close
Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2026 Jan 29:392:e087581.
doi: 10.1136/bmj-2025-087581.

Machine learning based screening of potential paper mill publications in cancer research: methodological and cross sectional study

Baptiste Scancar  1 , Jennifer A Byrne  2   3 , David Causeur  1 , Adrian G Barnett  4
Affiliations

Machine learning based screening of potential paper mill publications in cancer research: methodological and cross sectional study

Baptiste Scancar et al. BMJ. .

Abstract

Objectives: To train and validate a machine learning model to distinguish paper mill publications from genuine cancer research articles, and to screen the cancer research literature to assess the prevalence of papers that have textual similarities to paper mill papers.

Design: Methodological and cross sectional study applying a BERT (bidirectional encoder representations from transformers) based, text classification model to article titles and abstracts.

Setting: Retracted paper mill publications listed in the Retraction Watch database were used for model training. The cancer research corpus was screened by the model using the PubMed database restricted to original cancer research articles published between 1999 and 2024.

Population: The model was trained on 2202 retracted paper mill papers and validated on independent data collected by image integrity experts. 2.6 million cancer research papers were screened.

Main outcome measures: Classification performance of the model. Prevalence of papers flagged as similar to retracted paper mill publications with 95% confidence intervals and their distribution over time, by country, publisher, cancer type, research area, and within high impact journals (top 10%).

Results: The model achieved an accuracy of 0.91. When applied to the cancer research literature, it flagged 261 245 of 2 647 471 papers (9.87%, 95% confidence interval 9.83 to 9.90) and revealed a large increase in flagged papers from 1999 to 2024, both across the entire corpus and in the top 10% of journals by impact factor. More than 170 000 papers affiliated with Chinese institutions were flagged, accounting for 36% of Chinese cancer research articles. Most publishers had published substantial numbers of flagged papers. Flagged papers were overrepresented in fundamental research and in gastric, bone, and liver cancer.

Conclusions: Paper mills are a large and growing problem in the cancer literature and are not restricted to low impact journals. Collective awareness and action will be crucial to address the problem of paper mill publications.

PubMed Disclaimer

Conflict of interest statement

Competing interests: All authors have completed the ICMJE uniform disclosure form at www.icmje.org/disclosure-of-interest/ and declare support from the National Health and Medical Research Council for the submitted work; no support from any organisation for the submitted work; no financial relationships with any organisations that might have an interest in the submitted work in the previous three years; no other relationships or activities that could appear to have influenced the submitted work.

Figures

Fig 1
Fig 1
Number of papers each year in cancer research corpus flagged because their titles and abstracts were similar to those of retracted paper mill papers. 95% confidence intervals estimated using bootstrap resampling. An interactive version of this graphic and downloadable data are available at  https://public.flourish.studio/visualisation/27240897/
Fig 2
Fig 2
Percentage of papers in cancer research corpus flagged because their titles and abstracts were similar to those of retracted paper mill papers across 25 countries with highest numbers of flagged papers based on first author's affiliation country. An interactive version of this graphic and downloadable data are available at https://public.flourish.studio/visualisation/27226146/
Fig 3
Fig 3
Percentage of papers in cancer research corpus flagged because their titles and abstracts were similar to those of retracted paper mill papers for 25 publishers with highest numbers of flagged papers. An interactive version of this graphic and downloadable data are available at https://public.flourish.studio/visualisation/27226940/
Fig 4
Fig 4
Percentage of cancer research papers according to cancer type flagged because their titles and abstracts were similar to those of retracted paper mill papers. An interactive version of this graphic and downloadable data are available at https://public.flourish.studio/visualisation/27227226/
Fig 5
Fig 5
Percentage of cancer research papers within each research area flagged because their titles and abstracts were similar to those of retracted paper mill papers. Because categories were assigned using a multi-labelling tool, each paper may appear in several categories and sum of all categories does not equal total number of flagged papers. Percentages represent proportion of papers flagged as similar to retracted paper mill papers within each research area, calculated as (flagged papers in area/total papers in area)×100. An interactive version of this graphic and downloadable data are available at https://public.flourish.studio/visualisation/27227359/
Fig 6
Fig 6
Percentage of cancer research papers flagged because their titles and abstracts were similar to those of retracted paper mill papers in top 10% of journals by impact factor according to publication year. An interactive version of this graphic and downloadable data are available at https://public.flourish.studio/visualisation/27227402/
See this image and copyright information in PMC

References

    1. Byrne JA, Park Y, Richardson RAK, Pathmendra P, Sun M, Stoeger T. Protection of the human gene research literature from contract cheating organizations known as research paper mills. Nucleic Acids Res 2022;50:12058-70. 10.1093/nar/gkac1139 - DOI - PMC - PubMed
    1. Committee on Publication Ethics. STM. Paper mills research report and recommendations. Technical report. Vol 6. 2022. https://members.publicationethics.org/sites/default/files/paper-mills-co...
    1. Van Noorden R. How big is science’s fake-paper problem? Nature 2023;623:466-7. 10.1038/d41586-023-03464-x - DOI - PubMed
    1. Joelving F, Retraction Watch . Paper trail. Science 2024;383:252-5. 10.1126/science.ado0309 - DOI - PubMed
    1. Van Noorden R. More than 10,000 research papers were retracted in 2023—a new record. Nature 2023;624:479-81. 10.1038/d41586-023-03974-8 - DOI - PubMed

LinkOut - more resources