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 • Machine learning analysis

Cancer genomics: new ML tool weeds out false positives

A major challenge in cancer genomics is separating meaningful mutations from false positives. A new tool uses machine learning to significantly reduce these errors.

Photo

News • Deep learning-based assessment

AI ‘Sybil’ predicts lung cancer risk from single LDCT scan

A deep learning model was able to predict future lung cancer risk from a single low-dose chest CT (LDCT) scan, according to new research published at the ATS 2025 International Conference.

Photo

News • AI-assisted platelet imaging

Monitoring blood clotting in real-time

Researchers have found a way to observe clotting activity in blood as it happens — without needing invasive procedures. This could open the door to better treatment of coronary artery disease (CAD).

Related products

Subscribe to Newsletter