AI Persuasion, Bayesian Attribution, and Career Concerns of Doctors

This paper examines how AI persuades doctors when their diagnoses differ. Disagreements arise from two sources: attention differences, which are objective and play a complementary role to the doctor, and comprehension differences, which are subjective and act as substitutes. AI's interpretabili...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Li, Hanzhe, Li, Jin, Luo, Ye, Zhang, Xiaowei
Format: Article
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper examines how AI persuades doctors when their diagnoses differ. Disagreements arise from two sources: attention differences, which are objective and play a complementary role to the doctor, and comprehension differences, which are subjective and act as substitutes. AI's interpretability influences how doctors attribute these sources and their willingness to change their minds. Surprisingly, uninterpretable AI can be more persuasive by allowing doctors to partially attribute disagreements to attention differences. This effect is stronger when doctors have low abnormality detection skills. Additionally, uninterpretable AI can improve diagnostic accuracy when doctors have career concerns.
ISSN:2331-8422