FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting
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.
Related
- Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer
- Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
- Neural Realized Measures: Forecast-Supervised Intraday Aggregation for Volatility Forecasting
- RATSIFT: Resolution-Adaptive Transformer for Solar Irradiance Forecasting and Temporal Downscaling
- STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting
BibTeX
@misc{engan2026fhrformer,
title = {{FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting}},
author = {Kjersti Engan and Neel Kanwal and Anita Yeconia and Ladislaus Blacy and Yuda Munyaw and Estomih Mduma and Hege Ersdal},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.29695},
eprint = {2605.29695},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.29695},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting
AU - Kjersti Engan
AU - Neel Kanwal
AU - Anita Yeconia
AU - Ladislaus Blacy
AU - Yuda Munyaw
AU - Estomih Mduma
AU - Hege Ersdal
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2605.29695
UR - https://arxiv.org/abs/2605.29695
AB - 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.
ER -