Implementation of Breast Cancer Risk Assessment Tool using SAS

Le résumé fourni par la source

In this paper, a SAS macro is developed to implement the breast cancer risk assessment (BCRA) tool designed by National Cancer Institute (NCI). The BCRA tool itself is based on a complex statistical model known as the Gail model. The Gail model provides an estimate of a woman’s risk of developing invasive breast cancer over a specific period of time by utilizing an individual’s demographic information and risk factors. Breast cancer risk factors considered in the Gail model include (1) the number of previous breast biopsies, (2) the presence of atypical hyperplasia in any previous breast biopsy specimen, (3) age at the start of menstruation, (4) age at the first live birth of a child, (5) the history of breast cancer among her first-degree relatives (mother, sisters, daughters), and (6) the individual’s age and race. The statistical model calculates individualized invasive breast cancer risk in terms of probabilities based on both the relative risk and the baseline hazard rate. We converted the C++ source code available from the NCI website to a SAS© macro. Features of the macro include ease of implementation and integration through SAS© as well as flexibility in calculating the probabilistic breast cancer risk at any duration of time.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.