Towards Conversational Patient History-Taking: Voice-Interactive AI Agents for Pre-visit Dementia Diagnostic Interviews

2026-07-20 · Source: Paper Index on ACL Anthology · Field: Health & Wellbeing — Medical Devices & Health Technology, Clinical Care & Medical Practice, Artificial Intelligence & Machine Learning · Depth: Expert, medium

Summary

An LLM-based voice-interactive conversational system has been developed for semi-structured diagnostic interviews. It targets older adults suspected of Alzheimer's disease and related dementias (ADRD). The system features conditional conversation branching using specialist-developed scripts. It also includes interaction adaptations tailored for older adults. A within-subjects study with 30 participants from a cognitive neurology clinic compared two LLM prompting strategies. Findings show that prompting strategy influences conversational dynamics and symptom coverage. High sensitivity scores and positive user experience ratings demonstrate the system's clinical potential for scalable, patient-centered history-taking in ADRD care.

Key takeaway

For AI Scientists developing healthcare applications, this research suggests voice-interactive LLM agents can streamline patient history-taking for conditions like ADRD. You should prioritize designing systems with adaptable conversation branching and user experience considerations, especially for specific demographics. Experimenting with different LLM prompting strategies is crucial to optimize conversational flow and comprehensive symptom elicitation, enhancing diagnostic efficiency.

Key insights

LLM-based voice agents can effectively conduct dementia diagnostic interviews with high sensitivity and positive user experience.

Principles

• Prompting strategy impacts dialogue.
• Tailored interactions improve user experience.
• AI can scale patient history-taking.

Method

The system uses conditional conversation branching over specialist-developed scripts. It compares two LLM prompting strategies through dialogue analysis, user experience assessment, and symptom elicitation evaluation.

In practice

• Implement conditional branching.
• Adapt UI for older adults.
• Test multiple prompting strategies.

Topics

• Conversational AI
• LLM Agents
• Dementia Diagnosis
• Patient History-Taking
• Voice Interaction
• Clinical Applications

Best for: AI Scientist, NLP Engineer, Research Scientist

Related on AIssential

• Exploring the feasibility of conversational diagnostic AI in a real-world clinical study — Supervised conversational AI for pre-visit history taking is feasible, safe, and well-received by patients and clinicians.
• Listening Between the Lines: Joint Learning of ASR Embeddings and LLM-Augmented Linguistics for Dementia Detection — Jointly learning ASR embeddings and LLM-augmented linguistics significantly improves dementia detection from speech.
• SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills — SocialWise offers scalable, LLM-agentic conversation therapy for ASD, providing instant, structured feedback via a browser-based platform.
• From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members — LLM-generated summaries for remote family members require context-aware narratives beyond raw data to be helpful and trusted.
• SymptomAI: Towards a conversational AI agent for everyday symptom assessment — Conversational AI can achieve clinician-preferred and more accurate differential diagnoses in real-world symptom assessment.
• Can AI Chatbots Reason Like Doctors? — Large language models demonstrate potential in clinical reasoning, but require careful integration and standardized evaluation in medical workflows.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.