AIF-C01 Fundamentals of AI and ML Practice Question

A hospital wants to detect pneumonia from chest X-ray images. Radiologists have already labeled thousands of past X-rays as either 'pneumonia' or 'no pneumonia'. The hospital wants a model that generalizes to new X-rays. Which type of machine learning task is this?

⚠ Common exam trap

The trap here is assuming medical imaging must use unsupervised anomaly detection, when the presence of radiologist-assigned labels makes it supervised classification.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Supervised image classification

Labeled images with known diagnoses are the defining input for supervised classification. The model learns from pneumonia and no-pneumonia examples and predicts the class for new X-rays, which is precisely the generalization the hospital wants. Unsupervised, clustering, and reinforcement approaches either ignore the labels or lack the required structure.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Reinforcement learning
Why it's wrong here
Reinforcement learning requires an agent taking actions and receiving rewards over time. Diagnosing a static X-ray is a single prediction with no sequential decision-making, environment, or reward signal. The labeled images instead point to supervised learning, not reinforcement learning.
✓
Supervised image classification
Why this is correct
The labeled X-rays provide input images paired with correct diagnoses, which is exactly the training data supervised classification needs. A convolutional neural network can learn visual patterns distinguishing pneumonia from normal lungs and then predict on unseen X-rays, matching the hospital's goal of generalization.
✗
Unsupervised anomaly detection
Why it's wrong here
Anomaly detection finds unusual records without labeled examples of normal and abnormal. Here thousands of X-rays already carry explicit pneumonia or no-pneumonia labels, so the task is not about discovering outliers in unlabeled data. The existing ground truth makes this a supervised problem instead.
✗
Clustering
Why it's wrong here
Clustering groups similar unlabeled records. The hospital's X-rays are already labeled by radiologists into two known diagnostic classes, so there is no need to discover latent groups. Clustering would ignore the valuable labels and cannot directly output the pneumonia diagnosis the hospital needs.

Go deeper

AIF-C01 Fundamentals of AI and ML Practice Question

Why each option matters

Option-by-option breakdown

Related to this question