A Flinders University study finds that vision-enabled AI scribes using video and audio dramatically improve documentation accuracy in medication history interviews.
Key Details
- 1The study combined Google's Gemini model with Ray-Ban Meta smart glasses to create a vision-enabled AI scribe.
- 2In pharmacist-patient medication history simulations, the AI scribe achieved 98% documentation accuracy with video and audio, versus 81% for audio-only.
- 3Capture of critical medication strength and form details rose to 97% with video input, compared to 28% with audio alone.
- 4110 mock interviews involving 10 pharmacists and over 100 medication types were recorded for analysis.
- 5Researchers emphasized the need for clinician review, privacy and data security, and cautious governance before broader adoption.
- 6Published (pre-print) in npj Digital Medicine, study highlights potential improvements in clinical workflow and patient safety.
Why It Matters
Structured, accurate clinical data capture is essential for quality care and reducing administrative burden—a priority in radiology and other specialties. Vision-enabled AI scribes may set the stage for broader adoption of multimodal AI systems that could also benefit radiological documentation and reporting workflows.
Source
EurekAlert
Related News
•EurekAlert
NYU AI Model Improves 5-Year Breast Cancer Risk Prediction via 3D Mammograms
NYU researchers developed an AI model using longitudinal 3D mammograms that outperforms single-scan and 2D-based tools in predicting 5-year breast cancer risk.
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.