Skip to content



The concordance index or C-index is a generalization of the area under the ROC curve (AUC) that can take into account censored data. It represents the global assessment of the model discrimination power: this is the model’s ability to correctly provide a reliable ranking of the survival times based on the individual risk scores. It can be computed with the following formula:


  • , the risk score of a unit
  • if else
  • if else

Similarly to the AUC, corresponds to the best model prediction, and represents a random prediction.


The function can be found at pysurvival.utils.metrics.concordance_index.


concordance_index - Concordance Index computations

    concordance_index(model, X, T, E, include_ties = True, additional_results=False)


  • model : Pysurvival object -- Pysurvival model

  • X : array-like -- input samples; where the rows correspond to an individual sample and the columns represent the features (shape=[n_samples, n_features]).

  • T : array-like -- target values describing the time when the event of interest or censoring occurred.

  • E : array-like -- values that indicate if the event of interest occurred i.e.: E[i]=1 corresponds to an event, and E[i] = 0 means censoring, for all i.

  • include_ties: bool (default=True) -- Specifies whether ties in risk score are included in calculations

  • additional_results: bool (default=False) -- Specifies whether only the c-index should be returned (False) or if a dict of values should returned. In that case, the values are:

    • c_index
    • nb_pairs
    • nb_concordant_pairs


  • c_index: float or dict -- Result of the function

    • if additional_results = False then c_index is float.
    • if additional_results = True then c_index is dict, such that c_index = {'c_index': ., 'nb_pairs': ., 'nb_concordant_pairs': .}