Work

Impact of Label Noise from Large Language Model–generated Annotations on Evaluation of Diagnostic Model Performance

Year: 2025

Type: article

Abstract: Large language model–generated labels can introduce systematic bias in artificial intelligence binary classification model performance evaluation, with disease prevalence critically determining whether sensitivity or specificity is most affected.

Source: Radiology Artificial Intelligence

DOI: 10.1148/ryai.250477

Authors: Mohammadreza Chavoshi, Hari Trivedi, Aawez Mansuri, Janice Newsome, Chiratidzo Rudado Sanyika, Rohan Satya Isaac, Frank Li, Theo Dapamede, Judy Wawira Gichoya

Institution: Emory University

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

Funders: Robert Wood Johnson Foundation, Gordon and Betty Moore Foundation, National Institutes of Health, National Heart, Lung, and Blood Institute, National Institute of Biomedical Imaging and Bioengineering

Awards: G3018715022, G4749485581, Developing a Hive Learning and Datathon Supported Course on Imaging and Multimodal Data for Resource-Limited Institutions (CIMDAR-HIVE), G8842961228, G8877264399, Opportunistic Screening for ASCVD using a Multimodal Deep Learning Risk Prediction Model

OpenAlex ID: W4417128758

FWCI: 0.963

Cites: 19

Cited by: 4

Related to: 10