External validation of Adjuvant! Online breast cancer prognosis tool. Prioritising recommendations for improvement

Background

Adjuvant! Online is a web-based application designed to provide 10 years survival probability of patients with breast cancer. Several predictors have not been assessed in the original Adjuvant! Online study. We provide the validation of Adjuvant! Online algorithm on two breast cancer datasets, and we determined whether the accuracy of Adjuvant! Online is improved with other well-known prognostic factors.

Patients and Methods

The French data set is composed of 456 women with early breast cancer. The Dutch data set is composed of 295 women less than 52 years of age. Agreement between observation and Adjuvant! Online prediction was checked, and logistic models were performed to estimate the prognostic information added by risk factors to Adjuvant! Online prediction.

Results

Adjuvant! Online prediction was overall well-calibrated in the French data set but failed in some subgroups of such high grade and HER2 positive patients. HER2 status, Mitotic Index and Ki67 added significant information to Adjuvant! Online prediction. In the Dutch data set, the overall 10-year survival was overestimated by Adjuvant! Online, particularly in patients less than 40 years old.

Conclusion

Adjuvant! Online needs to be updated to adjust overoptimistic results in young and high grade patients, and should consider new predictors such as Ki67, HER2 and Mitotic Index.     

Integration of clinical and gene expression data has a synergetic effect on predicting breast cancer outcome

Breast cancer outcome can be predicted using models derived from gene expression data or clinical data. Only a few studies have created a single prediction model using both gene expression and clinical data. These studies often remain inconclusive regarding an obtained improvement in prediction performance. We rigorously compare three different integration strategies (early, intermediate, and late integration) as well as classifiers employing no integration (only one data type) using five classifiers of varying complexity. We perform our analysis on a set of 295 breast cancer samples, for which gene expression data and an extensive set of clinical parameters are available as well as four breast cancer datasets containing 521 samples that we used as independent validation.mOn the 295 samples, a nearest mean classifier employing a logical OR operation (late integration) on clinical and expression classifiers significantly outperforms all other classifiers. Moreover, regardless of the integration strategy, the nearest mean classifier achieves the best performance. All five classifiers achieve their best performance when integrating clinical and expression data. Repeating the experiments using the 521 samples from the four independent validation datasets also indicated a significant performance improvement when integrating clinical and gene expression data. Whether integration also improves performances on other datasets (e.g. other tumor types) has not been investigated, but seems worthwhile pursuing. Our work suggests that future models for predicting breast cancer outcome should exploit both data types by employing a late OR or intermediate integration strategy based on nearest mean classifiers.     

Dysfunctional CD8 T Cells Form a Proliferative,Dynamically Regulated Compartment within Human Melanoma

1. Download high-res image (272KB)
2. Download full-size image

     

SIRAC: Supervised Identification of Regions of Aberration in aCGH datasets

Background  

Array comparative genome hybridization (aCGH) provides information about genomic aberrations. Alterations in the DNA copy number may cause the cell to malfunction, leading to cancer. Therefore, the identification of DNA amplifications or deletions across tumors may reveal key genes involved in cancer and improve our understanding of the underlying biological processes associated with the disease.