PulseAugur
EN
LIVE 16:02:50

Google DeepMind's AI co-clinician shows promise in medical decision support

By PulseAugur Editorial · [6 sources] ·

Google DeepMind has introduced an AI co-clinician research initiative aimed at assisting healthcare professionals and patients. This system utilizes live video and audio to analyze physical symptoms in real-time, such as a patient's gait or breathing. In testing, the AI demonstrated strong performance, matching or exceeding physicians in 68 out of 140 assessed areas, including triage, and made zero critical errors in 97 out of 98 primary care queries under the NOHARM safety framework. AI

IMPACT Potential to augment clinical decision-making and improve patient care through multimodal AI analysis.

RANK_REASON Research initiative announcement with testing results from a major AI lab.

Read on X — Google DeepMind →

AI-generated summary · Google Gemini · from 6 sources. How we write summaries →

Google DeepMind's AI co-clinician shows promise in medical decision support

COVERAGE [6]

  1. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    We’re advancing this research with academics and institutions globally, and will gradually expand our clinician-facing trusted tester program to additional site

    We’re advancing this research with academics and institutions globally, and will gradually expand our clinician-facing trusted tester program to additional sites - to understand more perspectives of health workers and patients worldwide. Find out more → https://t.co/c1dA6iS166 h…

  2. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    To keep patient safety at the forefront, the system also runs on a dual agent architecture.

    To keep patient safety at the forefront, the system also runs on a dual agent architecture. A built-in "Planner" continuously monitors the conversation verifying that the "Talker" agent stays within safe clinical boundaries. https://t.co/X40w7h4hHo

  3. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    In testing, AI co-clinician matched or outperformed physicians in 68 out of 140 assessed areas, including triage.

    In testing, AI co-clinician matched or outperformed physicians in 68 out of 140 assessed areas, including triage. Yet humans were easily better at spotting crucial red flags and guiding physical exams - showing how these tools could augment clinical judgment. See the benchmarks …

  4. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    The system uses live video and audio to process physical symptoms in real-time. This means it could analyze a patient's walk, listen to their breathing, or look

    The system uses live video and audio to process physical symptoms in real-time. This means it could analyze a patient's walk, listen to their breathing, or look at how a rash is appearing. Alongside physicians from @Harvardmed and @StanfordMed, we created a simulation study with…

  5. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    Our research goal for AI co-clinician is to support medical decision making with high-quality evidence.

    Our research goal for AI co-clinician is to support medical decision making with high-quality evidence. We tested the system while adapting the NOHARM safety framework, and found it made zero critical errors in 97 of 98 primary care queries - outperforming comparable systems in …

  6. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    AI co-clinician is our new research initiative to help explore how multimodal agents could better support healthcare workers and patients. 🩺

    AI co-clinician is our new research initiative to help explore how multimodal agents could better support healthcare workers and patients. 🩺 Here’s a snapshot of our progress 🧵 https://t.co/7NbhQRzotE

RELATED ENTITIES

RELATED TOPICS