Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Year of publication
- 2012 (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- survival (2) (remove)
Recently, several classifiers that combine primary tumor data, like gene expression data, and secondary data sources, such as protein-protein interaction networks, have been proposed for predicting outcome in breast cancer. In these approaches, new composite features are typically constructed by aggregating the expression levels of several genes. The secondary data sources are employed to guide this aggregation. Although many studies claim that these approaches improve classification performance over single genes classifiers, the gain in performance is difficult to assess. This stems mainly from the fact that different breast cancer data sets and validation procedures are employed to assess the performance. Here we address these issues by employing a large cohort of six breast cancer data sets as benchmark set and by performing an unbiased evaluation of the classification accuracies of the different approaches. Contrary to previous claims, we find that composite feature classifiers do not outperform simple single genes classifiers. We investigate the effect of (1) the number of selected features; (2) the specific gene set from which features are selected; (3) the size of the training set and (4) the heterogeneity of the data set on the performance of composite feature and single genes classifiers. Strikingly, we find that randomization of secondary data sources, which destroys all biological information in these sources, does not result in a deterioration in performance of composite feature classifiers. Finally, we show that when a proper correction for gene set size is performed, the stability of single genes sets is similar to the stability of composite feature sets. Based on these results there is currently no reason to prefer prognostic classifiers based on composite features over single genes classifiers for predicting outcome in breast cancer.
Background: Recently published results of quality of life (QoL) studies indicated different outcomes of palliative radiotherapy for brain metastases. This prospective multi-center QoL study of patients with brain metastases was designed to investigate which QoL domains improve or worsen after palliative radiotherapy and which might provide prognostic information.
Methods: From 01/2007-01/2009, n=151 patients with previously untreated brain metastases were recruited at 14 centers in Germany and Austria. Most patients (82 %) received whole-brain radiotherapy. QoL was measured with the EORTC-QLQ-C15-PAL and brain module BN20 before the start of radiotherapy and after 3 months.
Results: At 3 months, 88/142 (62 %) survived. Nine patients were not able to be followed up. 62 patients (70.5 % of 3-month survivors) completed the second set of questionnaires. Three months after the start of radiotherapy QoL deteriorated significantly in the areas of global QoL, physical function, fatigue, nausea, pain, appetite loss, hair loss, drowsiness, motor dysfunction, communication deficit and weakness of legs. Although the use of corticosteroid at 3 months could be reduced compared to pre-treatment (63 % vs. 37 %), the score for headaches remained stable. Initial QoL at the start of treatment was better in those alive than in those deceased at 3 months, significantly for physical function, motor dysfunction and the symptom scales fatigue, pain, appetite loss and weakness of legs. In a multivariate model, lower Karnofsky performance score, higher age and higher pain ratings before radiotherapy were prognostic of 3-month survival.
Conclusions: Moderate deterioration in several QoL domains was predominantly observed three months after start of palliative radiotherapy for brain metastases. Future studies will need to address the individual subjective benefit or burden from such treatment. Baseline QoL scores before palliative radiotherapy for brain metastases may contain prognostic information.