ChatGPT-4's Accuracy in Estimating Thyroid Nodule Features and Cancer Risk From Ultrasound Images.

Journal: Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists
Published Date: Jun 1, 2025

Abstract

OBJECTIVE: To evaluate the performance of GPT-4 and GPT-4o in accurately identifying features and categories from thyroid nodule ultrasound images following the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS).

Authors

  • Esteban Cabezas
    Knowledge and Evaluation Research Unit, Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota.
  • David Toro-Tobon
    Knowledge and Evaluation Research Unit, Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota; Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Mayo Clinic, Rochester, Minnesota.
  • Thomas Johnson
    Division of Endocrinology, Mercy Hospital, Springfield, Missouri.
  • Marco Álvarez
    Universidad Politécnica de Sinaloa en Mazatlán, Sinaloa, México.
  • Javad R Azadi
    Johns Hopkins University School of Medicine, Department of Radiology, Baltimore, Maryland.
  • Camilo Gonzalez-Velasquez
    Hospital Universitario "Dr. José E. González", Universidad Autónoma de Nuevo León, México.
  • Naykky Singh Ospina
    Division of Endocrinology, Department of Medicine, University of Florida, Gainesville, Florida.
  • Oscar J Ponce
    Knowledge and Evaluation Research Unit, Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota; University Hospitals Plymouth NHS Trust, Plymouth, Devon, the United Kingdom.
  • Megan E Branda
    Knowledge and Evaluation Research Unit, Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota; Division of Biomedical Statistics and Informatics, Department of Health Sciences Research, Mayo Clinic, Rochester, Minnesota.
  • Juan P Brito
    Knowledge and Evaluation Research Unit, Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota; Division of Endocrinology, Diabetes, Metabolism, and Nutrition, Mayo Clinic, Rochester, Minnesota. Electronic address: brito.juan@mayo.edu.

Keywords

External Resources

Popular Topics
Recent Journals