Approximate dynamic programming approaches for appointment scheduling with patient preferences.

Area of Science:

• Operations Research
• Healthcare Management
• Computer Science

Background:

• Patient satisfaction in outpatient settings is significantly influenced by preference fulfillment for physicians and appointment times.
• Sequential appointment scheduling requires consideration of future requests for system efficiency.
• Existing models often do not adequately focus on patient preference satisfaction as a primary evaluation metric.

Purpose of the Study:

• To propose a novel Markov decision process (MDP) model for optimizing sequential appointment scheduling in outpatient departments.
• To incorporate patient preferences, including physician choice and time slots, as a key factor in booking decisions.
• To develop efficient algorithms for practical implementation of the proposed MDP model.

Main Methods:

• Formulation of a Markov decision process model tailored for sequential appointment scheduling with patient preferences.
• Analysis of model characteristics to derive effective booking policies.
• Development of two approximate dynamic programming algorithms to mitigate the curse of dimensionality.

Main Results:

• The proposed MDP model prioritizes patient preference satisfaction in booking decisions.
• Two approximate dynamic programming algorithms were developed and evaluated for efficiency.
• Experimental results provide insights for model refinement and algorithm improvement.

Conclusions:

• The MDP model offers a promising approach to optimizing appointment scheduling by focusing on patient preferences.
• The developed algorithms demonstrate potential for overcoming computational challenges in complex scheduling problems.
• Further research can enhance model fine-tuning and algorithmic performance for improved healthcare system efficiency.