DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI

# DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI
Source: https://arxiv.org/abs/2604.15456
Authors: Zhizheng Wang (https://arxiv.org/search/cs?searchtype=author&query=Wang,+Z), Chih-Hsuan Wei (https://arxiv.org/search/cs?searchtype=author&query=Wei,+C), Joey Chan (https://arxiv.org/search/cs?searchtype=author&query=Chan,+J), Robert Leaman (https://arxiv.org/search/cs?searchtype=author&query=Leaman,+R), Chi-Ping Day (https://arxiv.org/search/cs?searchtype=author&query=Day,+C), Chuan Wu (https://arxiv.org/search/cs?searchtype=author&query=Wu,+C), Mark A Knepper (https://arxiv.org/search/cs?searchtype=author&query=Knepper,+M+A), Antolin Serrano Farias (https://arxiv.org/search/cs?searchtype=author&query=Farias,+A+S), Jordina Rincon-Torroella (https://arxiv.org/search/cs?searchtype=author&query=Rincon-Torroella,+J), Hasan Slika (https://arxiv.org/search/cs?searchtype=author&query=Slika,+H), Betty Tyler (https://arxiv.org/search/cs?searchtype=author&query=Tyler,+B), Ryan Huu-Tuan Nguyen (https://arxiv.org/search/cs?searchtype=author&query=Nguyen,+R+H), Asmita Indurkar (https://arxiv.org/search/cs?searchtype=author&query=Indurkar,+A), Mélanie Hébert (https://arxiv.org/search/cs?searchtype=author&query=H%C3%A9bert,+M), Shubo Tian (https://arxiv.org/search/cs?searchtype=author&query=Tian,+S), Lauren He (https://arxiv.org/search/cs?searchtype=author&query=He,+L), Noor Naffakh (https://arxiv.org/search/cs?searchtype=author&query=Naffakh,+N), Aseem Aseem (https://arxiv.org/search/cs?searchtype=author&query=Aseem,+A), Nicholas Wan (https://arxiv.org/search/cs?searchtype=author&query=Wan,+N), Emily Y Chew (https://arxiv.org/search/cs?searchtype=author&query=Chew,+E+Y), Tiarnan D L Keenan (https://arxiv.org/search/cs?searchtype=author&query=Keenan,+T+D+L), Zhiyong Lu (https://arxiv.org/search/cs?searchtype=author&query=Lu,+Z)

View PDF (https://arxiv.org/pdf/2604.15456)

> Abstract: Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent deep research systems aim to accelerate evidence-grounded scientific discovery by integrating AI agents with multi-hop information retrieval, reasoning, and synthesis. However, most existing systems lack explicit and inspectable criteria for evidence appraisal, creating a risk of compounding errors and making it difficult for researchers and clinicians to assess the reliability of their outputs. In parallel, current benchmarking approaches rarely evaluate performance on complex, real-world medical questions. Here, we introduce DeepER-Med, a Deep Evidence-based Research framework for Medicine with an agentic AI system. DeepER-Med frames deep medical research as an explicit and inspectable workflow of evidence-based generation, consisting of three modules: research planning, agentic collaboration, and evidence synthesis. To support realistic evaluation, we also present DeepER-MedQA, an evidence-grounded dataset comprising 100 expert-level research questions derived from authentic medical research scenarios and curated by a multidisciplinary panel of 11 biomedical experts. Expert manual evaluation demonstrates that DeepER-Med consistently outperforms widely used production-grade platforms across multiple criteria, including the generation of novel scientific insights. We further demonstrate the practical utility of DeepER-Med through eight real-world clinical cases. Human clinician assessment indicates that DeepER-Med's conclusions align with clinical recommendations in seven cases, highlighting its potential for medical research and decision support.

## Submission history

From: Zhizheng Wang [view email (https://arxiv.org/show-email/798f7fe7/2604.15456)] **[v1]** Thu, 16 Apr 2026 18:17:24 UTC (4,720 KB)