The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to improve high-risk pregnancy care and preterm labor detection by developing a noninvasive, low-cost, point-of-care wearable electronic patch for pregnancy monitoring in both clinical and home environments. Each year, 4 million women give birth in the US. More than one in ten of pregnancies is considered high-risk, where the mother, fetus, or newborn has elevated risk of experiencing an adverse health condition. The proposed platform will allow doctors to remotely monitor and manage high-risk pregnancies and intervene, as needed, upon detection of labor or other potential complications. By enhancing early detection of fetal well-being and increasing access to care, the device will allow for improved healthcare delivery, thus increasing mother and infant safety, preventing maternal and neonatal morbidities, and lowering healthcare costs. By applying machine learning to what could become the largest and most comprehensive dataset on maternal and fetal health, the proposed platform could become a valuable resource to researchers to identify underlying causes and biomarkers of preterm birth. Primary end users are women with high-risk pregnancies, and elevated risk of preterm birth. Target customers are hospitals, health care providers and insurance companies. This Small Business Innovation Research (SBIR) Phase I project seeks to develop an unprecedented means to support advances in maternal and fetal health: a state-of-the-art miniaturized mobile monitor that discretely sticks onto the mother's abdomen and uses sensors to noninvasively monitor fetal heart rate (FHR) and other physiological parameters in home and clinical environments. The device communicates to a smartphone, which acts as gateway to send data to a cloud-based platform, where the data is collected, stored and analyzed, with doctors able to set notification thresholds. For this project, patch technology, proven to effectively measure uterine activity and fetal movement will be leveraged to develop a disruptive product capable of detecting FHR as early as 25 weeks gestation. Miniaturization, power consumption and cost levels necessary for deployment in remote settings will be achieved. A usability study of the prototype monitor will then be conducted in expectant women in hospital settings, followed by an equivalency study to validate accuracy of the prototype compared to cardiotocogram, the current clinical gold standard. This solution will increase specificity of FHR testing, and improve interpretation of monitoring data, as well as aggregate data to train AI models to predict adverse events such as preterm birth.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
