Multi-View Hierarchical Representation Learning of Fetal Hemodynamics for Maternal Hypertension Detection at the Edge
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909009400823808 |
|---|---|
| author | Rafiei, Alireza Strader, Anahí Venzor Aragón, Esteban Castro Serech, Victoriana Rosibely Sut Ixen, Enma Carolina Coyote Sameni, Reza Rohloff, Peter Clifford, Gari D. Katebi, Nasim |
| author_facet | Rafiei, Alireza Strader, Anahí Venzor Aragón, Esteban Castro Serech, Victoriana Rosibely Sut Ixen, Enma Carolina Coyote Sameni, Reza Rohloff, Peter Clifford, Gari D. Katebi, Nasim |
| contents | Hypertensive disorders of pregnancy remain a leading cause of maternal and fetal morbidity worldwide, yet diagnosis relies on intermittent cuff-based blood pressure measurements that are prone to bias and fail to capture continuous physiological dynamics. Growing evidence suggests that fetal cardiovascular activity is associated with maternal-placental hemodynamics and may encode markers of maternal hypertension. To analyze this, we collected a large-scale dataset of fetal one-dimensional Doppler ultrasound recordings paired with maternal blood pressure from 3,255 pregnant women across 8,170 antenatal visits in rural Guatemala. We developed AutoHyPE, a hierarchical attention network that models short- and long-term signal structure, incorporating a novel prototype-based contrastive learning and multi-view strategy to enhance representation robustness under long-tailed class distribution and biological variability. AutoHyPE achieved an AUROC of 0.80 for maternal hypertension detection, outperforming baseline approaches while maintaining balanced performance across classes, with no performance degradation in an edge deployment scenario. Our findings demonstrated that fetal cardiac mechanical activity contains hemodynamic features indicative of maternal hypertension status. This supports a promising paradigm shift toward continuous, objective monitoring of maternal health using existing, low-cost ultrasound technology and introduces a complementary approach to traditional methods based on blood pressure measurements, advancing scalable prenatal care. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00872 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-View Hierarchical Representation Learning of Fetal Hemodynamics for Maternal Hypertension Detection at the Edge Rafiei, Alireza Strader, Anahí Venzor Aragón, Esteban Castro Serech, Victoriana Rosibely Sut Ixen, Enma Carolina Coyote Sameni, Reza Rohloff, Peter Clifford, Gari D. Katebi, Nasim Signal Processing Artificial Intelligence Computer Vision and Pattern Recognition Hypertensive disorders of pregnancy remain a leading cause of maternal and fetal morbidity worldwide, yet diagnosis relies on intermittent cuff-based blood pressure measurements that are prone to bias and fail to capture continuous physiological dynamics. Growing evidence suggests that fetal cardiovascular activity is associated with maternal-placental hemodynamics and may encode markers of maternal hypertension. To analyze this, we collected a large-scale dataset of fetal one-dimensional Doppler ultrasound recordings paired with maternal blood pressure from 3,255 pregnant women across 8,170 antenatal visits in rural Guatemala. We developed AutoHyPE, a hierarchical attention network that models short- and long-term signal structure, incorporating a novel prototype-based contrastive learning and multi-view strategy to enhance representation robustness under long-tailed class distribution and biological variability. AutoHyPE achieved an AUROC of 0.80 for maternal hypertension detection, outperforming baseline approaches while maintaining balanced performance across classes, with no performance degradation in an edge deployment scenario. Our findings demonstrated that fetal cardiac mechanical activity contains hemodynamic features indicative of maternal hypertension status. This supports a promising paradigm shift toward continuous, objective monitoring of maternal health using existing, low-cost ultrasound technology and introduces a complementary approach to traditional methods based on blood pressure measurements, advancing scalable prenatal care. |
| title | Multi-View Hierarchical Representation Learning of Fetal Hemodynamics for Maternal Hypertension Detection at the Edge |
| topic | Signal Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.00872 |