Regarding the Credibility of Data Showing an Alleged Association of Cancer with Radiation from CT Scans

Abstract

Computed tomography (CT) scans are of high clinical value as a diagnostic technique, and new applications continue to be identified. However, their application is challenged by emerging concerns regarding carcinogenesis from their radiation. Recent articles made a significant contribution to the above-mentioned concerns by reporting evidence for direct association of the radiation from CT scans with cancer. Such interpretation of the data has already been criticized; there is the possibility of reverse causation due to confounding factors. Nevertheless, such work has had a high impact, with one article being cited more than 300 times from the Web of Science Core Collection within 2 years. However, the data points on cancer relative risk versus CT dose in that article fit straight lines corresponding to the linear no-threshold hypothesis suspiciously well. Here, by applying rigorous statistical analysis, it is shown that the probability of the fit truly being that good or better is only 2%. The results of such studies therefore appear "too good to be true" and the credibility of their conclusions must be questioned.

Keywords: CT; LNT hypothesis; carcinogenesis; hypothesis testing; radiation; statistics.