Evaluating Artificial Intelligence Technologies in Healthcare Using the EDAS Method

The rapid advancement of Artificial Intelligence (AI) in healthcare has led to the adoption of diverse technologies aimed at improving accuracy, efficiency, and cost-effectiveness. This study applies the Evaluation Based on Distance from Average Solution (EDAS) method to evaluate and rank six prominent AI technologies in healthcare: AI-Powered Diagnosis (AID), Robotic Surgery (RS), Clinical Decision Support Systems (CDSS), Patient Monitoring Systems (PMS), AI-Based Drug Discovery (AIDD), and Chatbots for Patient Interaction (CPI). The technologies were assessed using four evaluation parametersAccuracy (%), Cost Savings (%), Time Efficiency (%), and Training (Hours)with equal weighting assigned to each criterion.The results indicate that Chatbots for Patient Interaction (CPI) rank first due to their superior performance in training efficiency and time optimization, making them ideal for rapid deployment and scalability in healthcare settings. Patient Monitoring Systems (PMS) secured second place, demonstrating a balanced performance across cost savings and operational efficiency. Clinical Decision Support Systems (CDSS) ranked third, largely benefiting from their streamlined training requirements. AI-Based Drug Discovery (AIDD) followed closely, ranking fourth due to significant cost-saving advantages and moderate time efficiency. AI-Powered Diagnosis (AID) ranked fifth, primarily excelling in accuracy but underperforming in other parameters. Finally, Robotic Surgery (RS) ranked last (sixth) despite achieving the highest accuracy, as its extensive training requirements and relatively limited cost efficiency impacted its overall performance.This study highlights the effectiveness of the EDAS method as a multi-criteria decision-making framework, enabling a comprehensive evaluation of AI technologies in healthcare. The rankings emphasize the trade-offs among accuracy, cost, efficiency, and ease of implementation, offering valuable insights for healthcare stakeholders to prioritize AI solutions that align with their operational needs and resource constraints. Future research can further refine this approach by integrating additional criteria or dynamic weight assignments to reflect varying healthcare priorities.