From Clinical Notes to GPT-4: Dr. Emily Alsentzer on Natural Language Processing in Medicine
NEJM AI Grand Rounds
00:00
Bias in AI Healthcare Diagnostics
This chapter analyzes a study on GPT-4's potential to reinforce racial and gender biases in healthcare, particularly in clinical decision-making. The discussion highlights significant disparities in diagnosis accuracy based on patient demographics and underscores the importance of addressing biases in AI training data and methodologies. Personal anecdotes further illustrate the complexities of integrating AI in medicine, emphasizing the need for cautious application and robust evaluations.
Transcript
Play full episode
