Proactive Knowledge Inquiry in Doctor-Patient Dialogue: Stateful Extraction, Belief Updating, and Path-Aware Action Planning

2026-03-18

AI Summary

This work proposes a paradigm shift in electronic health record (EHR) construction by framing medical documentation as an active, inquiry-driven dialogue process rather than passive post-consultation transcription. Viewing EHR generation as knowledge acquisition in a partially observable environment, the approach integrates stateful information extraction, sequential belief updating, gap-aware modeling, and lightweight POMDP-based action planning to dynamically produce structured records. Evaluated on standard multi-turn dialogues and a 300-query benchmark, the method achieves 83.3% coverage, 80.0% risk recall, and 81.4% structural completeness, significantly outperforming baseline systems in reducing redundancy while effectively identifying known information, missing elements, uncertainties, and next-step actions during clinical conversations.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Information Extraction
• Machine Learning: Active Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Most automated electronic medical record (EMR) pipelines remain output-oriented: they transcribe, extract, and summarize after the consultation, but they do not explicitly model what is already known, what is still missing, which uncertainty matters most, or what question or recommendation should come next. We formulate doctor-patient dialogue as a proactive knowledge-inquiry problem under partial observability. The proposed framework combines stateful extraction, sequential belief updating, gap-aware state modeling, hybrid retrieval over objectified medical knowledge, and a POMDP-lite action planner. Instead of treating the EMR as the only target artifact, the framework treats documentation as the structured projection of an ongoing inquiry loop. To make the formulation concrete, we report a controlled pilot evaluation on ten standardized multi-turn dialogues together with a 300-query retrieval benchmark aggregated across dialogues. On this pilot protocol, the full framework reaches 83.3% coverage, 80.0% risk recall, 81.4% structural completeness, and lower redundancy than the chunk-only and template-heavy interactive baselines. These pilot results do not establish clinical generalization; rather, they suggest that proactive inquiry may be methodologically interesting under tightly controlled conditions and can be viewed as a conceptually appealing formulation worth further investigation for dialogue-based EMR generation. This work should be read as a pilot concept demonstration under a controlled simulated setting rather than as evidence of clinical deployment readiness. No implication of clinical deployment readiness, clinical safety, or real-world clinical utility should be inferred from this pilot protocol.

Problem

• Proactive Knowledge Inquiry
• Doctor-Patient Dialogue
• Electronic Medical Record
• Partial Observability
• Information Gap

Innovation

• proactive knowledge inquiry
• stateful extraction
• belief updating
• POMDP-lite planning
• gap-aware modeling