Disparities in seizure outcomes revealed by large language models.
Kevin XieWilliam K S OjemannRyan S GallagherRussell T ShinoharaAlfredo LucasChloé E HillRoy H HamiltonKevin B JohnsonDan RothBrian LittColin A EllisPublished in: Journal of the American Medical Informatics Association : JAMIA (2024)
We found little evidence that our LLM was intrinsically biased against any demographic group. Seizure freedom extracted by LLM revealed disparities in seizure outcomes across several demographic groups. These findings quantify the critical need to reduce disparities in the care of people with epilepsy.