13 Dec AI Has Ability To Speed Up Medical Literature Searches, But Not All Information Reliable

MedicalResearch.com Interview with:
Prof. Enomoto, Masaru
Department of Hepatology
Graduate School of Medicine
Osaka Metropolitan University
Osaka, Japan

MedicalResearch.com: What is the background for this study?

Response: This research was conceived out of the use of generative AI drawing upon past experience in selecting a large amount of literature over an extended amount of time. In recent years, generative AI, such as ChatGPT, has gained attention and is being used in various fields, including information gathering and idea generation.

In the medical field in particular, it is challenging to gather pertinent data as the volume of information proliferates on a daily basis, so there is a need to improve the efficiency of information collection.

MedicalResearch.com: What are the main findings?

Response:  The research group focused on generative AI as an information-gathering tool in the medical field and examined whether it could be used to search for the literature, which takes up an enormous amount of time when writing papers. In this study, identical clinical questions and literature selection criteria were input into both generative AIs; ChatGPT and Elicit.

As a result, many of the references suggested by ChatGPT were fictitious, whereas Elicit suggested multiple references in a matter of minutes with the same degree of accuracy typically achieved by a researcher’s manual selection. 

MedicalResearch.com: What should readers take away from your report?

Response: The results of this research suggest that generative AI is likely to be useful in improving the efficiency of medical information collection. It is advisable to be aware that the performance of generative AI is still in its developmental stage, and that not all information is necessarily reliable.

MedicalResearch.com: What recommendations do you have for future research as a results of this study?

Response: Access to medical information using this research method is still in its infancy, so we should exercise caution and be aware that the information may not be accurate or up-to-date. However, ChatGPT and other generative AIs are evolving and are expected to be powerful tools for efficient collection of medical information in the future.

Citation: Enomoto, Masaru1; Tseng, Cheng-Hao2; Hsu, Yao-Chun2; Thuy, Le Thi Thanh1; Nguyen, Mindie H.3,4. Collaborating with AI in literature search—An important frontier. Hepatology Communications 7(12):e0336, December 2023. | DOI: 10.1097/HC9.0000000000000336

The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition.

Some links may be sponsored. Products are not endorsed.

Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.

Last Updated on December 13, 2023 by Marie Benz MD FAAD