Reliability and accuracy of artificial intelligence ChatGPT in providing information on ophthalmic diseases and management to patients.
Francesco CappellaniKevin R CardCarol L ShieldsJose S PulidoJulia A HallerPublished in: Eye (London, England) (2024)
Despite the positive scores, ChatGPT on its own still provides incomplete, incorrect, and potentially harmful information about common ophthalmic conditions, defined as the recommendation of invasive procedures or other interventions with potential for adverse sequelae which are not supported by the AAO for the disease in question. ChatGPT may be a valuable adjunct to patient education, but currently, it is not sufficient without concomitant human medical supervision.
Keyphrases
- artificial intelligence
- end stage renal disease
- machine learning
- healthcare
- big data
- endothelial cells
- deep learning
- ejection fraction
- chronic kidney disease
- newly diagnosed
- health information
- physical activity
- prognostic factors
- emergency department
- quality improvement
- patient reported outcomes
- patient reported
- climate change
- adverse drug
- cataract surgery