DocCHA: Towards LLM-Augmented Interactive Online diagnosis System

2025-07-10

AI Summary

Current conversational health assistants (CHAs) rely on large language models (LLMs) but lack adaptive multi-turn reasoning, dynamic symptom clarification, and decision interpretability—limiting their ability to support structured clinical diagnostic interactions. This paper proposes a modular, diagnosis-oriented interactive system integrating a confidence-aware dynamic reasoning mechanism to jointly optimize symptom elicitation, medical history modeling, and causal graph construction. The system ensures efficiency and transparency in multilingual and resource-constrained settings. Key contributions include: (i) an interpretable, progressive reasoning framework that incrementally refines diagnostic hypotheses; and (ii) joint modeling of confidence-guided symptom recall and causal relationships. Evaluated on a real-world Chinese clinical consultation dataset, our approach improves diagnostic accuracy by 5.18% and symptom recall rate by over 30%, with only marginal increases in dialogue turns.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• 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: User modeling and simulation for interactive and conversational systems

Abstract

Despite the impressive capabilities of Large Language Models (LLMs), existing Conversational Health Agents (CHAs) remain static and brittle, incapable of adaptive multi-turn reasoning, symptom clarification, or transparent decision-making. This hinders their real-world applicability in clinical diagnosis, where iterative and structured dialogue is essential. We propose DocCHA, a confidence-aware, modular framework that emulates clinical reasoning by decomposing the diagnostic process into three stages: (1) symptom elicitation, (2) history acquisition, and (3) causal graph construction. Each module uses interpretable confidence scores to guide adaptive questioning, prioritize informative clarifications, and refine weak reasoning links. Evaluated on two real-world Chinese consultation datasets (IMCS21, DX), DocCHA consistently outperforms strong prompting-based LLM baselines (GPT-3.5, GPT-4o, LLaMA-3), achieving up to 5.18 percent higher diagnostic accuracy and over 30 percent improvement in symptom recall, with only modest increase in dialogue turns. These results demonstrate the effectiveness of DocCHA in enabling structured, transparent, and efficient diagnostic conversations -- paving the way for trustworthy LLM-powered clinical assistants in multilingual and resource-constrained settings.

Problem

• Enhancing adaptive multi-turn reasoning in health diagnosis
• Improving symptom clarification and decision transparency
• Boosting diagnostic accuracy and symptom recall efficiency

Innovation

• Modular framework emulating clinical reasoning stages
• Interpretable confidence scores guide adaptive questioning
• Causal graph construction refines weak reasoning links