Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content

Table 4 Concordance between ChatGPT and expert preoperative assessment

From: The performance of ChatGPT in day surgery and pre-anesthesia risk assessment: a case-control study of 150 simulated patient presentations

ASA

ChatGPT n (%)

Expert n (%)

 

I

10 (6.7)

28 (18.7)

Mann-Whitney U-test/P 12,548.00/P = 0.064, > 0.05

II

66 (44.0)

58 (38.7)

III

63 (42.0)

52 (34.7)

IV

10 (6.7)

12 (8.0)

V

1 (0.7)

0 (0.0)

Conclusion

 Day surgery can be performed

76 (50.7)

55 (36.7)

χ2/P 6.761/P = 0.034, < 0.05

 Needs further treatment and evaluation

56 (37.3)

66 (44.0)

 Day surgery is not recommended

18 (12.0)

29 (9.3)

Back to article page

Perioperative Medicine

ISSN: 2047-0525