Grant: Operating Grant: Analyses of Existing Cohorts & Databases - IHDCYH
McMaster University
$74,991.00
Innovative prediction models for risk assessment of preterm birth: a key step to improve care and outcomes
FY 2016-17
Summary
Preterm birth is the leading cause of death in infants and developmental disability in children. Early and accurate risk prediction is challenging, but it could help to prevent preterm birth. There are other important pregnancy outcomes, including small size of babies, babies who do not tolerate the process of labour, and Cesarean section.
Our aim is to improve prediction of preterm birth and other important pregnancy outcomes by using an innovative approach called 'algorithmic statistical modeling' or "ensemble learning". Algorithmic models learn by examples and generalize patterns from data to be able to predict outcomes. This is a powerful approach when the underlying causes of an outcome, such as preterm birth, are too complex to be described by simple mathematical formulas. This will be the first study that will combine the strengths of algorithmic and conventional approaches using data from the whole population of Ontario.
After careful validation of our prediction model on the following year's data, although outside of the scope of this application, we will develop an interactive risk assessment tool for clinical use. Such an application can contribute to improved pregnancy care, prevention of preterm birth and the other outcomes mentioned above and promote healthy pregnancies. It will do so by aiding both decision-making on whether to use interventions or order further tests and communicating risk to pregnant women.
Department
Program
Operating Grant: Analyses of Existing Cohorts & Databases - IHDCYH
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
363409
Name
McDonald Sarah D
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Instname2
Human Development, Child and Youth Health
Theme2
Clinical
Prcname2
Analyses of Existing Canadian Cohorts & Databases - Reproductive Maternal & Child Health
Projecttitle
Innovative prediction models for risk assessment of preterm birth: a key step to improve care and outcomes
Programtype2
Operating Grants
Orgnameinp2
McMaster University
Cihramount2
$74,991
Cihrequipment2
$0
Programname2
Operating Grant: Analyses of Existing Cohorts & Databases - IHDCYH
Keyworddelim
Big Data; Ensemble Model; Epidemiology; Machine Learning; Prediction Models; Preterm Birth
Abstract
Preterm birth is the leading cause of death in infants and developmental disability in children. Early and accurate risk prediction is challenging, but it could help to prevent preterm birth. There are other important pregnancy outcomes, including small size of babies, babies who do not tolerate the process of labour, and Cesarean section.
Our aim is to improve prediction of preterm birth and other important pregnancy outcomes by using an innovative approach called 'algorithmic statistical modeling' or "ensemble learning". Algorithmic models learn by examples and generalize patterns from data to be able to predict outcomes. This is a powerful approach when the underlying causes of an outcome, such as preterm birth, are too complex to be described by simple mathematical formulas. This will be the first study that will combine the strengths of algorithmic and conventional approaches using data from the whole population of Ontario.
After careful validation of our prediction model on the following year's data, although outside of the scope of this application, we will develop an interactive risk assessment tool for clinical use. Such an application can contribute to improved pregnancy care, prevention of preterm birth and the other outcomes mentioned above and promote healthy pregnancies. It will do so by aiding both decision-making on whether to use interventions or order further tests and communicating risk to pregnant women.
Competitiondate
201609
Approvedterm2
1 yr 0 mth
Pinamesdelim
McDonald, Sarah D
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $74,991~ $0~