Artificial Intelligence-Assistant Cardiotocography: Unified Model for Signal Reconstruction, Fetal Heart Rate Analysis, and Variability Assessment

2026-05-13

AI Summary

Traditional fetal heart rate monitoring is limited by device performance, signal interference, and subjective interpretation, hindering accurate assessment of fetal well-being. This work proposes a unified end-to-end deep learning model that jointly performs fetal electrocardiogram denoising and reconstruction, heart rate analysis, and variability quantification through self-supervised pretraining followed by fine-tuning on expert annotations. The study introduces an innovative Intersection Overlapping Labels approach to reformulate heart rate event detection as a classification task and incorporates the Fisher criterion to quantify variability. Experimental results demonstrate high performance, with 89.13% sensitivity and 87.78% specificity for deceleration events, 92.04% specificity for acceleration events, and area under the curve (AUC) scores of 0.7214 and 0.9643 for periodicity and amplitude variability, respectively.

Abstract

The monitoring of fetal heart rate (FHR) and the assessment of its variability are crucial for preventing fetal compromise and adverse outcomes. However, traditional methods encounter limitations arising from equipment performance, data transmission, and subjective assessments by doctors. We have developed a tailored AI-based FHrCTG model specifically for FHR monitoring, which effectively mitigates noise interference and precisely reconstructs signals. Our model was pre-trained on a massive dataset consisting of 558,412 unlabeled data points and further refined using 7,266 expert-reviewed entries. To validate FHR, we introduced the Intersection Overlapping Labels (IOL) approach, which transforms rate analysis into categorical judgments. Testing revealed that our model demonstrates high sensitivity and specificity in detecting critical FHR decelerations (89.13% and 87.78%, respectively) and accelerations (62.5% and 92.04%, respectively). Furthermore, based on Fischer's criteria for clinical application, our model achieved impressive AUC scores of 0.7214 and 0.9643 for verifying FHR periodicity and amplitude variation, respectively.

Problem

• fetal heart rate
• cardiotocography
• signal noise
• variability assessment
• subjective assessment

Innovation

• AI-assisted cardiotocography
• signal reconstruction
• fetal heart rate variability
• Intersection Overlapping Labels (IOL)
• unified deep learning model