#**Goal Metric**

The metric: Balanced Accuracy Score

The balanced accuracy in binary and multiclass classification problems to deal with imbalanced datasets. It is defined as the average of recall obtained on each class.

**This is the sole metric that will be considered to determine your ranking.**

#**Other Metrics**


Participants will be ranked based only on the multiclass accuracy metric. However, for scientific completeness, predicted responses will also have the following metrics computed (comparing prediction vs. ground truth) for each image:

##**Individual Category Metrics**

* [sensitivity](https://en.wikipedia.org/wiki/Sensitivity_and_specificity#Sensitivity)
* [specificity](https://en.wikipedia.org/wiki/Sensitivity_and_specificity#Specificity)
* [accuracy](https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification)
* [area under the receiver operating characteristic curve (AUC)](https://en.wikipedia.org/wiki/Receiver_operating_characteristic#Area_under_the_curve)
* [mean average precision](http://fastml.com/what-you-wanted-to-know-about-mean-average-precision/)
* [F1 score](https://en.wikipedia.org/wiki/F1_score)
* average AUC across all diagnoses
* [positive predictive value (PPV)](https://en.wikipedia.org/wiki/Positive_and_negative_predictive_values)
* [negative predictive value (NPV)](https://en.wikipedia.org/wiki/Positive_and_negative_predictive_values)