In contrast, the sources used by ChatGPT-4 were 90% academic, with the remaining FAQs being answered using a commercial source; however, although ChatGPT-4 used a greater proportion of academic resources, this difference failed to reach statistical significance ( P = .14).
← all excerpts
Understanding How ChatGPT May Become a Clinical Administrative Tool Through an Investigation on the Ability to Answer Common Patient Questions Concerning Ulnar Collateral Ligament Injuries.
1
0.1400
0.1400