Harnessing Artificial Intelligence and Machine Learning for Improved Demand Forecasting and Resource Optimization in Saudi Arabian Emergency Medical Services: A Qualitative Study

Abstract

Objective: This qualitative study explores the potential of artificial intelligence (AI) and machine learning (ML) techniques to enhance demand forecasting and resource management in emergency medical services (EMS) in Saudi Arabia.

Methods: Semi-structured interviews were conducted with 25 purposively sampled stakeholders, including EMS technicians, medical secretaries, health services managers, and health assistants. Thematic analysis was performed to identify key themes.

Results: Participants recognized the variability and unpredictability of EMS demand as a major challenge. They believed AI/ML could improve forecast accuracy by leveraging diverse data sources and sophisticated modeling techniques. However, they emphasized the importance of considering contextual factors, involving frontline staff in development, and ensuring transparency and explainability of AI/ML models.

Conclusion: AI/ML has significant potential to optimize EMS demand forecasting and resource allocation in Saudi Arabia. Successful implementation requires addressing technical, organizational, and ethical factors in collaboration with interdisciplinary stakeholders.