Artificial intelligence models used in medical diagnoses, especially with images like X-rays, have shown to have accuracy discrepancies across demographic groups, performing worse in women and people of color. A surprising development in 2022 showed that AI models are able to predict a patient’s race from chest X-rays, surpassing radiologists. Researchers have found that these models may use “demographic shortcuts” in their evaluations, leading to incorrect results for certain groups. Strategies to reduce bias in AI models have shown success, but only when tested on the same type of patients they were trained on. These findings highlight the importance of thoroughly evaluating AI models before use in hospitals to ensure fairness across all groups.
https://medicalxpress.com/news/2024-06-reveals-ai-medical-images-biased.html