Evidence map›Paper›PMID 37542078›Full record

ArticleScientific reports2023

Training certified detectives to track down the intrinsic shortcuts in COVID-19 chest x-ray data sets.

Ran Zhang, Dalton Griner, John W Garrett, Zhihua Qi, Guang-Hong Chen

Abstract read
In one paragraph

Article in Scientific reports, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.

0numbers the graph read from it
0cells of the map it votes in
1citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

1 citing paper in PubMed.

  1. Article
4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

5 authors.

Ran Zhang *Department of Medical Physics, School of Medicine and Public Health, The University of Wisconsin in Madison, Madison, WI, 53705, USA.
Dalton Griner *Department of Medical Physics, School of Medicine and Public Health, The University of Wisconsin in Madison, Madison, WI, 53705, USA.
John W GarrettDepartment of Medical Physics, School of Medicine and Public Health, The University of Wisconsin in Madison, Madison, WI, 53705, USA.
Zhihua QiDepartment of Radiology, Henry Ford Health, Detroit, MI, 48202, USA.
Guang-Hong ChenDepartment of Medical Physics, School of Medicine and Public Health, The University of Wisconsin in Madison, Madison, WI, 53705, USA. gchen7@wisc.edu.

Funding

RADX TECH - CERES NANOSCIENCE INC NANOTRAP PARTICLE MANUFACTURING75N92020C00021 · NHLBI · CERES NANOSCIENCES, LLLP · PI DUNLAP, ROSS · 2021 to 2021
$4.0M
One Stop Shop Imaging for Acute Ischemic StrokeTreatmentU01EB021183 · NIBIB · UNIVERSITY OF WISCONSIN-MADISON · PI CHEN, GUANG-HONG · 2015 to 2020
$3.5M
Functional Lung Imaging Using a Single kV CT AcquisitionR01HL153594 · NHLBI · UNIVERSITY OF WISCONSIN-MADISON · PI CHEN, GUANG-HONG, LI, KE · 2021 to 2024
$3.0M
NHLBI NIH HHS 75N92020C00008NHLBI NIH HHS 75N92020C00021NHLBI NIH HHS R01 HL153594NIBIB NIH HHS U01 EB021183
6 · The paper itself

Abstract

Deep learning faces a significant challenge wherein the trained models often underperform when used with external test data sets. This issue has been attributed to spurious correlations between irrelevant features in the input data and corresponding labels. This study uses the classification of COVID-19 from chest x-ray radiographs as an example to demonstrate that the image contrast and sharpness, which are characteristics of a chest radiograph dependent on data acquisition systems and imaging parameters, can be intrinsic shortcuts that impair the model's generalizability. The study proposes training certified shortcut detective models that meet a set of qualification criteria which can then identify these intrinsic shortcuts in a curated data set.

Indexed as

COVID-19Deep LearningHumansRadiographic Image Interpretation, Computer-AssistedRadiography, ThoracicX-Rays

Identifiers

PMID37542078
PMCPMC10403557

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.