AI Insight
Researchers developed a privacy-preserving conversational system that allows clinicians to perform statistical analysis using natural language commands instead of coding, while keeping sensitive patient data stored locally. The system uses an AI agent (DeepSeek-Reasoner) hosted remotely to interpret requests and generate R code, which executes only on the local machine without transmitting raw patient data to the cloud. The approach was validated by successfully replicating a published study on metabolic dysfunction-associated steatotic liver disease entirely through natural-language dialogue.
Why it matters
This framework addresses two major barriers in clinical research: the technical programming skills required for data analysis and the privacy risks of cloud-based AI systems accessing sensitive health records. By enabling clinicians without coding experience to conduct rigorous statistical analyses while maintaining complete data privacy, it could democratize data-driven clinical research and accelerate medical discoveries.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Background Clinical data analysis typically requires statistical programming skills, whereas cloud-based artificial intelligence (AI) agents risk exposing sensitive patient records. We developed and functionally validated a privacy-preserving, zero-code conversational statistical analysis framework that translates natural-language clinical research requests into executable R workflows while strictly retaining raw patient data within local computing environments. Methods Orchestrated by the n8n engine, the system integrates the DeepSeek-Reasoner model with a Pinecone vector database for retrieval-augmented generation (RAG), grounding statistical selection in curated biostatistical guidance and R templates. Core functionalities include data schema perception, interactive data cleaning, requirements refinement, and local R code execution via a controlled command-line interface. System performance was evaluated by replicating a published prognostic model study on metabolic dysfunction-associated steatotic liver disease (MASLD). Findings All core analytical workflows, including data cleaning, multivariable Cox proportional hazards modeling, model diagnostics, and publication-ready tables and figures (e.g., baseline characteristics, Schoenfeld residuals, receiver operating characteristic curves, and forest plots), were executed solely through natural-language dialogues without manual coding. The external large language model actively clarified analytical prompts while receiving zero row-level patient data. Interpretation Decoupling remote cloud reasoning from local code execution lowers the technical threshold for clinicians conducting data-driven research while safeguarding data privacy. This architecture provides a practical, scalable, and reproducible framework for converting natural-language clinical questions into executable statistical workflows. Funding National Natural Science Foundation of China (82473291), Shaanxi Province "Three Qin Scholars" Innovation Team Project (2023001), and Fundamental Research Funds for the Central Universities (xtr062023003).