cs.CLApr 14, 2026

Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research

Authors: Taehun Kim, Hyeryun Park, Hyeonhoon Lee, Yushin Lee, Kyungsang Kim, Hyung-Chul Lee

Organizations: Infmedix, Co., Ltd., Seoul, Republic of Korea. · Department of Transdisciplinary Studies, Seoul National University, Seoul, Republic of Korea. · Healthcare AI Research Institute, Seoul National University Hospital, Seoul, Republic of Korea. · Department of Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea. · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Clinical data-driven research requires clinical expertise, programming skills, access to patient data, and extensive documentation, creating barriers and slowing the pace for clinicians and external researchers. To address this, we developed the Clinical Agentic Research Intelligence System (CARIS) that automates the workflow: research planning, literature search, cohort construction, Institutional Review Board (IRB) documentation, Vibe Machine Learning (ML), and report generation, with human-in-the-loop refinement. CARIS integrates Large Language Models (LLMs) with modular tools through the Model Context Protocol (MCP), enabling natural language-driven research without coding while allowing users to access only outputs. We evaluated CARIS on three heterogeneous datasets with distinct clinical tasks, where it completed planning and IRB documentation within four iterations, supported Vibe ML, and generated reports, achieving 96% completeness in LLM-based evaluation and 82% in human evaluation. CARIS demonstrates potential to reduce documentation burden and technical barriers, accelerating data-driven clinical research across public and private data environments.

Figures & tables

Figure 1: Overview of Clinical Agentic Research Intelligence System (CARIS). Given a user intent, CARIS autonomously executes a multi-step clinical research workflow by interacting with agents, heterogeneous datasets, and various tools, while allowing user intervention. Users do not have direct access to the file or DB systems.
Figure 2: Overview of the clinical research workflow. (A) User interaction to iteratively generate and refine a structured research plan. (B) Keyword extraction using the PIMO framework and retrieval of relevant PubMed literature. (C) Database exploration, cohort definition, query execution, and dataset generation. (D) Iterative generation and refinement of IRB document sections through user interaction. (E) Data analysis, preprocessing, model training, evaluation, and visualization, followed by the automated generation of a clinical ML report.
DatasetData sourceData formatPrediction taskNumber of instances
MIMIC-IVBeth Israel Deaconess Medical CenterRDBICU readmission83,101
INSPIRESeoul National University HospitalRDBPostoperative AKI100,474
SyntheticMassSynthetic Massachusetts patient dataOMOP-CDMPrediabetes-to-diabetes2,556
Table 1: Summary of datasets and target tasks. RDB: Relational Database.
Figure 3: Revision patterns in IRB document generation. (A) Sections revised across iterations. Each dot represents a revision, with colors indicating section types. (B) Distribution of revision items per section. Numbers inside wedges indicate item counts, and percentages indicate their proportions.
Figure 4: Radar chart of IRB document evaluation results across four criteria. Each axis represents the pass rate (%) for each criteria assessed across three tasks.
Task (dataset)ModelFeature selection(#)AUROCPrecisionRecallF1
ICU readmission (MIMIC)XGBoostMI + RFE (55)71.50%73.24%51.24%49.97%
XGBoostSelectKBest MI (37)71.09%68.42%50.92%49.38%
Preoperative AKI (INSPIRE)LightGBMRFE (31)85.77%80.00%53.88%56.24%
LightGBMBoruta with SHAP (30)85.61%78.64%53.80%56.08%
Prediabetes-to-diabetes (SyntheticMass)XGBoostLLM features + HDL (10)88.58%74.79%68.62%70.72%
XGBoostLLM features + HDL + TG (11)88.03%70.98%67.04%68.50%
Table 2: Performance comparison of the top two ML models for each task under different feature selection methods. RF: Random Forest; MI: Mutual Information; RFE: Recursive Feature Elimination; TG: Triglycerides.
Figure 5: Checklist coverage of the final report across nine criteria. (A) Evaluation results by Claude Sonnet. (B) Evaluation results by human evaluator. Each axis represents criteria with checklist item count in parentheses. The dashed line indicates the average across all three reports.
Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

AgentTool nameDescription
Research planningget_title_answerGet the user’s research topic and refine it into a title
 get_titleGenerate questions to clarify the research from the title
 stream_generatorCollects user responses to the generated questions
 get_querysGenerates content for each research plan section
 get_update_answerUpdates generated content based on user revision requests
 get_pubmed_searchSummarizes proposed research, creates search keywords, evaluates the searched papers
Appendix
Table 1: Key Tools for Clinical Research Process Automation
Figure 1: User interface to interact with LLMs and modular MCP tools.
Figure 2: Revision form used to capture evaluator feedback, along with results across three tasks.
Figure 3: Evaluation form used to assess the final IRB document.
Figure 4: Evaluation results on the final IRB document across tasks.
Figure 5: IRB document evaluation results on the MIMIC ICU readmission prediction task.
Figure 6: IRB document evaluation results on the INSPIRE preoperative AKI prediction task.
Figure 7: IRB document evaluation results on the SyntheticMass ICU readmission prediction task.
Figure 8: Evaluation form used to assess the generated IRB document.
Figure 9: Claude Sonnet evaluation results on the final report (section 1-3) across tasks.
Figure 10: Claude Sonnet Evaluation results on the final report (section 4-6) across tasks.
Figure 11: Claude Sonnet evaluation results on the MIMIC ICU readmission prediction final report.
Figure 12: Claude Sonnet evaluation results on the INSPIRE preoperative AKI prediction final report.
Figure 13: Claude Sonnet evaluation results on SyntheticMass ICU readmission prediction final report.
Figure 14: Human evaluation results on the final report (section 1-3) across tasks.
Figure 15: Human evaluation results on the final report (section 4-6) across tasks.
Figure 16: Human evaluation results on the MIMIC ICU readmission prediction final report.
Figure 17: Human evaluation results on the INSPIRE preoperative AKI prediction final report.
Figure 18: Human evaluation results on SyntheticMass ICU readmission prediction final report.
More in this topic

AI-Assisted Scientific Research

AI-assisted scientific research uses machine learning and AI agents to support discovery, analysis, experimentation, and scientific communication.

See all 253 papers

Explore similar work

CardsList

  1. Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work

    Apr 26, 2026Zihao Wu, Steven Xu, Bowen Chen +8HealthcareAI-Assisted Scientific Research

    School of Computing University of Georgia Athens GA 30602 USA · Department of Biomedical Engineering New Jersey Institute of Technology Newark NJ 07102 USA · Department of Computer Science and Engineering University of Texas at Arlington Arlington TX 76019 USA

  2. Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks

    Jul 23, 2026Mack Nixon, Liam Wright, Yevgeniya Kovalchuk +4AI Agent BenchmarksOpen-Weight Language Models

    Centre for Advanced Research Computing, University College London, London, UK · Centre for Longitudinal Studies, University College London, London, UK · UK Longitudinal Linkage Collaboration, University of Bristol, Bristol, UK

  3. CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents

    May 10, 2026Timothy Ossowski, Xinchi Liu, Danyal Maqbool +6HealthcareLLM Agent Skill Learning

    University of Wisconsin–Madison · 2Microsoft Research