Clustering and Stochastic Simulation Optimization for Outpatient Chemotherapy Appointment Planning and Scheduling

Area of Science:

• Operations Research
• Healthcare Management
• Applied Mathematics

Background:

• Outpatient Chemotherapy Appointment (OCA) planning and scheduling is a complex multi-stage process critical for patient care and resource management.
• Current methods often fail to address interdependencies, stochastic durations, uncertain events, and complex patient pathways simultaneously.
• Inefficient scheduling leads to prolonged patient stays and staff overtime, impacting overall healthcare system performance.

Purpose of the Study:

• To develop and evaluate a novel methodology for Outpatient Chemotherapy Appointment (OCA) planning and scheduling.
• To address the complexities of multi-stage processes, stochastic durations, and uncertain events in chemotherapy scheduling.
• To improve the overall performance of the Outpatient Chemotherapy Process (OCP) by minimizing patient length of stay and staff overtime.

Main Methods:

• A Stochastic Discrete Simulation-Based Multi-Objective Optimization (SDSMO) model was developed.
• Clustering algorithms were integrated with the SDSMO model using an iterative sequential approach.
• The methodology was tested using data from a real Outpatient Chemotherapy Center (OCC) and compared against baseline and sequencing heuristics.

Main Results:

• Clustering similar appointments significantly improved performance measures, including reduced patient length of stay and staff overtime.
• The developed cluster-based stochastic optimization approach demonstrated superior performance compared to existing heuristics.
• Computational time was also positively affected by the clustering of similar appointments.

Conclusions:

• The proposed clustering and stochastic optimization methodology effectively addresses the multifaceted challenges in OCA planning and scheduling.
• This approach offers a robust decision support system for optimizing chemotherapy scheduling in real-world clinical settings.
• The findings highlight the benefits of integrating clustering with stochastic optimization for enhanced healthcare operational efficiency.