Grant: Master's Award: Canada Graduate Scholarships
University of Toronto
$17,500.00
The Development of An Artificial Intelligence Model for Operative Hand Fractures
FY 2023-24
Summary
Artificial intelligence (AI) tools are becoming ubiquitous in their capacity to automate and enhance clinicians' diagnostic and clinical decision-making. Leveraging AI tools in diagnosing fractures offers a plethora of benefits, including reducing the number of missed fractures, streamlining referral to clinics, facilitating further imaging, increasing timely access to surgical care, and improving patient outcomes. However, there is no existing AI tool for guiding clinical decision making in hand surgery.
Annual costs of upper extremity injuries are estimated at $18 billion in the United States. These costs are only exacerbated by missed or delayed diagnoses. Missed hand fracture diagnoses occur frequently, particularly amongst physicians who are inexperienced in hand surgery and in polytrauma patients. This leads to poor functional outcomes, disability, and altered work ability.
Our aim is to develop an AI tool to diagnose hand fractures that require operative intervention based on x-ray imaging. First, we will use existing, open-access data, i.e. BoneView, to pretrain our model. Next, we will conduct a retrospective chart review (n=1000) of diverse hand fracture cases to train the AI tool to recognize both radiological and clinical patterns indicative of operative fractures with a high degree of accuracy. This tool is unique in its comprehensive application to fractures of the entire hand. Further, its clinical applicability extends beyond simply fracture detection by identifying which fractures require surgery. Finally, what sets this tool apart from the others is its integration of not only radiological examinations, but also relevant patient history and physical examination aspects, offering a more holistic and nuanced diagnostic capability.
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
506556
Name
Wong Chloe
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
The Development of An Artificial Intelligence Model for Operative Hand Fractures
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Bone; Deep Learning; Hand Fracture; Health Services Research; Radiology; Surgery
Abstract
Artificial intelligence (AI) tools are becoming ubiquitous in their capacity to automate and enhance clinicians' diagnostic and clinical decision-making. Leveraging AI tools in diagnosing fractures offers a plethora of benefits, including reducing the number of missed fractures, streamlining referral to clinics, facilitating further imaging, increasing timely access to surgical care, and improving patient outcomes. However, there is no existing AI tool for guiding clinical decision making in hand surgery.
Annual costs of upper extremity injuries are estimated at $18 billion in the United States. These costs are only exacerbated by missed or delayed diagnoses. Missed hand fracture diagnoses occur frequently, particularly amongst physicians who are inexperienced in hand surgery and in polytrauma patients. This leads to poor functional outcomes, disability, and altered work ability.
Our aim is to develop an AI tool to diagnose hand fractures that require operative intervention based on x-ray imaging. First, we will use existing, open-access data, i.e. BoneView, to pretrain our model. Next, we will conduct a retrospective chart review (n=1000) of diverse hand fracture cases to train the AI tool to recognize both radiological and clinical patterns indicative of operative fractures with a high degree of accuracy. This tool is unique in its comprehensive application to fractures of the entire hand. Further, its clinical applicability extends beyond simply fracture detection by identifying which fractures require surgery. Finally, what sets this tool apart from the others is its integration of not only radiological examinations, but also relevant patient history and physical examination aspects, offering a more holistic and nuanced diagnostic capability.
Competitiondate
202312
Approvedterm2
1 yr 0 mth
Pinamesdelim
Wong, Chloe
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~