Grant: Master's Award: Canada Graduate Research Scholarships - Master's program
University of Toronto
$27,000.00
Smart Scheduling: Integrated Machine Learning and Optimization for Comprehensive Operating Room Management
FY 2025-26
Summary
Canadian hospitals face a critical challenge: surgical wait times continue to increase despite rising healthcare spending. Current surgical scheduling relies on manual approaches that don't account for patient complexity, available resources, or fluctuating demand. This inefficiency costs billions annually and prevents patients from receiving timely care. This research will develop and test a novel approach to optimize how hospitals schedule surgeries. The system combines machine learning (ML) models that predict how long surgeries will take and how many emergency trauma cases will arrive, with automated scheduling algorithms that create optimized daily and quarterly operating room schedules. Using data from Sunnybrook Health Sciences Centre and provincial health records, the system will learn from past surgical cases to make better predictions about future needs. Critically, this research explicitly addresses fairness to ensure the system doesn't replicate biases from past scheduling practices. We will analyze whether historical scheduling decisions favoured certain patient groups and build safeguards into the algorithms to ensure equitable access. The system will be designed to balance multiple objectives: maximizing the number of completed surgeries, minimizing overtime and wasted operating room time, and ensuring fair treatment of all patients. The research will culminate with a 6-month real-world validation study comparing ML-generated shadow schedules against current manual scheduling practices. Success will demonstrate that intelligent scheduling can simultaneously improve hospital efficiency, reduce costs, and ensure equitable care; providing a blueprint for healthcare systems across Canada to deliver safer, more accessible surgical care to all patients.
Department
Program
Master's Award: Canada Graduate Research Scholarships - Master's program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
573164
Name
Abbas Aazad
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Smart Scheduling: Integrated Machine Learning and Optimization for Comprehensive Operating Room Management
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Research Scholarships - Master's program
Keyworddelim
Fairness; Machine Learning; Optimization; Orthopaedics; Patient Outcomes; Scheduling; Surgery
Abstract
Canadian hospitals face a critical challenge: surgical wait times continue to increase despite rising healthcare spending. Current surgical scheduling relies on manual approaches that don't account for patient complexity, available resources, or fluctuating demand. This inefficiency costs billions annually and prevents patients from receiving timely care. This research will develop and test a novel approach to optimize how hospitals schedule surgeries. The system combines machine learning (ML) models that predict how long surgeries will take and how many emergency trauma cases will arrive, with automated scheduling algorithms that create optimized daily and quarterly operating room schedules. Using data from Sunnybrook Health Sciences Centre and provincial health records, the system will learn from past surgical cases to make better predictions about future needs. Critically, this research explicitly addresses fairness to ensure the system doesn't replicate biases from past scheduling practices. We will analyze whether historical scheduling decisions favoured certain patient groups and build safeguards into the algorithms to ensure equitable access. The system will be designed to balance multiple objectives: maximizing the number of completed surgeries, minimizing overtime and wasted operating room time, and ensuring fair treatment of all patients. The research will culminate with a 6-month real-world validation study comparing ML-generated shadow schedules against current manual scheduling practices. Success will demonstrate that intelligent scheduling can simultaneously improve hospital efficiency, reduce costs, and ensure equitable care; providing a blueprint for healthcare systems across Canada to deliver safer, more accessible surgical care to all patients.
Competitiondate
202512
Approvedterm2
1 yr 0 mth
Pinamesdelim
Abbas, Aazad
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~