Optimization

Dynamic Patient Scheduling Optimization

In many healthcare systems patients require multiple visits to a healthcare provider. The first visit is the consult visit and all subsequent visits are follow-up visits, typically occurring according to predefined booking guidelines. A Markov Decision Process model is used to efficiently allocate available capacity to consult and follow-up visits in a dynamic fashion. A Linear Programming approach to Approximate Dynamic Programming (ADP) is used to solve this model.

Domain

Healthcare Operations

Methods

  • Markov Decision Processes
  • Approximate Dynamic Programming
  • Linear Programming
  • Simulation

Tools

  • Python
  • Gurobi

Impact / Outcome

Derived approximate optimal booking policies for multi-class patient settings, balancing consult and follow-up capacity allocation.