FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting

2026-05-28

AI Summary

This study addresses the challenge of signal loss in wearable fetal heart rate monitoring caused by maternal or fetal movement, which compromises data integrity and hinders AI-driven fetal risk assessment. To overcome this limitation, the authors propose a novel self-supervised autoencoder based on a masked Transformer architecture—the first to integrate masked self-supervised learning with Transformers for this application. By jointly modeling time-frequency local features, the method enables high-fidelity reconstruction of arbitrarily long missing segments and accurate prediction of future trends. Evaluated across diverse missing-data scenarios, the approach demonstrates robust performance and significantly enhances data completeness, thereby providing high-quality inputs for downstream AI-based fetal risk预警 systems.

Abstract

Approximately 10% of newborns require assistance to initiate breathing at birth, and around 5% need ventilation support. Fetal heart rate (FHR) monitoring plays a crucial role in assessing fetal well-being during prenatal care, enabling the detection of abnormal patterns and supporting timely obstetric interventions to mitigate fetal risks during labor. Applying artificial intelligence (AI) methods to analyze large datasets of continuous FHR monitoring episodes with diverse outcomes may offer novel insights into predicting the risk of needing breathing assistance or interventions. Recent advances in wearable FHR monitors have enabled continuous fetal monitoring without compromising maternal mobility. However, sensor displacement during maternal movement, as well as changes in fetal or maternal position, often lead to signal dropout, resulting in gaps in recorded FHR data. Such missing data limits the extraction of meaningful insights and complicates automated (AI-based) analysis. Traditional approaches to handling missing data, such as simple interpolation techniques, often fail to preserve the spectral characteristics of the signals. In this paper, we propose a masked transformer-based autoencoder approach to reconstruct missing FHR signals by capturing both local temporal and frequency components of the data. The proposed method demonstrates robustness across varying durations of missing data and can be used for signal inpainting and forecasting. The proposed approach can be applied retrospectively to research datasets to support the development of AI-based risk algorithms. In the future, the proposed method could be integrated into wearable FHR monitoring devices to achieve earlier and more robust risk detection.

Problem

• fetal heart rate
• missing data
• signal dropout
• time-series inpainting
• wearable monitoring

Innovation

• masked transformer
• self-supervised learning
• fetal heart rate
• time-series inpainting
• signal reconstruction