Workflow
观心大模型CardioMind
icon
Search documents
推动大健康产业跃升,上海积极推动人工智能赋能生命健康领域
Zhong Guo Jing Ji Wang· 2025-06-03 02:01
在数字化转型浪潮中,人工智能技术已经渗透医疗服务全链条,从早期筛查到精准治疗,从药物研发到 术后管理,为医疗行业"提质增效"提供了强大动能。连日来,记者在采访中了解到,随着一系列医疗智 能体的落地,上海积极推动人工智能赋能生命健康产业,一场健康产业智能变革,正在这里展开。 破解基层痛点 2016年,被称为"健康守门人"的家庭医生制度开始在国内全面推行,尤其要解决慢病患者、老年人等重 点人群的医疗卫生服务问题。作为试点城市,上海从2011年便开始推行家庭医生签约制。今年5月18 日,上海市卫健委公布一组最新数据:全上海累计家庭医生签约数超1100万人,常住人口签约率达 45%,老年人和慢性病患者等重点人群签约率超84%;上海二级、三级医院50%门诊号源优先向社区开 放,实现家庭医生快捷预约。 但是,家庭医生签约服务存在不少难点、痛点和堵点。中国第一代全科医生、中国医师协会全科医师分 会原会长杜雪平曾坦言,其所在的机构每一个全科医生要签500—2000个老百姓,"人手不够,全科医生 不仅是家庭医生,还要完成门诊、教研、科学、社会等各方面任务,分身乏术。" 无独有偶,中国电信(601728)上海公司(以下简称"上海 ...
AI赋能健康专业大模型、智能体多场景应用
Huan Qiu Wang Zi Xun· 2025-06-02 03:29
Group 1 - The development of AI in Shanghai is enhancing disease diagnosis and treatment, serving as a valuable assistant for clinicians and a tool for health education in schools, communities, and families [1][2] - The AI model "Qizhi," focused on children's brain health, has been launched in Shanghai, enabling rapid identification of brain abnormalities through patient-uploaded reports, thus improving diagnostic capabilities for grassroots doctors [1] - The "CardioMind" model, introduced at the 19th Oriental Cardiology Conference, showcases advanced multimodal data integration and deep reasoning capabilities, significantly improving diagnostic accuracy and reducing misdiagnosis [1] Group 2 - The establishment of the "Tumor-Cardiology AI Consortium" aims to address the challenges of treating immune myocarditis in cancer patients by integrating various myocardial injury markers and new indicators developed by a multidisciplinary team [2] - AI is expected to optimize medical resource allocation and enhance accessibility to healthcare services, extending its applications beyond hospitals to schools, communities, and homes [2] - The "Smart Eye Spirit," an AI eye health assistant, debuted during a children's eye health event, providing immediate answers to public inquiries about eye care [2] Group 3 - The accuracy and reliability of large models depend on the quality of training data, and challenges such as patient trust in digital doctors and compliance with ethical and regulatory standards must be addressed for AI's effective application in medicine [3]