPACT This research introduces a new deep learning architecture that could improve the accuracy and automation of diagnosing neonatal hypoxic-ischemic encephalopathy.