Abstract
Antepartum Cardiotocography (CTG) is a biomedical sensing technology widely used for fetal health monitoring. While the visual interpretation of CTG traces is highly subjective, with the inter-observer agreement as low as 29% and a false positive rate of approximately 60%, the Dawes-Redman system provides an automated approach to fetal well-being assessments. However, it is primarily designed to rule out adverse outcomes rather than detect them, resulting in a high specificity (90.7%) but low sensitivity (18.2%) in identifying fetal distress. This paper introduces PatchCTG, an AI-enabled biomedical time series transformer for CTG analysis. It employs patch-based tokenisation, instance normalisation, and channel-independent processing to capture essential local and global temporal dependencies within CTG signals. PatchCTG was evaluated on the Oxford Maternity (OXMAT) dataset, which comprises over 20,000 high-quality CTG traces from diverse clinical outcomes, after applying the inclusion and exclusion criteria. With extensive hyperparameter optimisation, PatchCTG achieved an AUC of 0.77, with a specificity of 88% and sensitivity of 57% at Youden's index threshold, demonstrating its adaptability to various clinical needs. Its robust performance across varying temporal thresholds highlights its potential for both real-time and retrospective analysis in sensor-driven fetal monitoring. Testing across varying temporal thresholds showcased it robust predictive performance, particularly with finetuning on data closer to delivery, achieving a sensitivity of 52% and specificity of 88% for near-delivery cases. These findings suggest the potential of PatchCTG to enhance clinical decision-making in antepartum care by providing a sensor-based, AI-driven, objective tool for reliable fetal health assessment.