Click on a filter below to refine your search. Remove a filter to broaden your search.
Performance was better than that of a certified rater but not quite as good as that of an expert neurologists.
The greatest effectiveness, however, was seen for young children compared with adults.
Standard AI models improve predictions, but systematically biased predictions reduce accuracy.
Responses are moderately understandable, not readily actionable, and written at the college reading level.
The likelihood of chatbot answers containing incorrect or inappropriate material was comparable with human answers.