Ever wondered how doctors decide if a test really finds cancer?
Receiver operating characteristic
Ever wondered how doctors decide if a test really finds cancer?
Imagine you're at a doctor's office, and they give you a new test for cancer. You want to know if it's good at finding real cases without raising too many false alarms.
Picture a graph where the left side shows how well the test catches cancer (like spotting all the real cases), and the right side shows how many healthy people it wrongly flags as having cancer. The better the test, the higher the area above this graph.
Example
If the test catches 90% of real cancer cases but also flags 10% of healthy people, the graph's area above it shows its effectiveness.
Remember this
The Area Under the ROC Curve (AUC-ROC) measures how well a test can distinguish between real cases and false alarms.
Text adapted from Wikipedia, licensed under CC BY-SA 4.0.
Related concepts
Binary classification
Why is it important to know if something is a disease or not?
to use AUC-ROC: comparing classifiers across all thresholds
Why can't we always trust a yes-or-no answer?
F-score
Why is one metric not enough to judge a binary classification model's performance?
Evaluation of binary classifiers
Why can't we just use one score for everything?
Bayesian inference
Ever wondered how doctors update diagnoses as new symptoms arise?
MAP (mean average precision) measures: area under the precision-recall curve averaged across queries
Ever wondered how search engines rank your queries?
Swipe through more Machine Learning concepts
Open Pocket Polymath