Overall, the results of this study represent a call to action to develop more equitable AI models in healthcare.
Faisal Mahmoud
The researchers attempted to reduce the observed differences using standard machine learning techniques to reduce bias, such as highlighting examples of underrepresented groups during model training. However, these methods only slightly reduced bias. Instead, the disparity was reduced by using a self-supervised underlying model. This is a new form of advanced AI trained on large datasets to perform a wide range of clinical tasks. These models encode a richer representation of histology that may reduce the potential for model bias.
Despite the observed improvements, performance gaps remain evident, reflecting the need for further refinement of basic models in pathology. Additionally, this study included a small number of patients from some demographic groups. Researchers are continuing to explore how multimodality-based models that incorporate multiple forms of data, such as genomics and electronic medical records, can improve these models.
The emergence of AI tools in healthcare has the potential to positively reshape healthcare delivery. Balancing the innovative potential of AI with a commitment to quality and safety is essential. General Brigham is a leader in responsible AI, conducting rigorous research on newly emerging technologies to inform the incorporation of AI in healthcare.
“Overall, the results of this study represent a call to action to develop more fair AI models in healthcare,” Mahmoud said. “While this is a call to action for scientists to use more diverse datasets in their research, it is also a call to action for regulators and policy bodies to provide evaluation guidelines for these models before they are approved and deployed. It also calls for including demographic stratification of these models to ensure that AI systems can be used safely and equitably to benefit all patient groups. ”
sauce: General Brigham Mass
