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]

央广网北京11月7日消息（总台中国之声记者白杰戈）据中央广播电视总台中国之声报道，北京市 卫生健康委今天（7日）发布《关于开展医疗领域人工智能应用评测工作的通知》（以下简称《通 知》），正式向各企业、研究机构提供评测服务。 "评测结果的科学性"。考试中如果只靠专家凭经验打分，可能会有主观偏差；只靠选择题的准确率 或者得分点的计分，又会漏掉对思考过程的评价。因此，对医疗人工智能应用的评测，不能只看答案， 还要对它的思考和答题过程进行评价，防止"蒙"对了结果，逻辑却错了。 针对上述这几个医疗领域人工智能应用评测的重点难点问题，北京市卫生健康委委托北京市卫生健 康大数据与政策研究中心，配合医疗领域国家人工智能应用中试基地建设，联合全国重点医院与顶尖专 家团队，拿出破题方案，打造了北京医疗人工智能应用评测中心。 评测引入"裁判模型"判卷考察逻辑水平 北京市卫生健康委表示，医疗AI的评测是一项高度专业性的工作，必须依托深厚的医学知识与临 床经验开展，需要顶尖医疗专家的深度参与，需要汇聚医疗行业领域内最前沿的智慧，确保评测工作既 科学严谨又切合临床实际。为此，北京市卫生健康委在国家基地建设中专门设立了医疗人工智能应用评 ...