Detection of maternal and fetal stress from the electrocardiogram with self-supervised representation learning

• Autores: Sarkar, Pritam; Lobmaier, Silvia; Fabre, Bibiana; Gonzalez, Diego Javier; Mueller, Alexander; Frasch, Martin G.; Antonelli, Marta Cristina; Etemad, Ali
• Año de publicación: 2021
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: DEEP LEARNING; HEART RATE VARIABILITY; PRENATAL STRESS; ELECTROCARDIOGRAM
• Institución: Consejo Nacional de Investigaciones Científicas y Técnicas

In the pregnant mother and her fetus, chronic prenatal stress results in entrainment of the fetal heartbeat by the maternal heartbeat, quantified by the fetal stress index (FSI). Deep learning (DL) is capable of pattern detection in complex medical data with high accuracy in noisy real-life environments, but little is known about DL’s utility in non-invasive biometric monitoring during pregnancy. A recently established self-supervised learning (SSL) approach to DL provides emotional recognition from electrocardiogram (ECG). We hypothesized that SSL will identify chronically stressed mother-fetus dyads from the raw maternal abdominal electrocardiograms (aECG), containing fetal and maternal ECG. Chronically stressed mothers and controls matched at enrolment at 32 weeks of gestation were studied. We validated the chronic stress exposure by psychological inventory, maternal hair cortisol and FSI. We tested two variants of SSL architecture, one trained on the generic ECG features for emotional recognition obtained from public datasets and another transfer-learned on a subset of our data. Our DL models accurately detect the chronic stress exposure group (AUROC = 0.982 ± 0.002), the individual psychological stress score (R2 = 0.943 ± 0.009) and FSI at 34 weeks of gestation (R2 = 0.946 ± 0.013), as well as the maternal hair cortisol at birth reflecting chronic stress exposure (0.931 ± 0.006). The best performance was achieved with the DL model trained on the public dataset and using maternal ECG alone. The present DL approach provides a novel source of physiological insights into complex multi-modal relationships between different regulatory systems exposed to chronic stress. The final DL model can be deployed in low-cost regular ECG biosensors as a simple, ubiquitous early stress detection and monitoring tool during pregnancy. This discovery should enable early behavioral interventions.
Fil: Sarkar, Pritam. Queens University; Canadá
Fil: Lobmaier, Silvia. Universitat Technical Zu Munich; Alemania
Fil: Fabre, Bibiana. Universidad de Buenos Aires; Argentina
Fil: Gonzalez, Diego Javier. Universidad de Buenos Aires; Argentina
Fil: Mueller, Alexander. Universitat Technical Zu Munich; Alemania
Fil: Frasch, Martin G.. University of Washington; Estados Unidos
Fil: Antonelli, Marta Cristina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Biología Celular y Neurociencia "Prof. Eduardo de Robertis". Universidad de Buenos Aires. Facultad de Medicina. Instituto de Biología Celular y Neurociencia; Argentina
Fil: Etemad, Ali. Queens University; Canadá