slide1 n.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Intelligent Systems (AI-2) Computer Science cpsc422 , Lecture 9 Jan, 24, 2014 PowerPoint Presentation
Download Presentation
Intelligent Systems (AI-2) Computer Science cpsc422 , Lecture 9 Jan, 24, 2014

Loading in 2 Seconds...

play fullscreen
1 / 19

Intelligent Systems (AI-2) Computer Science cpsc422 , Lecture 9 Jan, 24, 2014 - PowerPoint PPT Presentation


  • 93 Views
  • Uploaded on

Intelligent Systems (AI-2) Computer Science cpsc422 , Lecture 9 Jan, 24, 2014. An MDP Approach to Multi-Category Patient Scheduling in a Diagnostic Facility. Adapted from: Matthew Dirks. Goal / Motivation.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Intelligent Systems (AI-2) Computer Science cpsc422 , Lecture 9 Jan, 24, 2014' - naava


Download Now An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
slide1

Intelligent Systems (AI-2)

Computer Science cpsc422, Lecture 9

Jan, 24, 2014

CPSC 422, Lecture 9

an mdp approach to multi category patient scheduling in a diagnostic facility

An MDP Approach to Multi-Category Patient Scheduling in a Diagnostic Facility

Adapted from: Matthew Dirks

goal motivation
Goal / Motivation
  • To develop a mathematical model for multi-category patient scheduling decisions in computed tomography (CT), and to investigate associated trade-offs from economic and operational perspectives.
  • Contributions to AI, OR and radiology
types of patients
Types of patients:
  • Emergency Patients (EP)
    • Critical(CEP)
    • Non-critical (NCEP)
  • Inpatients (IP)
  • Outpatients
    • Scheduled OP
    • Add-on OP:Semi-urgent (OP)
  • (Green = Types used in this model)
proposed solution
Proposed Solution
  • Finite-horizon MDP
  • Non-stationary arrival probabilities for IPs and EPs
  • Performance objective: Max $
mdp representation
MDP Representation
  • State
    • CEP arrived
    • Number waiting to be scanned
  • Action
    • , )
    • Number chosen for next slot
  • State Transition
    • + - , + - , + - )
    • d Whether a patient type has arrived since the last state
mdp representation cont
MDP Representation (cont’)
  • Transition Probabilities
performance metrics over 1 work day
Performance Metrics (over 1 work-day)
  • Expected net CT revenue
  • Average waiting-time
  • Average # patients not scanned by day’s end
  • Rewards
  • Terminal reward obtained
maximize total expected revenue
Maximize total expected revenue
  • Optimal Policy
    • Solving this gives the policy for each state, n, in the day
  • Finite Horizon MDP
evaluation comparison of mdp with heuristic policies
Evaluation: Comparison of MDP with Heuristic Policies
  • 100,000 independent day-long sample paths (one for each scenario)
  • Percentage Gap in avg. net revenue =

Result Metric

heuristics
Heuristics
  • FCFS: First come first serve
  • R-1: One patient from randomly chosen type is scanned
  • R-2: One patient randomly chosen from all waiting patients (favors types with more people waiting)
  • O-1: Priority
    • OP
    • NCEP
    • IP
  • O-2: Priority:
    • OP
    • IP
    • NCEP
question types from students
Question Types from students
  • Finite vs. infinite
  • Why no VI?
  • 2 patients at once
  • More scanners
  • More patient types (urgency)
  • Uniform slot length (realistic?)
  • Only data from one Hospital (general?)
  • Used in practice ?
  • Operational Cost of Implementing the policy (take into account)