Voice-guided Orchestrated Intelligence for Clinical Evaluation (VOICE): A Voice AI Agent System for Prehospital Stroke Assessment

We developed a voice-driven artificial intelligence (AI) system that guides anyone—from paramedics to family members—through expert-level stroke evaluations using natural conversation, while also enabling smartphone video capture of key examination components for documentation and potential expert review. This addresses a critical gap in emergency care: current stroke recognition by first responders is inconsistent and often inaccurate, with sensitivity for stroke detection as low as 58%, causing life-threatening delays in treatment. Three non-medical volunteers used our AI system to assess ten simulated stroke patients, including cases with likely large vessel occlusion (LVO) strokes and stroke-like conditions, while we measured diagnostic accuracy, completion times, user confidence, and expert physician review of the AI-generated reports. The AI system correctly identified 84% of individual stroke signs and detected 75% of likely LVOs, completing evaluations in just over 6 minutes. Users reported high confidence (median 4.5/5) and ease of use (mean 4.67/5). The system successfully identified 86% of actual strokes but also incorrectly flagged 2 of 3 non-stroke cases as strokes. When an expert physician reviewed the AI reports with videos, they identified the correct diagnosis in 100% of cases, but felt confident enough to make preliminary treatment decisions in only 40% of cases due to observed AI errors including incorrect scoring and false information. While the current system’s limitations necessitate human oversight, ongoing rapid advancements in speech-to-speech AI models suggest that future versions are poised to enable highly accurate assessments. Achieving human-level voice interaction could transform emergency medical care, putting expert-informed assessment capabilities in everyone’s hands.

• Publication year

  2025

• Venue

  2025 Second International Conference on Artificial Intelligence for Medicine, Health and Care (AIxMHC)

• Publication date

  2025-06-25

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1109/AIxMHC65380.2025.00013arXiv 2507.22898
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multimodal generative AI for interpreting 3D medical images and videos

  2025cited by this paper
• Coordinated AI agents for advancing healthcare

  2025cited by this paper
• Transport time as a potential limiting factor for thrombolytic treatment of stroke in Norway

  2025cited by this paper
• An evaluation framework for clinical use of large language models in patient interaction tasks

  2025cited by this paper
• Toward an application of automatic evaluation system for central facial palsy using two simple evaluation indices in emergency medicine

  2024cited by this paper
• Project Aria: A New Tool for Egocentric Multi-Modal AI Research

  2023cited by this paper
• Not so FAST: pre-hospital posterior circulation stroke

  2022cited by this paper
• ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

  2022cited by this paper
• Smartphone App in Stroke Management: A Narrative Updated Review

  2022cited by this paper
• Validation of a shortened FAST-ED algorithm for smartphone app guided stroke triage

  2021cited by this paper
• Characteristics of patients who had a stroke not initially identified during emergency prehospital assessment: a systematic review

  2021cited by this paper
• Assistant

  2021cited by this paper
• Prehospital Triage Strategies for the Transportation of Suspected Stroke Patients in the United States

  2020cited by this paper
• Accuracy of Prehospital Identification of Stroke in a Large Stroke Belt Municipality

  2018cited by this paper
• Accuracy of Emergency Medical Services Dispatcher and Crew Diagnosis of Stroke in Clinical Practice

  2017cited by this paper
• The FAST-ED App: A Smartphone Platform for the Field Triage of Patients With Stroke

  2017cited by this paper
• Field Assessment Stroke Triage for Emergency Destination: A Simple and Accurate Prehospital Scale to Detect Large Vessel Occlusion Strokes

  2016cited by this paper
• Dispatcher Stroke Recognition Using a Stroke Screening Tool: A Systematic Review

  2016cited by this paper
• Development of Smartphone Application That Aids Stroke Screening and Identifying Nearby Acute Stroke Care Hospitals

  2013cited by this paper
• Diagnostic Accuracy of Stroke Referrals From Primary Care, Emergency Room Physicians, and Ambulance Staff Using the Face Arm Speech Test

  2003cited by this paper
• Cincinnati Prehospital Stroke Scale: reproducibility and validity.

  1999cited by this paper

• No citing papers are available for this paper.