Analysis of Saturation in the Emergency Department: A Data-Driven Queuing Model Using Machine Learning.

Area of Science:

• Health Systems Science
• Operations Research
• Machine Learning

Background:

• Emergency departments (EDs) are critical healthcare components.
• ED crowding negatively impacts patient outcomes and operational efficiency.
• Effective management of ED crowding is essential for patient well-being.

Purpose of the Study:

• To propose a novel machine learning methodology for ED crowding.
• To develop a queuing network model for optimizing ED patient flow.
• To introduce a congestion indicator for real-time saturation assessment.

Main Methods:

• Development of a machine learning algorithm tailored for healthcare settings.
• Implementation of a queuing network model to simulate patient arrival and service.
• Creation of a dynamic congestion indicator to quantify ED saturation levels.

Main Results:

• The proposed methodology effectively measures real-time ED crowding.
• The queuing model provides insights for optimizing patient throughput.
• The congestion indicator accurately reflects the level of saturation within the ED.

Conclusions:

• The integrated approach offers a robust solution for managing ED crowding.
• This methodology can enhance patient care and operational efficiency in emergency departments.
• Real-time monitoring via a congestion indicator is key to proactive crowding management.