节点文献

沃森肿瘤人工智能系统在临床中的应用

Clinical Application of Artificial Intelligence——Watson for Oncology

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 周娜李爱芹刘广伟张国庆张晓春

【Author】 ZHOU Na;LI Ai-qin;LIU Guang-wei;The Oncology Hospital of Qingdao University;

【通讯作者】 张晓春;

【机构】 青岛大学附属医院肿瘤内科青岛大学附属医院门诊部青岛大学附属医院青岛大学附属医院肿瘤医院

【摘要】 目的:IBM开发的沃森肿瘤(Watson for Oncology,WFO)2017年开始应用于中国。通过比较沃森肿瘤与医院肿瘤科医生关于肿瘤病人的治疗方案之间的一致性分析,验证沃森肿瘤在我国临床肿瘤中的应用。方法:青岛大学附属医院是国内领先应用该系统和至今接诊病人最多的医院,目前接诊病人1002例。沃森肿瘤的建议分为3类,即:"推荐""可考虑"和"不推荐"。当肿瘤科医生选择"推荐"方案或"可考虑"方案时,认为一致,其余则不一致。结果:肺癌、结直肠癌以及Her-2阴性乳腺癌的一致性均为90%以上。结论:不同癌症类型表现出不同的一致性。发病率和药物可能是不一致的主要原因。沃森肿瘤应用于临床具有一定的优势,要全面、快速地应用于中国,WTO需要加快本土化。

【Abstract】 Objective: Watson for Oncology(WFO) developed by IBM began to be applied in China in 2017. We compared the concordance between WFO and oncologist’s treatment plan for cancer patients, and verified the application of Watson tumor in clinical tumors in China. Methods: The Affiliated Hospital of Qingdao University is the leading hospital in China to apply the system and to receive the most patients up to now. At present, 1002 cases of patients are received. WFO recommendations were provided in 3 categories: "Recommended", "For Consideration", and "Not Recommended." Concordance was achieved when the oncologist’ treatment decisions were in the "Recommended" or "For Consideration" categories in WFO. Results: The concordance of lung cancer, colorectal cancer and Her-2 negative breast cancer was all more than 90%. Conclusion: Different types of cancer have different concordance. The incidence of the disease and the drug may be the main cause of disagreement. WFO has a certain advantage in clinical application. To be comprehensively and rapidly applied in China, WFO needs to accelerate localization.

【基金】 泰山学者建设工程专项经费资助项目(编号:tshw201502061);青岛市民生科技计划项目(编号:16-6-2-3-nsh)~~
  • 【文献出处】 中国数字医学 ,China Digital Medicine , 编辑部邮箱 ,2018年10期
  • 【分类号】R730;TP18
  • 【被引频次】16
  • 【下载频次】456
节点文献中: 

本文链接的文献网络图示:

本文的引文网络