Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Master's Award: Canada Graduate Scholarships

McGill University

$17,500.00

Validating the generalizability of automated methods for the detection of adverse events associated with the use of mechanical ventilation in intensive care patients

EF 2016-17

Résumé
Adverse-events (AEs) are unintended complications caused by health care management, not by the underlying disease process. Ventilator-Associated events (VAE) is a common AE afflicting mechanically-ventilated intensive care unit (ICU) patients. VAEs are associated with high mortality and morbidity rates and impose a significant economic burden. Preventing VAEs is a high priority worldwide. With the growing emphasis on public reporting and benchmarking of AE data, there is a critical requirement for AE detection methods that are generalizable across healthcare institutions. Currently there are no such methods. With the advent of electronic health records (EHR), and the development of automated methods for encoding and classifying clinical narratives, like the natural language processing (NLP) technique, there is a unique opportunity to develop potentially better methods of VAE detection. Taking advantage of this opportunity, the aim of this Master's thesis research project, which is nested within a broader CIHR-funded study assessing the accuracy and generalizability of novel methods of AE detection methods based on EHR data, is to develop, validate and assess the generalizability of a statistical model predicting the occurrence of VAE in ICU patients. It is expected that this study will result in a more accurate and efficient measure of VAE occurrence and aid in reducing the amount of time devoted by professionals to manually keep track of patients. This measure could be used to assess the incidence rates of VAEs, evaluate the success of preventive interventions, track progress in patient safety through time, or benchmark performance across hospitals.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
367162
Name
Jing Jenny Wenyue
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Validating the generalizability of automated methods for the detection of adverse events associated with the use of mechanical ventilation in intensive care patients
Programtype2
Studentship Programs
Orgnameinp2
McGill University
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Acute Care Hospital; Adverse Events; Automated Detection; Data Warehouse; Electronic Health Record; Hospital-Acquired Infection; Natural Language Processing; Patient Safety; Pneumonia; Ventilator-Associated Event
Abstract
Adverse-events (AEs) are unintended complications caused by health care management, not by the underlying disease process. Ventilator-Associated events (VAE) is a common AE afflicting mechanically-ventilated intensive care unit (ICU) patients. VAEs are associated with high mortality and morbidity rates and impose a significant economic burden. Preventing VAEs is a high priority worldwide. With the growing emphasis on public reporting and benchmarking of AE data, there is a critical requirement for AE detection methods that are generalizable across healthcare institutions. Currently there are no such methods. With the advent of electronic health records (EHR), and the development of automated methods for encoding and classifying clinical narratives, like the natural language processing (NLP) technique, there is a unique opportunity to develop potentially better methods of VAE detection. Taking advantage of this opportunity, the aim of this Master's thesis research project, which is nested within a broader CIHR-funded study assessing the accuracy and generalizability of novel methods of AE detection methods based on EHR data, is to develop, validate and assess the generalizability of a statistical model predicting the occurrence of VAE in ICU patients. It is expected that this study will result in a more accurate and efficient measure of VAE occurrence and aid in reducing the amount of time devoted by professionals to manually keep track of patients. This measure could be used to assess the incidence rates of VAEs, evaluate the success of preventive interventions, track progress in patient safety through time, or benchmark performance across hospitals.
Competitiondate
201612
Approvedterm2
1 yr 0 mth
Pinamesdelim
Jing, Jenny Wenyue
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~