Load-sensitive dynamic workflow re-orchestration and optimisation for faster patient healthcare

Area of Science:

• Healthcare Operations Research
• Health Informatics
• Queueing Theory Applications

Background:

• Hospital waiting times are a significant and growing problem, exacerbated by demographic shifts and infrastructure limitations.
• Current healthcare systems face challenges in managing patient flow efficiently, leading to prolonged delays for essential services.
• Factors like population growth and an aging population are projected to worsen existing hospital wait times.

Purpose of the Study:

• To demonstrate how healthcare services can be modeled as queueing nodes within a workflow.
• To investigate the optimization of healthcare service workflows during execution to minimize patient waiting times.
• To explore dynamic re-orchestration strategies for improving efficiency in services like X-ray, CT, and MRI.

Main Methods:

• Modeling healthcare services as queueing nodes.
• Analyzing healthcare service workflows to identify bottlenecks.
• Implementing dynamic re-orchestration of workflows based on real-time waiting times.
• Utilizing queueing theory principles to optimize patient flow.

Main Results:

• Experimental results show that optimizing workflows through dynamic re-orchestration can reduce average patient waiting times.
• The proposed modeling approach effectively identifies areas for workflow improvement.
• Demonstrated feasibility of re-orchestrating services like X-ray, CT, and MRI to decrease queues.

Conclusions:

• Dynamic re-orchestration of healthcare workflows is a viable strategy for reducing hospital waiting times.
• Modeling healthcare services as queueing nodes provides a framework for optimizing patient flow.
• Further implementation of these optimization techniques can lead to more efficient healthcare delivery.