Title: The balance hazard ratio for evaluating prognostic factors and survival risk groups
Authors: Pierre Dupont - University of Louvain, Belgium (Belgium) [presenting]
Abstract: Common clinical studies assess the quality of prognostic factors, such as gene expression signatures, clinical variables or environmental factors to cluster patients into various risk groups. Such groups are intended to represent patients with similar survival odds and to select the most appropriate therapy accordingly. The relevance of such risk groups, and of the related prognostic factors, is typically assessed through the computation of a hazard ratio. Some limitations of this commonly adopted procedure are stressed here. These issues could lead to inappropriate comparisons between various prognostic factors. One briefly describes some alternative measures including the Concordance Index, AUC, ... and discuss their benefits and limitations. Next, the balanced hazard ratio is introduced to solve these issues. This new performance metric keeps an intuitive interpretation and is as simple to compute as the original hazard ratio. It also leads to a natural cut-off choice to define risk groups from continuous risk scores. The proposed methodology is illustrated through the evaluation of a gene signature for breast cancer prognosis, and similar results are briefly presented on alternative clinical studies. Finally, one argues why the proposed methodology can be applied more generally to assess the quality of any prognostic or predictive markers.