1. Inherent Bias in Large Language Models: A Random Sampling Analysis
- Author
-
Noel F. Ayoub, MD, MBA, Karthik Balakrishnan, MD, MPH, Marc S. Ayoub, MD, Thomas F. Barrett, MD, Abel P. David, MD, and Stacey T. Gray, MD
- Subjects
Computer applications to medicine. Medical informatics ,R858-859.7 - Abstract
There are mounting concerns regarding inherent bias, safety, and tendency toward misinformation of large language models (LLMs), which could have significant implications in health care. This study sought to determine whether generative artificial intelligence (AI)-based simulations of physicians making life-and-death decisions in a resource-scarce environment would demonstrate bias. Thirteen questions were developed that simulated physicians treating patients in resource-limited environments. Through a random sampling of simulated physicians using OpenAI’s generative pretrained transformer (GPT-4), physicians were tasked with choosing only 1 patient to save owing to limited resources. This simulation was repeated 1000 times per question, representing 1000 unique physicians and patients each. Patients and physicians spanned a variety of demographic characteristics. All patients had similar a priori likelihood of surviving the acute illness. Overall, simulated physicians consistently demonstrated racial, gender, age, political affiliation, and sexual orientation bias in clinical decision-making. Across all demographic characteristics, physicians most frequently favored patients with similar demographic characteristics as themselves, with most pairwise comparisons showing statistical significance (P
- Published
- 2024
- Full Text
- View/download PDF