New! Sign up for our free email newsletter.
Science News
from research organizations

Battle of the AIs in medical research: ChatGPT vs Elicit

Date:
December 9, 2023
Source:
Osaka Metropolitan University
Summary:
A research team has focused on generative AI as an information-gathering tool in the medical field. The results showed that one of the generative AIs suggested mostly fictitious references, while the other suggested multiple references with the same level of accuracy as the researchers. It is advised to use different generative AIs depending on the type of information needed.
Share:
FULL STORY

The use of generative AI in literature search suggests the possibility of efficiently collecting a vast amount of medical information, provided that users are well aware that the performance of generative AI is still in its infancy and that not all information presented is necessarily reliable. It is advised to use different generative AIs depending on the type of information needed.

Can AI save us from the arduous and time-consuming task of academic research collection? An international team of researchers investigated the credibility and efficiency of generative AI as an information-gathering tool in the medical field.

The research team, led by Professor Masaru Enomoto of the Graduate School of Medicine at Osaka Metropolitan University, fed identical clinical questions and literature selection criteria to two generative AIs; ChatGPT and Elicit. The results showed that while ChatGPT suggested fictitious articles, Elicit was efficient, suggesting multiple references within a few minutes with the same level of accuracy as the researchers.

"This research was conceived out of our experience with managing vast amounts of medical literature over long periods of time. Access to information using generative AI is still in its infancy, so we need to exercise caution as the current information is not accurate or up-to-date." Said Dr. Enomoto. "However, ChatGPT and other generative AIs are constantly evolving and are expected to revolutionize the field of medical research in the future."

Their findings were published in Hepatology Communications.


Story Source:

Materials provided by Osaka Metropolitan University. Note: Content may be edited for style and length.


Journal Reference:

  1. Masaru Enomoto, Cheng-Hao Tseng, Yao-Chun Hsu, Le Thi Thanh Thuy, Mindie H. Nguyen. Collaborating with AI in literature search—An important frontier. Hepatology Communications, 2023; 7 (12) DOI: 10.1097/HC9.0000000000000336

Cite This Page:

Osaka Metropolitan University. "Battle of the AIs in medical research: ChatGPT vs Elicit." ScienceDaily. ScienceDaily, 9 December 2023. <www.sciencedaily.com/releases/2023/12/231209010034.htm>.
Osaka Metropolitan University. (2023, December 9). Battle of the AIs in medical research: ChatGPT vs Elicit. ScienceDaily. Retrieved March 2, 2024 from www.sciencedaily.com/releases/2023/12/231209010034.htm
Osaka Metropolitan University. "Battle of the AIs in medical research: ChatGPT vs Elicit." ScienceDaily. www.sciencedaily.com/releases/2023/12/231209010034.htm (accessed March 2, 2024).

Explore More
from ScienceDaily

RELATED STORIES