Arrhythmias & electrophysiology
Accuracy and comprehensibility of chat-based artificial intelligence for patient information on atrial fibrillation and cardiac implantable electronic devices
Authors' conclusion
Responses generated by an NLPC are mostly easy to understand with varying readability between the different NLPCs. The appropriateness of responses is limited and varies between different NLPCs. Important aspects are often missed to be mentioned.
Study context
- Population
- Responses of Natural Language Processing Chatbots (NLPCs) to questions on Atrial Fibrillation (AF) and Clinical Implantable Electronic Devices (CIEDs)
- Exposure
- Google Bard vs Bing Chat vs ChatGPT Plus
- Outcome
- Appropriate responses
Main finding
As reported in the abstract
AF
CIEDs
Observational data: associations, not effects.
Further findings
Comprehensible responses
AF
CIEDs
Relevant aspects missing
AF
CIEDs
Readability (word count, Flesch Reading Ease)
- Readability varied between NLPCs
Original publication
Accuracy and comprehensibility of chat-based artificial intelligence for patient information on atrial fibrillation and cardiac implantable electronic devices. Europace. Published 21 December 2023. doi:10.
Summarised from the published abstract; every number is checked against it