2026-10-13T14:45:08Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33828556 2026-09-16T05:30:06Z category_932 portal_316 item_type_3 month_year_09_2026

Data Sheet 1_CDTD-Agent: a retrieval-augmented multi-agent digital health framework for integrated diabetes care: a single-case expert-rated pilot study.docx Jieyi Zhang (5185352) Luqing Wu (24961036) Jielong Wu (17345853) Xiaoming Han (24961039) Lijin Lin (671929) Nengjiang Zhao (12357502) Zhihai Zhang (4974026) Miaona Cai (24961042) Meiqi Chen (9438816) Shuyu Yang (401091) Bo Li (112195) Health Informatics diabetes management large language models (LLMs) multi-agent system retrieval-augmented generation (RAG) traditional Chinese medicine (TCM) Background<p>Diabetes management increasingly requires coordination across Western medicine, traditional Chinese medicine (TCM), and lifestyle-based health management. General-purpose large language models (LLMs) can generate clinical text but may lack reliable source grounding and structured cross-disciplinary reasoning.</p>Methods<p>We developed CDTD-Agent, a retrieval-augmented multi-agent framework that combines a domain-specific knowledge base with an Extract-Retrieve-Reason workflow. The knowledge base included 12 medical textbooks, 8 clinical guidelines, and 183 expert-reviewed diabetes cases. In a blinded single-case pilot evaluation, 30 senior experts rated anonymized recommendations from CDTD-Agent, GPT-4o, DeepSeek-V3.2-Exp, Doubao, and two attending physicians across eight dimensions. Linear mixed-effects models accounted for repeated ratings within evaluators, with Holm correction across eight omnibus tests and global Benjamini-Hochberg correction across 40 focused CDTD-Agent-versus-comparator contrasts. A post hoc backbone-only ablation compared the full framework with Qwen3–235B-A22B using the same case and external prompt without retrieval or role-structured multi-agent processing.</p>Results<p>Significant source effects were detected in all eight dimensions after Holm correction (all adjusted p < 0.001). After global false discovery rate correction, CDTD-Agent received significantly higher ratings than all three general-purpose LLMs in five dimensions: safety, examination appropriateness, Western medicine treatment appropriateness, TCM treatment appropriateness, and evidence adherence. The largest differences occurred in Western medicine treatment appropriateness, where CDTD-Agent scored 4.07 ± 0.94 versus 1.37–1.60 for the general-purpose LLMs (all adjusted p < 0.001). Non-parametric sensitivity analyses agreed with the mixed-effects results for 39 of 40 focused contrasts. In the post hoc ablation, the full framework outperformed the backbone-only condition in seven of eight dimensions after Holm correction; health management was not significantly different (adjusted p = 0.080).</p>Conclusion<p>In this standardized complex T2DM case, CDTD-Agent received favorable expert ratings relative to the evaluated general-purpose LLMs in several clinically important dimensions. These findings are scenario-specific and do not establish generalizable clinical performance or isolate the effects of individual framework components. Multicase, repeated-generation, factorial-ablation, external, and prospective validation is needed before clinical deployment.</p> 2026-09-16T05:30:06Z Dataset Dataset 10.3389/fdgth.2026.1923975.s001 https://figshare.com/articles/dataset/Data_Sheet_1_CDTD-Agent_a_retrieval-augmented_multi-agent_digital_health_framework_for_integrated_diabetes_care_a_single-case_expert-rated_pilot_study_docx/33828556 CC BY 4.0