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

ResearchHealthUSConfirmed

Trial finds GPT-4 access did not improve doctors’ diagnoses, but GPT-4 alone scored higher

See how this story connects

Source: JAMA Network Open (doi:10.1001/jamanetworkopen.2024.40969)

A randomised trial led by Stanford researchers, published in JAMA Network Open on 28 October 2024, gave 50 physicians ChatGPT Plus (GPT-4) or conventional resources for up to six clinical vignettes. Diagnostic reasoning scores were 76% with the chatbot and 74% without, a difference that was not significant. GPT-4 working alone scored 16 percentage points higher than the doctors using conventional resources.

Why it matters

Hospitals giving clinicians chatbots had trial evidence that access alone did not raise diagnostic scores, while the model working alone scored higher than unaided doctors.

When
28 Oct 2024
ID
WTA-N-2024-0015
Who
Stanford University, OpenAI

Summary by wheresthe.ai, from JAMA Network Open. Checked against the source on 9 Oct 2026.

Read the original at JAMA Network Open

Source copy: download the page as saved on 21 Oct 2026 (PDF). Also held by the Internet Archive.

Next stop on this Storyline: Led toScience study: OpenAI’s o1 matched or beat physicians at diagnosis on real ER cases

Cite this story

WTA-N-2024-0015: “Trial finds GPT-4 access did not improve doctors’ diagnoses, but GPT-4 alone scored higher.” wheresthe.ai, 28 Oct 2024. https://wheresthe.ai/d/us-jama-llm-diagnostic-reasoning-rct-2024-10/ (source: JAMA Network Open (doi:10.1001/jamanetworkopen.2024.40969)).

Spotted an error? Email [email protected].