Xiangmei Yao
Xiangmei Yao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Liuyang Yang
Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Kunming, China
2 shared publications - Liyu Shan
The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Peking University Cancer Hospital Yunnan, Kunming, Yunnan, China
2 shared publications - Renbin Zhao
Department of Hematology, The First People’s Hospital of Yunnan Province, Affiliated Hospital of Kunming University of Science and Technology, Kunming, China
2 shared publications - Shuai Feng
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
2 shared publications - Yajie Wang
Fudan University
2 shared publications - Zengzheng Li
Department of Hematology, The First People’s Hospital of Yunnan Province, Affiliated Hospital of Kunming University of Science and Technology, Kunming, China
2 shared publications
Latest Publications
- Open Access
- 15 September 2026
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 12, e103545
AI Agents for Multimodal Oncology Diagnosis: Toward Transparent and Traceable Clinical Decision Support
Cancer diagnosis depends on data from radiology, digital pathology, molecular profiling, laboratory testing, and longitudinal clinical records. AI performs well in selected tasks, but most systems remain narrow and disconnected from the iterative reasoning required in oncology. This Viewpoint defines an AI agent as a feedback-driven system that maintains task state, selects among governed tools, observes results, and revises its plan under explicit safety constraints. This definition separates agents from multimodal foundation models, retrieval-augmented generation, and fixed workflow automation. We organize the discussion across multimodal data collection, preprocessing, fusion and representation learning, and diagnostic decision support. We distinguished agent-level evidence, component- or infrastructure-level evidence, and prospective propositions throughout. Clinical translation will require resilient failure handling, guideline version control, prospective evaluation, computational and workflow feasibility, and clinician authority over final decisions. The near-term opportunity is therefore transparent and traceable clinical decision support rather than autonomous cancer diagnosis.
- 15 September 2026
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 12, e103545
Open AccessAI Agents for Multimodal Oncology Diagnosis: Toward Transparent and Traceable Clinical Decision Support
Cancer diagnosis depends on data from radiology, digital pathology, molecular profiling, laboratory testing, and longitudinal clinical records. AI performs well in selected tasks, but most systems remain narrow and disconnected from the iterative reasoning required in oncology. This Viewpoint defines an AI agent as a feedback-driven system that maintains task state, selects among governed tools, observes results, and revises its plan under explicit safety constraints. This definition separates agents from multimodal foundation models, retrieval-augmented generation, and fixed workflow automation. We organize the discussion across multimodal data collection, preprocessing, fusion and representation learning, and diagnostic decision support. We distinguished agent-level evidence, component- or infrastructure-level evidence, and prospective propositions throughout. Clinical translation will require resilient failure handling, guideline version control, prospective evaluation, computational and workflow feasibility, and clinician authority over final decisions. The near-term opportunity is therefore transparent and traceable clinical decision support rather than autonomous cancer diagnosis.
- Open Access
- 4 June 2026
- Published by JMIR Publications Inc. in JMIR Preprints
AI Agents for Multimodal Oncology Diagnosis: Toward Transparent and Traceable Clinical Decision Support (Preprint)
UNSTRUCTURED Cancer diagnosis depends on data from radiology, digital pathology, molecular profiling, laboratory testing, and longitudinal clinical records. AI performs well in selected tasks, but most systems remain narrow and disconnected from the iterative reasoning required in oncology. This Viewpoint defines an AI agent as a feedback-driven system that maintains task state, selects among governed tools, observes results, and revises its plan under explicit safety constraints. This definition separates agents from multimodal foundation models, retrieval-augmented generation, and fixed workflow automation. We organize the discussion across multimodal data collection, preprocessing, fusion and representation learning, and diagnostic decision support. We distinguished agent-level evidence, component- or infrastructure-level evidence, and prospective propositions throughout. Clinical translation will require resilient failure handling, guideline version control, prospective evaluation, computational and workflow feasibility, and clinician authority over final decisions. The near-term opportunity is therefore transparent and traceable clinical decision support rather than autonomous cancer diagnosis.
- 4 June 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAI Agents for Multimodal Oncology Diagnosis: Toward Transparent and Traceable Clinical Decision Support (Preprint)
UNSTRUCTURED Cancer diagnosis depends on data from radiology, digital pathology, molecular profiling, laboratory testing, and longitudinal clinical records. AI performs well in selected tasks, but most systems remain narrow and disconnected from the iterative reasoning required in oncology. This Viewpoint defines an AI agent as a feedback-driven system that maintains task state, selects among governed tools, observes results, and revises its plan under explicit safety constraints. This definition separates agents from multimodal foundation models, retrieval-augmented generation, and fixed workflow automation. We organize the discussion across multimodal data collection, preprocessing, fusion and representation learning, and diagnostic decision support. We distinguished agent-level evidence, component- or infrastructure-level evidence, and prospective propositions throughout. Clinical translation will require resilient failure handling, guideline version control, prospective evaluation, computational and workflow feasibility, and clinician authority over final decisions. The near-term opportunity is therefore transparent and traceable clinical decision support rather than autonomous cancer diagnosis.