Evidence map›Paper›PMID 42215678›Full record

ArticleNPJ digital medicine2026

Detecting dataset bias in medical AI using a generalized and modality agnostic auditing approach.

Nathan Drenkow, Mitchell Pavlak, Keith Harrigian, Ayah Zirikly, Adarsh Subbaswamy, Mohammad Mehdi Farhangi, Nicholas Petrick, Mathias Unberath

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in NPJ digital medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 4 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
4citing papers in PubMed, 1 pooled it
–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

4 citing papers in PubMed, 1 synthesis or guideline pooled it.

  1. Pooled it
  2. Article
  3. Review
  4. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

8 authors.

Nathan Drenkow *The Johns Hopkins University, Baltimore, MD, USA. nathan.drenkow@jhuapl.edu.
Mitchell Pavlak *The Johns Hopkins University, Baltimore, MD, USA.
Keith HarrigianThe Johns Hopkins University, Baltimore, MD, USA.
Ayah ZiriklyThe Johns Hopkins University, Baltimore, MD, USA.
Adarsh SubbaswamyCenter for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD, USA.
Mohammad Mehdi FarhangiCenter for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD, USA.
Nicholas PetrickCenter for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD, USA.
Mathias UnberathThe Johns Hopkins University, Baltimore, MD, USA.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

Despite many success stories along the path of Artificial Intelligence's (AI) rise in healthcare, there are comparably many reports of significant shortcomings and unexpected behavior of AI in deployment. A major risk is AI's reliance on association-based learning, where non-representative machine learning datasets can amplify latent bias during training and hide it during testing. To unlock new tools capable of detecting such AI bias issues, we present Generalized Attribute Utility and Detectability-Induced bias Testing (G-AUDIT). G-AUDIT is a data modality-agnostic dataset auditing approach that automatically quantifies shortcut learning risks by examining the interplay between task-level annotations, sensor-level measurements, and patient, environmental, and acquisition characteristics. We demonstrate the broad applicability of this method by analyzing a range of medical datasets across three distinct modalities (images, text, and tabular data) and machine learning tasks, successfully identifying potential shortcuts commonly overlooked by traditional qualitative methods.

Identifiers

PMID42215678
PMCPMC13507256

What OpenQuestion holds

Textmetadata
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.