The RS calculator is capable to compute ER status, HER2 status and survival [recurrence score and recurrence risk] for a breast cancer patient using pre-defined sets of genes measured by a genome-wide microarray.

The Re-training algorithm can predict the risk of relapse (survival) for a breast cancer patient. It derives and employs an optimized personal classifier for each case by using only the molecularly most similar subset of training samples for predictor building.

What is Recurrence Online?

Recurrence Online is an online diagnostic service capable to predict

  • survival [risk of relapse and recurrence score],
  • response to hormonal treatment [ER status] and
  • response to targeted therapy [HER2 status]

for breast cancer patients using transcriptomic data. Quality control algorithms are implemented to exclude biases related to sample processing, hybridization and scanning. You must have a .CEL file to use the system.

How the dynamic re-training algorithm works

The system analyzes gene expression data from 3,534 breast cancers with clinical annotation including survival. For each test case a case-specific training subset is selected that includes only cases with the highest molecular similarity to the tests case. Similarity is measured by Euclidean distance over all genes. Informative genes are identified in the case-specific training cohort by computing Cox regression coefficient and develop a case-specific predictor. This fixed predictor is applied to the test case. This dynamic predictor building method yields different training sets and different predictors for each new case.