SEARCH

SEARCH BY CITATION

Keywords:

  • Multistate multifactorial model;
  • translational research

Few studies have focused on the different roles risk factors play in the multistate temporal natural course of breast cancer. We proposed a three-state Markov regression model to predict the risk from free of breast cancer (FBC) to the preclinical screen-detectable phase (PCDP) and from the PCDP to the clinical phase (CP). We searched the initiators and promoters affecting onset and subsequent progression of breast tumor to build up a three-state temporal natural history model with state-dependent genetic and environmental covariates. This risk assessment model was applied to a 1 million Taiwanese women cohort. The proposed model was verified by external validation with another independent data set. We identified three kinds of initiators, including the BRCA gene, seven single nucleotides polymorphism, and breast density. ER, Ki-67, and HER-2 were found as promoters. Body mass index and age at first pregnancy both played a role. Among women carrying the BRCA gene, the 10-year predicted risk for the transition from FBC to CP was 25.83%, 20.31%, and 13.84% for the high-, intermediate-, and low-risk group, respectively. The corresponding figures were 1.55%, 1.22%, and 0.76% among noncarriers. The mean sojourn time of staying at the PCDP ranged from 0.82 years for the highest risk group to 6.21 years for the lowest group. The lack of statistical significance for external validation (inline image) revealed the adequacy of our proposed model. The three-state model with state-dependent covariates of initiators and promoters was proposed for achieving individually tailored screening and also for personalized clinical surveillance of early breast cancer.