Grant: Collaborative Health Research Projects (NSERC partnered)
McGill University
$218,060.00
Knowledge-Based Detection of Hospital Acquired Infections
FY 2009-10
Summary
"At least one out of every twenty people admitted to a Canadian hospital will acquire an infection. These hospital-acquired infections (HAI) have a profound individual and system toll, resulting in thousands of deaths and hundreds of millions of dollars in additional expenses each year. Surveillance for HAI is essential to develop and evaluate prevention and control efforts. In nearly all health care institutions, however, surveillance for HAI is a manual process, requiring highly trained infection control practitioners to consult multiple information systems and paper charts. The amount of effort required for discovery and integration of relevant data from multiple sources limits the current effectiveness of HAI surveillance. Knowledge modeling methods, however, are a potential solution to this problem as they have been used successfully in many fields to integrate and reason with disparate data.
Knowledge modeling is the subfield of artificial intelligence concerned with developing representations or models of knowledge that computers can use to automate and optimize tasks such as classification, prediction, diagnosis, and design. Recent developments in knowledge modeling illustrate the transformational ability of this approach to facilitate the integration of large volumes of disparate data and support reasoning with the integrated data. Despite the clear advantages of knowledge modeling in data and knowledge intensive domains, its use in healthcare and surveillance has emerged slowly. Knowledge modeling is critical, however, to effectively exploit large volumes of data intelligently.
The proposed research brings together three mature research programs, each with a critical component of the expertise required to successfully apply knowledge modeling to the surveillance of HAI. These three research programs bring expertise in epidemiology and public health informatics (McGill), application of semantic technologies in the life sciences (UNB), and patient safety and infectious diseases (Ottawa). We propose to evaluate the ability of knowledge modeling and semantic technologies to support HAI surveillance. More generically, we propose to develop and evaluate methods for semantically annotating health data and then reasoning with these data to identify events of clinical interest."
Department
Program
Collaborative Health Research Projects (NSERC partnered)
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
198806
Name
Buckeridge David L
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Partnername
Natural Sciences and Engineering Research Council of Canada (NSERC)
Instname2
Unable to allocate
Prcname2
Collaborative Health Research Projects - NSERC Partnered
Projecttitle
Knowledge-Based Detection of Hospital Acquired Infections
Programtype2
Operating Grants
Orgnameinp2
McGill University
Cihramount2
$218,060
Cihrequipment2
$0
Programname2
Collaborative Health Research Projects (NSERC partnered)
Keyworddelim
Knoweldge Modeling
Abstract
"At least one out of every twenty people admitted to a Canadian hospital will acquire an infection. These hospital-acquired infections (HAI) have a profound individual and system toll, resulting in thousands of deaths and hundreds of millions of dollars in additional expenses each year. Surveillance for HAI is essential to develop and evaluate prevention and control efforts. In nearly all health care institutions, however, surveillance for HAI is a manual process, requiring highly trained infection control practitioners to consult multiple information systems and paper charts. The amount of effort required for discovery and integration of relevant data from multiple sources limits the current effectiveness of HAI surveillance. Knowledge modeling methods, however, are a potential solution to this problem as they have been used successfully in many fields to integrate and reason with disparate data.
Knowledge modeling is the subfield of artificial intelligence concerned with developing representations or models of knowledge that computers can use to automate and optimize tasks such as classification, prediction, diagnosis, and design. Recent developments in knowledge modeling illustrate the transformational ability of this approach to facilitate the integration of large volumes of disparate data and support reasoning with the integrated data. Despite the clear advantages of knowledge modeling in data and knowledge intensive domains, its use in healthcare and surveillance has emerged slowly. Knowledge modeling is critical, however, to effectively exploit large volumes of data intelligently.
The proposed research brings together three mature research programs, each with a critical component of the expertise required to successfully apply knowledge modeling to the surveillance of HAI. These three research programs bring expertise in epidemiology and public health informatics (McGill), application of semantic technologies in the life sciences (UNB), and patient safety and infectious diseases (Ottawa). We propose to evaluate the ability of knowledge modeling and semantic technologies to support HAI surveillance. More generically, we propose to develop and evaluate methods for semantically annotating health data and then reasoning with these data to identify events of clinical interest."
Competitiondate
200910
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Buckeridge, David L
Approvedterm
3 ans 0 mois
Cihrcontribution2
~ $218,060~ $0~