In order to bring you the best possible user experience, this site uses Javascript. If you are seeing this message, it is likely that the Javascript option in your browser is disabled. For optimal viewing of this site, please ensure that Javascript is enabled for your browser.
Did you know that your browser is out of date? To get the best experience using our website we recommend that you upgrade to a newer version. Learn more.

ChatGPT – the new kid on the block

Comment by Mark Abela, Sports Cardiology and Exercise Section

Artificial Intelligence (Machine Learning, Deep Learning)
Preventive Cardiology
e-Cardiology and Digital Health
Risk Factors and Prevention

The COVID-19 pandemic was certainly the biggest challenge international healthcare systems faced in recent history. Economic downfall and limited access to medical care paved the way for innovation. Efficiency became more important then ever. Computer science and informatics have substantially contributed towards healthcare outcomes and patient experiences. Digital cardiology is now an evolving specialty in its own right, expected to grow exponentially in the near future. Artificial intelligence (AI) algorithms are quickly becoming an integral component of modern healthcare. AI is certainly helping physicians manage patients better, one only expects AI to become more autonomous.

ChatGPT is the new kid on the block. Gathering worldwide attention in 2022, ChatGPT seems like a reliable platform for patients and clinicians alike. The authors attempted to evaluate ChatGPT with a series of common cardiovascular prevention questions. The AI model appropriately answered 84% of all the questions, an impressive feat. Inappropriate answers could have been attributed to the ChatGPT algorithm version at the time of the study, highlighting an important limitation in even high end AI algorithms.

ChatGPT is certainly promising, but is it ready to take on the challenge of helping patients and physicians? It certainly can be used to address common and simple patient concerns on digital platforms, notably telerehabilitation systems. I would advise being cautious at present. The benefits of such systems should be explored better.

References

Mark Abela commented on this article:

Appropriateness of Cardiovascular Disease Prevention Recommendations Obtained From a Popular Online Chat-Based Artificial Intelligence Model
Ashish Sarraju, et al. JAMA. Published online February 3, 2023. doi:10.1001/jama.2023.1044

Notes to editor

Note: The content of this article reflects the personal opinion of the author/s and is not necessarily the official position of the European Society of Cardiology.