Follow-up Question Generation For Enhanced Patient-Provider Conversations

2025-03-21

AI Summary

In asynchronous patient–physician dialogues, clinicians must formulate effective follow-up questions relying solely on static electronic health records (EHRs), posing significant challenges due to information fragmentation and multi-threaded clinical reasoning. Method: This paper proposes FollowupQ, a multi-agent framework that jointly encodes EHR data and patient-generated text, employs diagnosis-hypothesis-guided decoding, and leverages a medical-domain-adapted sequence generation model to produce personalized follow-up questions. Contributions/Results: (1) We introduce the first publicly available asynchronous medical dialogue + EHR paired dataset, annotated with 2,300 expert-crafted follow-up questions; (2) we pioneer a multi-agent collaborative generation paradigm tailored for EHR-constrained settings. Experiments demonstrate performance gains of 17% on real-world data and 5% on synthetic data, alongside a 34% reduction in required clinician follow-up queries—substantially mitigating information fragmentation and multi-threaded inference bottlenecks while improving diagnostic accuracy and consultation efficiency.

Technology Category

• Natural Language Processing: Question Answering
• Multiagent Systems: Adversarial Agents
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Follow-up question generation is an essential feature of dialogue systems as it can reduce conversational ambiguity and enhance modeling complex interactions. Conversational contexts often pose core NLP challenges such as (i) extracting relevant information buried in fragmented data sources, and (ii) modeling parallel thought processes. These two challenges occur frequently in medical dialogue as a doctor asks questions based not only on patient utterances but also their prior EHR data and current diagnostic hypotheses. Asking medical questions in asynchronous conversations compounds these issues as doctors can only rely on static EHR information to motivate follow-up questions. To address these challenges, we introduce FollowupQ, a novel framework for enhancing asynchronous medical conversation. FollowupQ is a multi-agent framework that processes patient messages and EHR data to generate personalized follow-up questions, clarifying patient-reported medical conditions. FollowupQ reduces requisite provider follow-up communications by 34%. It also improves performance by 17% and 5% on real and synthetic data, respectively. We also release the first public dataset of asynchronous medical messages with linked EHR data alongside 2,300 follow-up questions written by clinical experts for the wider NLP research community.

Problem

• Generates personalized medical follow-up questions from patient messages and EHR data
• Reduces conversational ambiguity in asynchronous doctor-patient interactions
• Addresses NLP challenges in fragmented data extraction and parallel thought modeling

Innovation

• Multi-agent framework processes messages and EHR
• Generates personalized follow-up medical questions
• Reduces provider follow-up communications by 34%