two mirrored robot icons on red and blue background

Image source: Adobe Stock/ProstoSvet

News • Battle of the AI large language models

Elicit: A better ChatGPT for medical research?

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. Their findings were published in Hepatology Communications.

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

Masaru Enomoto

“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.” 


Source: Osaka Metropolitan University

08.12.2023

More on the subject:

Related articles

Photo

News • Emergency medicine

Triaging patients: no job for AI (alone)

Overcrowded EDs and the escalating workload of nurses are pressing challenges in emergency medicine. While AI might not solve these problems, it could help staff mitigate them, new research suggests.

Photo

News • Machine learning analysis

‘Two-for-one’ screening uses mammograms to predict heart disease in women

Using AI to help detect one of the leading killers of women worldwide: A new machine learning model can successfully predict heart disease risk in women by analysing mammograms.

Photo

News • AI-supportred tissue engineering

3D bioprinting to solve donor organ shortage

To tackle the shortage of donor organs, researchers have developed a 3D printer that doesn’t just print implantable tissues, it also sees and even co-designs parts of organs.

Related products

Subscribe to Newsletter