Patient assignment optimization in cloud healthcare systems: a distributed genetic algorithm

Area of Science:

• Health Informatics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Cloud healthcare systems integrate Internet technologies with traditional healthcare.
• These systems aim to balance online diagnosis and offline treatment.
• Key challenges include reducing patient waiting times and optimizing medical resource utilization.

Purpose of the Study:

• To propose a distributed genetic algorithm (DGA) for optimizing patient assignment (PA) in cloud healthcare systems.
• To enhance the balance between online diagnosis and offline treatment.
• To improve the efficiency and scalability of cloud healthcare systems.

Main Methods:

• A distributed genetic algorithm (DGA) was developed for patient assignment optimization.
• The DGA employs individuals as solutions, using crossover, mutation, and selection operators.
• A distributed framework was implemented to boost population diversity and scalability.

Main Results:

• The proposed DGA effectively optimizes the patient assignment problem in cloud healthcare.
• Experimental results validated the algorithm's performance.
• The DGA demonstrated improvements in balancing online and offline healthcare components.

Conclusions:

• The DGA is a viable and effective method for optimizing patient assignment in cloud healthcare systems.
• This approach contributes to reduced patient waiting times and better resource allocation.
• The DGA framework offers enhanced diversity and scalability for cloud healthcare applications.