Core Viewpoint - The rapid advancement of artificial intelligence (AI) technology is driving the development of medical AI to assist doctors and take on some of their technical tasks, raising concerns about the safe and effective application of medical AI [1][3] Group 1: Establishment of Evaluation Center - The Beijing Municipal Health Commission has established a Medical AI Application Evaluation Center to create a regulatory framework and standards for medical AI evaluation [1][3] - The center aims to validate the clinical decision-making capabilities and effectiveness of medical AI, ensuring safety in its application [1][3] Group 2: Evaluation Criteria - Medical AI applications will be evaluated similarly to doctors, focusing on multiple dimensions such as safety, professionalism, and practicality [3] - A multi-dimensional assessment standard has been developed, consisting of six core evaluation dimensions: medical compliance and ethics, evidence-based medicine and knowledge, general auxiliary capabilities, specialty diagnosis and treatment quality control, adaptability of diagnosis and treatment processes, and accuracy of diagnostic decisions, encompassing over 70 specific evaluation tasks [3][4] Group 3: Data and Methodology - The evaluation center collaborates with key hospitals, research institutions, and authoritative expert teams to construct a high-quality evaluation dataset using clinical cases and authoritative medical guidelines [3][4] - An innovative AI-based scoring mechanism has been introduced to ensure objective and scientific evaluation results, focusing on reasoning logic and diagnostic thought processes rather than just final outcomes [4] Group 4: Future Plans - The evaluation center plans to expand its evaluation services to cover various medical fields, including internal medicine, surgery, and pediatrics, to support the healthy development of the medical AI industry and better meet public health needs [5]

Core Viewpoint - The Beijing Municipal Health Commission has launched an evaluation service for artificial intelligence applications in the medical field, focusing initially on thoracic surgery, marking the first external evaluation service from the national AI application pilot base in healthcare [1] Group 1: Evaluation Service Overview - The evaluation service aims to assess AI applications in healthcare, with a focus on thoracic surgery, and will prioritize promoting outstanding applications to medical institutions [1] - The initiative signifies the expansion and deepening of the national AI application pilot base's external service capabilities in Beijing [1] Group 2: Evaluation Requirements - The evaluation of medical AI must adhere to high standards, emphasizing three key aspects: comprehensive evaluation content, authoritative evaluation data, and scientific evaluation results [2][3] - Evaluation content should consider not only accuracy but also ethics, information security, and the reasoning process behind AI conclusions [2] - The evaluation data must be based on real clinical cases and the latest medical guidelines to accurately reflect AI applications in serious medical scenarios [2] Group 3: Evaluation Methodology - The evaluation center has established a multi-dimensional assessment standard with six core dimensions, including medical compliance, evidence-based knowledge, and diagnostic accuracy, covering over 70 specific evaluation tasks [4] - The evaluation process involves user application, system assessment, and expert review, ensuring a rigorous and objective evaluation [6] - An innovative "referee model" has been introduced to assess the reasoning logic and diagnostic thought processes of AI applications, ensuring a fair and scientific evaluation [6]