Researchers have developed an on-device AI system designed to assist in breast cancer multidisciplinary team meetings. This system utilizes open-source Automatic Speech Recognition (ASR) and Large Language Models (LLMs) to transcribe patient discussions, structure clinical information, and generate treatment recommendations based on established guidelines. The AI pipeline operates entirely on local hardware, ensuring patient data privacy and compliance with institutional infrastructure requirements. Evaluations showed improved transcription accuracy and more accurate identification of interventions compared to a cloud-based comparator, with stakeholders identifying automated documentation and decision support as key applications, while also noting challenges in workflow integration and clinician trust. AI
IMPACT This development demonstrates the feasibility of privacy-preserving, on-device AI for clinical decision support, potentially improving efficiency and quality in medical team meetings.
RANK_REASON The cluster contains a research paper detailing the development and evaluation of a novel AI system for a specific medical application. [lever_c_demoted from research: ic=1 ai=1.0]
- Breast Cancer
- Edge AI
- Large Language Models
- MedGemma-RAG
- National Institute for Health and Care Excellence
- NVIDIA Jetson AGX Orin
- Whisper large-v3
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
