Conflict of interest in spine research reporting

Abstract

Background: Medical studies are more likely to report favorable findings when a conflict of interest is declared. We aim to quantify and determine the effect of author disclosure of conflict of interest on scientific reporting.

Methods: Abstracts from an international spine research meeting (North American Spine Society 2010) were selected that specifically evaluated a device, biologic, or proprietary procedure. They were then made anonymous to reviewers. An item of interest was established in each of the abstracts in order to standardize evaluation. Next, three blinded reviewers independently rated the abstracts as favorable, neutral, or unfavorable with regard to the item of interest. Additionally, the blinded reviewers attempted to predict whether a related disclosure was made. The meeting disclosure index was used to tabulate the minimum US dollar value attributable to disclosures.

Results: Of the 344 total abstracts, 76 met inclusion criteria. In 79%, a related conflict of interest was reported. The amount of the disclosure was incompletely reported in 30% of cases. Where available, it averaged a cumulative minimum of $219,634 USD per abstract. The results of the abstracts were judged to be favorable, neutral, and unfavorable in 63%, 32% and 5% of abstracts, respectively. There was no correlation between the presence of a related disclosure and the findings of the studies (p = 0.81), although interpretation of this is limited by a small sample size and an overall apparent bias to report favorable studies. Additionally, the blinded reviewers were unable to predict whether a related disclosure was made (p = 0.40).

Conclusion: No association existed between the presence of a related disclosure and the results of the studies. While the actual compliance with reporting a potential conflict of interest is unable to be determined, the value amount related to the disclosures made was inadequately reported according to meeting guidelines.

Figure 1. Observer interpretation of study favorability.

Three independent and blinded researchers assessed the favorability of the results of an abstract with respect to a designated item of interest. There was no association with these ratings and whether a related conflict of interest was present (p = 0.81).

Figure 2. Observer prediction of disclosure declaration.

Three independent and blinded researchers were unable to predict whether a related conflict of interest was present for each abstract (p = 0.40).