Toggle Side Panel
Close search

‘Irredeemable flaws’: $17 billion medical AI firm’s social media attack on Nature study

A Nature Medicine study that found general AIs such as Gemini or Claude outperformed dedicated medical AI software has drawn criticism from OpenEvidence.

Medical AI company OpenEvidence has accused researchers of bias and “irredeemable” methodological failings after a Nature Medicine study concluded general AIs outperformed dedicated clinical AIs on medical questions.

The study compared advanced versions of OpenAI’s ChatGPT, Google’s Gemini, and Anthropic’s Claude with two AIs that draw only from clinical sources: UpToDate Expert AI and OpenEvidence.

Launched in 2022, OpenEvidence has been valued at $17 billion, while Forbes magazine puts the personal wealth of founder and CEO Daniel Nadler at about $11 billion.

In the study, researchers tested the AIs on 500 multiple-choice medical exam questions, formatted as vignettes; a database of 500 clinical scenarios assessed by expert doctors; and 100 real clinical queries (RCQs), with blinded human experts ranking the AI’s clinical advice.

Report

Harassment or bullying behavior
Contains mature or sensitive content
Contains misleading or false information
Contains abusive or derogatory content
Content that breaches the privacy of other individuals
Contains spam, fake content or potential malware

Block Member?

Please confirm you want to block this member.

You will no longer be able to:

  • See blocked member's posts
  • Mention this member in posts
  • Message this member
  • Add this member as a connection

Please note: This action will also remove this member from your connections and send a report to the site admin. Please allow a few minutes for this process to complete.

Report

You have already reported this .