Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureHard
A healthcare provider is using a machine learning model to predict the risk of a patient developing a rare but severe disease. The model has been trained and achieved high accuracy on a dataset where healthy patients vastly outnumber those with the disease. During evaluation, it's observed that while the model rarely misclassifies a healthy person as having the disease, it frequently fails to detect actual disease cases among the sick. Which type of error is the model making that is of most concern in this critical medical scenario?
- ATrue Negative
- BFalse Positive (Type I Error)
- CTrue Positive
- DFalse Negative (Type II Error)
Show answer & explanationAnswer & explanation
Correct answer: D. False Negative (Type II Error)
A False Negative (Type II Error) occurs when the model predicts a negative outcome, but the actual outcome is positive. In this medical context, it means the model fails to detect an actual disease case, which is a critical and potentially life-threatening error that must be minimized.
Why the other options are wrong
- A. True Negative is a correct prediction of a negative outcome (correctly identifying a healthy person), which is desirable.
- B. A False Positive (Type I Error) means predicting a positive outcome when it's actually negative (misclassifying a healthy person as sick). While undesirable, it's less critical than missing an actual disease.
- C. True Positive is a correct prediction of a positive outcome (correctly identifying a sick person), which is desirable.
False Negative (Type II Error)
A classification error where the model incorrectly predicts a negative outcome when the actual outcome is positive. It means the model failed to detect an instance of the positive class.
- Also known as a Type II Error.
- Represents a 'miss' or 'under-detection' of the positive class.
- Often more costly or dangerous than False Positives in critical applications (e.g., medical diagnosis, security systems).
Memory trick: When the doctor's AI makes a wrong call.