Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian

2025-07-15

AI Summary

In Romanian telemedicine, written communication quality depends critically on linguistic expressiveness—not merely clinical accuracy—yet existing solutions lack robust, low-resource–adapted support. Method: This paper introduces the first multi-agent large language model (LLM) system tailored to low-resource medical settings. Built on the DSPy framework, it automatically optimizes prompts and orchestrates three open-weight LLM agents to perform real-time, interpretable assessment and rewriting of physician responses across 17 human-centered dimensions—including empathy, clarity, and comprehensibility. Contribution/Results: It establishes the first Romanian-language medical multi-agent collaboration architecture; implements a lightweight, fine-grained, and interpretable feedback mechanism; and was deployed in a live healthcare platform with 41 physicians. Evaluation shows statistically significant improvements in both patient satisfaction and response quality, marking the first production-ready LLM-assisted clinician–patient communication system in Romania.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Text-based telemedicine has become increasingly common, yet the quality of medical advice in doctor-patient interactions is often judged more on how advice is communicated rather than its clinical accuracy. To address this, we introduce Dr.Copilot , a multi-agent large language model (LLM) system that supports Romanian-speaking doctors by evaluating and enhancing the presentation quality of their written responses. Rather than assessing medical correctness, Dr.Copilot provides feedback along 17 interpretable axes. The system comprises of three LLM agents with prompts automatically optimized via DSPy. Designed with low-resource Romanian data and deployed using open-weight models, it delivers real-time specific feedback to doctors within a telemedicine platform. Empirical evaluations and live deployment with 41 doctors show measurable improvements in user reviews and response quality, marking one of the first real-world deployments of LLMs in Romanian medical settings.

Problem

• Improving Romanian doctor-patient text communication quality
• Enhancing presentation of medical advice, not clinical accuracy
• Real-time feedback for doctors in telemedicine platforms

Innovation

• Multi-agent LLM system for Romanian doctors
• Feedback on 17 interpretable communication axes
• Open-weight models optimized via DSPy