Nigon, Sandra

4127 Background: The MMRpredict model, developed at the University of Edinburgh, is a web-based model developed to predict which patients diagnosed with colorectal cancer (CRC) under age 55 years have germline mutations in a DNA mismatch repair (MMR) gene [Barnetson et al., NEngJMed 2006;354:2751–63]. Stage 1 MMRpredict estimates the carrier probability for MMR mutations from clinical parameters (age of diagnosis of colorectal cancer, proximal vs distal site, family history, multiple primary CRCs). We evaluated the performance of Stage 1 of this model in a well characterized cohort of colorectal cancer patients. Methods: Cases with CRC were identified through the Minnesota Cancer Surveillance System (MCSS), a population based registry and Mayo Clinic Rochester, a clinical practice. All were consented participants in the Mayo Colon Cancer Family Registry. Of 342 cases tested for MMR mutations (MLH1, MSH2, MSH6), 45 had insufficient information on colon site and 62 were older than 55 and could not be used in the study. The remaining 235 included 110 females/125 males; 90 cases with proximal site/145 with distal site; 229/235 were self-identified as White. Results: We defined 5 probability risk groups based on output from the MMRpredict web model Stage 1: 1–10%, 11–25%, 26–50%, 51–75%, and 76–100%. In our study, the number of cases in each of these groups was 60, 45, 65, 34, and 31, respectively. The corresponding number of mutations in each group was 1 (1.7%), 4 (8.9%), 9 (13.8%), 3 (8.8%), and 11 (35.5%). Overall, 28/235 patients were found to have mutations (11.9%), compared to predicted range of 62–107 (26–45%). Conclusion: MMRpredict Stage 1 over-estimated the probability of detecting a MMR gene mutation in this study. This may reflect ascertainment issues or genetics of different populations. No significant financial relationships to disclose.

Abstract Introduction: Colorectal adenomas and other types of polyps are commonly used as end points or risk factors in epidemiologic studies. However, it is not known how accurately patients are able to self-report the presence or absence of adenomas following colonoscopy. Methods: Participants in the Colon Cancer Family Registry provided self-reports of recent colorectal cancer (CRC) screening activity, and whether or not they had ever been told they had a polyp. Positive and negative predictive values for polyp self-report were calculated by comparing medical records with self-reports from 488 participants. Results: The positive predictive value for self-reported polyp was 80.9%, and the negative predictive value was 85.8%. The predictive values did not differ by age group or sex, but participants with a previous diagnosis of CRC had a lower negative predictive value (76.2%) than participants with no personal history of CRC (89.0%; P = 0.04). Conclusions: Predictive values for self-reports of polyps are fairly high, but researchers needing accurate polyp data should obtain medical record confirmation. Pursuing medical records on only those participants self-reporting a polyp could result in an underestimation of the polyp prevalence in a study population. (Cancer Epidemiol Biomarkers Prev 2007;16(9):1898–901)