Latest
  1. Johns Hopkins Bayview tells 3,182 patients an employee put their health data into a public AI tool
  2. China’s AI compute access expected to double in 2027, with US-designed chips about 65 per cent
  3. UK commits £100m to national AI Biosecurity Lab
  4. Moonshot AI releases Kimi K3.1 Pro with 1-million-token context window
  5. Residents in Newport and Cardiff oppose hyperscale datacentres near homes
  6. Study: Grok 4.7 picked Republicans in 92% of forced midterm answers, GPT-6.1 Sol picked Democrats in 97%
  7. Attackers exploiting the PHP flaws hand the break-in to AI agents, Unit 42 says
  8. Elvis Presley’s rightsholders sue Anthropic over training on 274 songs

Latest / Health and life sciences

ResearchHealthFrontierUS UKConfirmed

Google’s AMIE beats primary care doctors in a simulated text-chat diagnosis study

See how this story connects

Source: arXiv: Towards Conversational Diagnostic AI (2401.05654)

Google Research and Google DeepMind posted a preprint on 11 January 2024 describing AMIE (Articulate Medical Intelligence Explorer), a large language model tuned for diagnostic conversations. In a randomised, double-blind crossover study of text consultations with patient actors across 149 case scenarios from Canada, the UK and India, AMIE had higher diagnostic accuracy than 20 primary care physicians and scored better on 28 of 32 axes rated by specialists and 24 of 26 rated by patient actors. The authors said doctors were limited to unfamiliar text chat, which is not usual clinical practice.

Why it matters

Health systems and regulators had controlled evidence that a chatbot could take a history and reach a diagnosis as well as primary care doctors in exam conditions, though not in real clinics.

When
11 Jan 2024
ID
WTA-N-2024-0002
Who
Google Research, Google DeepMind

Summary by wheresthe.ai, from arXiv. Checked against the source on 9 Oct 2026.

Read the original at arXiv

Source copy: download the page as saved on 18 Oct 2026 (PDF). Also held by the Internet Archive.

Next stop on this Storyline: What happened nextTrial finds GPT-4 access did not improve doctors’ diagnoses, but GPT-4 alone scored higher

Cite this story

WTA-N-2024-0002: “Google’s AMIE beats primary care doctors in a simulated text-chat diagnosis study.” wheresthe.ai, 11 Jan 2024. https://wheresthe.ai/d/google-amie-diagnostic-dialogue-study-2024-01/ (source: arXiv: Towards Conversational Diagnostic AI (2401.05654)).

Spotted an error? Email [email protected].