GPT-4 beats human doctors in medical soft skills

Researchers evaluated how well AI models GPT-4 and ChatGPT perform on the US Medical Licensing Examination questions focused on soft skills like judgment and empathy. GPT-4 outperformed both ChatGPT and human test-takers, answering 90% of questions correctly, while ChatGPT had a 62.5% accuracy rate.

BI-765179 by Boehringer Ingelheim International for Cutaneous Squamous Cell Carcinoma (cSCC): Likelihood of Approval

Share this article GlobalData tracks drug-specific phase transition and likelihood of approval scores, in addition to indication benchmarks based off 18 years of historical drug

December 26, 2023

Does DIY still have a place in diabetes care?

When Dana Lewis built her first artificial pancreas in 2014, she — and millions of other people with type 1 diabetes — didn’t have another

June 24, 2023

Amgen gives first glimpse at PRMT5 inhibitor, days after Bristol Myers put a $1B promise on the target

In a first look at Amgen’s experimental PRMT5 inhibitor, roughly 16% of patients with various cancers saw their tumors shrink by at least 30%, equating

October 14, 2023

Supercharge Your Portfolio with Future Health Stocks!

Join us for Profitable Insights & Expert Tips!

With expert analysis, comprehensive market coverage, and actionable insights, our newsletter equips you with the knowledge & tools necessary to make informed decisions & maximize your potential returns in the dynamic world of future health stocks.