Prevención farmacológica del cáncer de mama

Abstract

Several breast cancer risk estimation models are available that combine reproductive factors and family history. These algorithms have been used to select subjects in clinical trials, but they have a low individual prediction power. Attempts to improve this performance have included incorporation of mammographic density and polymorphisms as well as adaption to specific populations cancer risk. Recent advances in artificial intelligence have substantially improve risk estimation accuracy. Prevention of breast cancer have been consistently and repeatedly demonstrated by manipulating the estrogenic environment in women with different levels of basal risk. Despite the potential impact of aromatase inhibitors and SERMS in reducing the personal, social, and economic burden of breast cancer this strategy is not widely implemented. The finding that low dose of tamoxifen given for three years may suffice to have an important preventative effect may help augment the use of breast cancer chemoprevention. In the near future, the incorporation of artificial intelligence will probably revolutionize early diagnosis and personalized risk estimation in breast cancer.