AI0-001 AI Concepts and Techniques Practice Question
A hospital's AI team is building a model that estimates a patient's 10-year risk of developing heart disease from 30 clinical and lifestyle variables. A cardiologist asks the team to explain why the model produced a high-risk score for a specific patient, because clinicians are legally required to justify their recommendations. The team needs a technique that assigns a numeric contribution to each input feature for that individual prediction. Which approach should the team use?
⚠ Common exam trap
The trap here is assuming that any feature importance output explains an individual prediction, when most built-in importance measures are global averages across the whole dataset.
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
✓
SHAP (SHapley Additive exPlanations) values
The clinician needs a per-instance explanation that quantifies how each input variable contributed to one patient's predicted risk. SHAP values satisfy this because they compute additive feature attributions grounded in Shapley values, and their sum reconstructs the model's output for that individual. Aggregate importance, confusion matrices, and cross-validation all describe model behavior across datasets or thresholds rather than explaining a single prediction.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Confusion matrix analysis on a held-out validation set
Why it's wrong here
A confusion matrix summarizes counts of true positives, false positives, true negatives, and false negatives for a classification threshold. It tells the team how often the model is right or wrong overall, but it contains no information about which features influenced any single prediction. It therefore cannot explain why one specific patient received a high-risk score, making it irrelevant to the cardiologist's request.
- ✓
SHAP (SHapley Additive exPlanations) values
Why this is correct
SHAP values come from cooperative game theory and distribute the prediction among the input features, giving each feature a signed numeric contribution for the single patient being explained. Because the sum of the SHAP values plus the base value reconstructs the model output, the cardiologist can see exactly how much variables such as blood pressure or cholesterol pushed the risk score up or down, which satisfies the need for a per-patient justification.
- ✗
k-fold cross-validation with stratified sampling
Why it's wrong here
Cross-validation is a resampling procedure that estimates how well a model generalizes by training and testing on different folds of the data. It produces performance statistics such as mean accuracy or AUC, not feature-level attributions. Running k-fold here would not reveal which clinical variables raised this patient's risk score, so it does not address the explainability requirement the hospital faces.
- ✗
Global feature importance from a random forest's mean decrease in impurity
Why it's wrong here
Mean decrease in impurity is computed across the entire training set and describes which features matter to the model overall. For this patient, it cannot say whether cholesterol or age drove the particular high-risk score, because the same ranking would be reported for every patient. The cardiologist needs an individualized justification, so an aggregate importance measure fails to answer the clinical question being asked.
About these practice questions
One of 962 original AI0-001 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official CompTIA exam blueprint
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.