Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Master's Award: Canada Graduate Scholarships

University of Toronto

$17,500.00

Development of advanced computer vision technologies for unobtrusive monitoring of sleep during pregnancy

EF 2021-22

Résumé
Stillbirth is a tragedy with lasting physical and mental health effects on the mother and father similar to the death of a child. In high-income countries (HICs) like Canada, the top three risk factors for stillbirth are age over 35, obesity, and smoking. Of these three risk factors, the only one that can be realistically eliminated in the course of a nine-month pregnancy is smoking. Recently, however, supine sleeping position in late pregnancy has been associated with stillbirth, which is likely due to changes in uteroplacental hemodynamics that occur in the supine position. A recent individual patient data meta analysis using HIC data demonstrated that if all pregnant persons avoided sleeping supine in late pregnancy, stillbirth rates could be reduced by 5.8%. For comparison, if all pregnant persons quit smoking, the stillbirth rate could be reduced by 5.5%. One issue with previous research showing an association between supine sleep and late stillbirth is that sleeping position was self-reported retrospectively, which is known to be inaccurate. There is currently a lack of tools for detecting and measuring sleeping position in late pregnancy making research in this area challenging. This summer, I collected infrared videos of 25 pregnant participants and used computer vision techniques (CVT) to build a tool for automatic and accurate detection of 12 unique sleeping positions. Now, I am collecting a large dataset of infrared video recordings of overnight sleep during late pregnancy along with important maternal-fetal physiologic signals. I am using CVT to gain insight on interactions between supine sleep and maternal-fetal physiology. I plan to use CVT to build research and clinical tools for diagnosis and treatment of sleep disorders in pregnancy.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
467115
Name
Kember Allan J
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Development of advanced computer vision technologies for unobtrusive monitoring of sleep during pregnancy
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Computer Vision; Deep Learning; Fetal Growth; Low Birth Weight; Posture; Pregnancy; Sleep; Sleep Disordered Breathing; Stillbirth
Abstract
Stillbirth is a tragedy with lasting physical and mental health effects on the mother and father similar to the death of a child. In high-income countries (HICs) like Canada, the top three risk factors for stillbirth are age over 35, obesity, and smoking. Of these three risk factors, the only one that can be realistically eliminated in the course of a nine-month pregnancy is smoking. Recently, however, supine sleeping position in late pregnancy has been associated with stillbirth, which is likely due to changes in uteroplacental hemodynamics that occur in the supine position. A recent individual patient data meta analysis using HIC data demonstrated that if all pregnant persons avoided sleeping supine in late pregnancy, stillbirth rates could be reduced by 5.8%. For comparison, if all pregnant persons quit smoking, the stillbirth rate could be reduced by 5.5%. One issue with previous research showing an association between supine sleep and late stillbirth is that sleeping position was self-reported retrospectively, which is known to be inaccurate. There is currently a lack of tools for detecting and measuring sleeping position in late pregnancy making research in this area challenging. This summer, I collected infrared videos of 25 pregnant participants and used computer vision techniques (CVT) to build a tool for automatic and accurate detection of 12 unique sleeping positions. Now, I am collecting a large dataset of infrared video recordings of overnight sleep during late pregnancy along with important maternal-fetal physiologic signals. I am using CVT to gain insight on interactions between supine sleep and maternal-fetal physiology. I plan to use CVT to build research and clinical tools for diagnosis and treatment of sleep disorders in pregnancy.
Competitiondate
202112
Approvedterm2
1 yr 0 mth
Pinamesdelim
Kember, Allan J
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~