Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Operating Grant: Advancing Theoretical Method. Innovations Hlth Res- HSPR

McGill University

$193,863.00

Accuracy of using automated methods of adverse events detection

EF 2011-12

Résumé
Each year, adverse events (AEs) are responsible of 44,000 to 98,000 deaths in acute care hospitals, and it is estimated that 30% to 40% of all AEs are preventable. Recent research suggests that understaffing and the use of less qualified nursing staff are important contributors to the incidence of AEs in these settings. With a shortage of nurses that is expected to worsen in the coming years, there is a need to identify the optimal nurse staffing levels (i.e., the number of nurses and mixes of skills, education, and experience) that are needed to minimize AEs. To this end, the association between nurse staffing levels and the incidence of AEs, and the thresholds for safe staffing levels, need to be determined by conducting longitudinal studies. An important prerequisite to examining these central questions in the management of nursing staff in acute care hospitals is to identify accurate, timely and effective methods for measuring AEs. However, most acute care hospitals do not have such methods for monitoring AEs. With the advent of electronic medical records and the digital capture of clinical data - which were paralleled with the development of automated methods for encoding and classifying narrative clinical data -, an exciting opportunity has emerged to identify potentially more accurate and timely methods of AE detection. Taking advantage of this new opportunity, the objective of this study is to assess the accuracy of using automated methods for detecting AEs from electronic clinical data. Specifically, the accuracy of using automated methods of AEs detection will be assessed in comparison with the information contained in patients' medical charts (gold standard). The results of this study will likely produce more accurate and timely measures of AEs detection, a critical requirement to advance existing approaches to nursing staff allocation in acute care hospitals. Moreover, these measures could be used to assess and improve acute care hospitals' performance.
Programme
Operating Grant: Advancing Theoretical Method. Innovations Hlth Res- HSPR
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
256227
Name
Rochefort Christian
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Partnername
Public Health Agency of Canada
Instname2
Health Services and Policy Research
Theme2
Health systems / services
Prcname2
Operating Grant: Innovations in Health Research
Projecttitle
Accuracy of using automated methods of adverse events detection
Programtype2
Operating Grants
Orgnameinp2
McGill University
Cihramount2
$193,863
Cihrequipment2
$0
Programname2
Operating Grant: Advancing Theoretical Method. Innovations Hlth Res- HSPR
Keyworddelim
Acute Care Hospitals; Adverse Events; Automated Detection; Health Informatics; Machine Learning; Natural Language Processing; Surveillance
Abstract
Each year, adverse events (AEs) are responsible of 44,000 to 98,000 deaths in acute care hospitals, and it is estimated that 30% to 40% of all AEs are preventable. Recent research suggests that understaffing and the use of less qualified nursing staff are important contributors to the incidence of AEs in these settings. With a shortage of nurses that is expected to worsen in the coming years, there is a need to identify the optimal nurse staffing levels (i.e., the number of nurses and mixes of skills, education, and experience) that are needed to minimize AEs. To this end, the association between nurse staffing levels and the incidence of AEs, and the thresholds for safe staffing levels, need to be determined by conducting longitudinal studies. An important prerequisite to examining these central questions in the management of nursing staff in acute care hospitals is to identify accurate, timely and effective methods for measuring AEs. However, most acute care hospitals do not have such methods for monitoring AEs. With the advent of electronic medical records and the digital capture of clinical data - which were paralleled with the development of automated methods for encoding and classifying narrative clinical data -, an exciting opportunity has emerged to identify potentially more accurate and timely methods of AE detection. Taking advantage of this new opportunity, the objective of this study is to assess the accuracy of using automated methods for detecting AEs from electronic clinical data. Specifically, the accuracy of using automated methods of AEs detection will be assessed in comparison with the information contained in patients' medical charts (gold standard). The results of this study will likely produce more accurate and timely measures of AEs detection, a critical requirement to advance existing approaches to nursing staff allocation in acute care hospitals. Moreover, these measures could be used to assess and improve acute care hospitals' performance.
Competitiondate
201110
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Rochefort, Christian
Approvedterm
3 ans 0 mois
Cihrcontribution2
Inst of Hlth Serv & Policy Res~ $193,863~ $0~