A deep learning model pre-trained on over 558k unlabeled FHR recordings and fine-tuned on 7k expert labels achieves 89% sensitivity for decelerations and AUC 0.96 for amplitude variability assessment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Artificial Intelligence-Assistant Cardiotocography: Unified Model for Signal Reconstruction, Fetal Heart Rate Analysis, and Variability Assessment
A deep learning model pre-trained on over 558k unlabeled FHR recordings and fine-tuned on 7k expert labels achieves 89% sensitivity for decelerations and AUC 0.96 for amplitude variability assessment.