The evaluation metric for this competition is ROC AUC (Area Under the Curve). The AUC, commonly used in binary classification models, measures the area under a curve that is obtained by varying the threshold for binary classification (0.5 by default) and computing True Positive Rates and False Positive Rates (http://en.wikipedia.org/wiki/Receiver_operating_characteristic).


## Submission File
Submission Format
For every patient in the dataset, submission files should contain two columns: icustayid (this defines the individual prediction, and it's extracted from the test dataset) and HOSPITAL_EXPIRE_FLAG (float number between 0 and 1, the probability of death)..
 

The file should contain a header and have the following format:

    icustay_id,HOSPITAL_EXPIRE_FLAG
    2,0.651
    5,0.004
    6,0.104
    etc.