RESEARCH OF MODELS FOR OPTIMIZING THE USE OF MEDICAL EQUIPMENT IN CRISIS CONDITIONS

Abstract

The algorithms and models for optimizing the management of healthcare systems for the efficient use of medical equipment in crisis conditions are considered. The study proposes an integrated approach that combines linear integer programming (MILP) methods, heuristic algorithms such as the genetic algorithm and particle swarm optimization (PSO), as well as stochastic methods. The key objective of this research is to improve the efficiency of resource allocation in medical facilities during emergency situations, ensuring optimal distribution of critical medical equipment in response to dynamically changing demands.

The study evaluates the performance of different optimization techniques based on key criteria: computational speed, resource allocation quality, and adaptability to unpredictable changes. The integration of parallel computing through the MapReduce framework significantly enhances processing efficiency, making it suitable for real-time crisis response scenarios.

The proposed models are tested under simulated crisis conditions, including pandemic scenarios, natural disasters, and supply chain disruptions. The results indicate that hybrid optimization methods, combining deterministic and heuristic approaches, provide a balance between computational efficiency and optimal decision-making.

The study highlights the importance of resilience in healthcare systems and the need for flexible optimization models that can dynamically adjust to sudden changes in medical equipment demand. The findings contribute to the development of advanced decision-support systems for emergency medical resource management, ensuring that healthcare institutions can respond effectively to critical shortages. Future research will focus on expanding these models to optimize pharmaceutical distribution and emergency medical staffing.