Reviewing the reviews: the example of chronic fatigue syndrome

Abstract

Objective: To test the hypothesis that the selection of literature in review articles is unsystematic and is influenced by the authors' discipline and country of residence.

Data sources: Reviews in English published between 1980 and March 1996 in MEDLINE, EMBASE (BIDS), PSYCHLIT, and Current Contents were searched.

Study selection: Reviews of chronic fatigue syndrome (CFS) were selected. Articles explicitly concerned with a specialty aspect of CFS and unattributed, unreferenced, or insufficiently referenced articles were discarded.

Data extraction: Record of data sources in each review was noted as was the departmental specialty of the first author and his or her country of residence. The references cited in each index paper were tabulated by assigning them to 6 specialty categories, by article title, and by assigning them to 8 categories, by country of journal publication.

Data synthesis: Of 89 reviews, 3 (3.4%) reported on literature search and described search method. Authors from laboratory-based disciplines preferentially cited laboratory references, while psychiatry-based disciplines preferentially cited psychiatric literature (P = .01). A total of 71.6% of references cited by US authors were from US journals, while 54.9% of references cited by United Kingdom authors were published in United Kingdom journals (P = .001).

Conclusion: Citation of the literature is influenced by review authors' discipline and nationality.