Retracted papers originating from paper mills: cross sectional study

OBJECTIVES To describe retracted papers originating from paper mills, including their characteristics, visibility, and impact over time, and the journals in which they were published. DESIGN Cross sectional study. SETTING The Retraction Watch database was used for identification of retracted papers from paper mills, Web of Science was used for the total number of published papers, and data from Journal Citation Reports were collected to show characteristics of journals. PARTICIPANTS All paper mill papers retracted from 1 January 2004 to 26 June 2022 were included in the study. Papers bearing an expression of concern were excluded. MAIN OUTCOME MEASURES Descriptive statistics were used to characterise the sample and analyse the trend of retracted paper mill papers over time, and to analyse their impact and visibility by reference to the number of citations received. RESULTS 1182 retracted paper mill papers were identified. The publication of the first paper mill paper was in 2004 and the first retraction was in 2016; by 2021, paper mill retractions accounted for 772 (21.8%) of the 3544 total retractions. Overall, retracted paper mill papers were mostly published in journals of the second highest Journal Citation Reports quartile for impact factor (n=529 (44.8%)) and listed four to six authors (n=602 (50.9%)). Of the 1182 papers, almost all listed authors of 1143 (96.8%) paper mill retractions came from Chinese institutions and 909 (76.9%) listed a hospital as a primary affiliation. 15 journals accounted for 812 (68.7%) of 1182 paper mill retractions, with one journal accounting for 166 (14.0%). Nearly all (n=1083, 93.8%) paper mill retractions had received at least one citation since publication, with a median of 11 (interquartile range 5-22) citations received. CONCLUSIONS Papers retracted originating from paper mills are increasing in frequency, posing a problem for the research community. Retracted paper mill papers most commonly originated from China and were published in a small number of journals. Nevertheless, detected paper mill papers might be substantially different from those that are not detected. New mechanisms are needed to identify and avoid this relatively new type of misconduct.