Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

X-ray Imaging01:24

X-ray Imaging

German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with X-rays, and by 1900, X-ray was widely...
Imaging Studies for Cardiovascular System III: X-Ray01:20

Imaging Studies for Cardiovascular System III: X-Ray

The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and the...
Computed Tomography01:10

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ultrasound-Fluoroscopy Versus Ultrasound Guidance for Catheter Drainage of Loculated Pleural Effusions: A Retrospective Study.

Diagnostics (Basel, Switzerland)·2026
Same author

Diagnostic accuracy and safety of cone-beam computed tomography-guided percutaneous transthoracic lung biopsy: an updated systematic review and meta-analysis.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

The Memory Inflation Response Against Spread-Defective CMV Requires Priming-Independent CD4<sup>+</sup> T Cell Help.

European journal of immunology·2026
Same author

Nutritional Risk Assessed by Royal Free Hospital-Nutritional Prioritizing Tool Predicts Survival in Cirrhosis With or Without Hepatocellular Carcinoma.

Journal of Korean medical science·2026
Same author

Association between extreme temperatures and out-of-hospital cardiac arrest: A time-stratified case-crossover study in Korea.

The journal of climate change and health·2026
Same author

Enhanced Sensitivity and Altered EEG Patterns During General Anesthesia in BTBR Mice, a Model of Autism.

Brain sciences·2026

Related Experiment Video

Updated: Jul 16, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Encoding Versus Linear Use of Patient Characteristics in Chest X-Ray Foundation Models on MIMIC-CXR.

Yeonsu Kim1, Yangwon Kim1, Yoojin Nam1,2

  • 1Department of Radiology, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon 51353, Republic of Korea.

Diagnostics (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

Patient attributes encoded in chest X-ray foundation models do not drive finding prediction. Residualizing attributes like heart failure had minimal impact, and did not reduce subgroup bias, highlighting the need for careful pre-deployment audits.

Keywords:
algorithmic fairnessattribute dependencechest X-raydebiasingfoundation modelodds ratioresidualizationshortcut learning

More Related Videos

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
12:09

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations

Published on: January 8, 2013

Related Experiment Videos

Last Updated: Jul 16, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
12:09

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations

Published on: January 8, 2013

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Foundation Models for Healthcare
  • Medical Image Analysis and Fairness

Background:

  • Chest X-ray (CXR) foundation models can infer patient demographics (sex, age, race) via linear probing.
  • The extent to which these encoded attributes influence the prediction of thoracic findings remains unquantified at scale.

Purpose of the Study:

  • To investigate the relationship between encoded patient attributes and the prediction of thoracic findings in CXR foundation models.
  • To assess whether removing attribute information (residualization) impacts finding prediction accuracy and reduces subgroup bias.

Main Methods:

  • Utilized the MIMIC-CXR dataset (230,697 images, 60,518 patients) with 24 patient attributes and 10 thoracic findings.
  • Measured attribute dependence by the drop in AUROC after residualizing attributes from frozen model embeddings across 6 foundation models.
  • Regressed dependence on attribute-finding odds ratios (ORs), encoding strength, and model-level factors; analyzed subgroup gaps.

Main Results:

  • Attribute encoding and dependence were dissociated; sex contributed minimally (<0.001), while heart failure showed the largest dependence (0.018).
  • Attribute-finding odds ratios explained 50.6% of dependence variance; model factors had no detectable contribution.
  • Residualizing top attributes reduced AUROC by 0.026 but did not narrow sex or age subgroup gaps; race subgroup gaps were significantly larger than residualization drops.

Conclusions:

  • Encoding, dependence, and subgroup bias are separable properties of CXR foundation models.
  • Pre-deployment audits should prioritize attributes by local odds ratios; residualizing race and cardiac correlates does not mitigate race subgroup bias.
  • Subgroup bias appears linked to group-wise finding base rates, necessitating further research into cross-institutional transfer and external validation.