arXiv cs.AI· Daoyun Wang, Zhicheng Huang, Huaiyuan Sun, Jiaqi Xu, Xiaowei Xu, Zhibo Zheng, Zhongxing Bing, Yuxiao Lin, Yicheng Liang, Chao Gao, Bowen Xue, Kai Zhang, Song Xu, Wanpu Yan, Hui Xia, Lin Li, Xiang Yan, Mu Hu, Qianli Ma, Zhiqiang Xue, Xiaofang Liu, Zhihai Han, Nan Zhang, Chuanhao Tang, Tongmei Zhang, Lan Song, Zhaohui Zhu, Xuan Zeng, Shafei Wu, Hui Guan, Lei Deng, Huaxia Yang, Zeliang Lian, Wubin Sun, Yongxin Wang, Xiaohui Shen, Binlin Wang, Tiantian Gu, Yu Cui, Li Zhang, Shirui Wang, Naixin Liang·· 2 小时前AI 评分42
MedGPT Clinical Explorer：面向复杂肺癌开放性决策的可审计条件化策略框架
An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer
AI 导读
MedGPT Clinical Explorer（MCE）将肺癌的可选路径、决策关键未知项、安全约束与回退方案组织成可审核的条件化策略。在 98 家机构 250 名医生对 100 例病例库中 40 例建立参考、共产生 2,250 份策略的评估中，MCE 辅助策略的 APAS 得分较无辅助高 12.87（95% CI 11.18-14.55），较检索参考高 5.22。
来源：arXiv cs.AI · arxiv.org