Evidence map›Paper›PMID 41249460›Full record

ArticleNPJ digital medicine2025

Evaluating transparency in AI/ML model characteristics for FDA-reviewed medical devices.

Viraj Mehta, Abhinav Komanduri, Rishabh Singh Bhadouriya, Vilina Mehta, Michael David Johnson, Priyanka Shrestha, Margaret Nikolov, Bhav Jain, Nigam Shah, Kevin Schulman

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in NPJ digital medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 15 papers.

0numbers the graph read from it
0cells of the map it votes in
15citing 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

15 citing papers in PubMed.

  1. Article
  2. Article
  3. Review
  4. Review
  5. Regulatory science for AI-basedJournal of pathology informatics · 2026
    Article
  6. AI/ML-based computational models for toxicity prediction.Environmental science and pollution research international · 2026
    Review
  7. Article
  8. Article
  9. Article
  10. Review
  11. Review
  12. Review
  13. Review
  14. Article
  15. 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

10 authors.

Viraj MehtaStanford University, Department of Computer Science, Stanford, USA, CA.
Abhinav KomanduriUniversity of Southern California, Department of Population and Public Health Sciences, Los Angeles, USA, CA.
Rishabh Singh BhadouriyaUniversity of Pittsburgh, College of General Studies, Pittsburgh, USA, PA.
Vilina MehtaStanford University, School of Medicine, Stanford, USA, CA.
Michael David JohnsonStanford University, School of Medicine, Stanford, USA, CA.
Priyanka ShresthaStanford University, Department of Computer Science, Stanford, USA, CA.
Margaret NikolovClinical Excellence Research Center, School of Medicine, Stanford University, Stanford, USA, CA.
Bhav JainStanford University, School of Medicine, Stanford, USA, CA.
Nigam ShahClinical Excellence Research Center, School of Medicine, Stanford University, Stanford, USA, CA.
Kevin SchulmanClinical Excellence Research Center, School of Medicine, Stanford University, Stanford, USA, CA. Kevin.Schulman@Stanford.Edu.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

The rapid integration of artificial intelligence (AI) and machine learning (ML) into medical devices has underscored the need for transparency in regulatory reporting. In 2021, the U.S. Food and Drug Administration (FDA) issued Good Machine Learning Practice (GMLP) principles, but adherence in FDA-reviewed devices remains uncertain. We reviewed 1,012 summaries of safety and effectiveness (SSEDs) for AI/ML-enabled devices approved or cleared by the FDA between 1970 and December 2024. Transparency in model development and performance was assessed using a novel AI Characteristics Transparency Reporting (ACTR) score across 17 categories. The average ACTR score was 3.3 out of 17, with modest improvement by 0.88 points (95% CI, 0.54-1.23) after the 2021 guidelines. Nearly half of devices did not report a clinical study and over half did not report any performance metric. These findings highlight transparency gaps and emphasize the need for enforceable standards to ensure trust in AI/ML medical technologies.

Identifiers

PMID41249460
PMCPMC12624113

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
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.