AI0-001 AI Governance and Ethics Practice Question
A healthcare AI startup is developing a model to predict patient readmission risk. The company wants to ensure the model's decisions can be understood by clinicians. Which explainability technique provides local, model-agnostic explanations by fitting a simple surrogate model around a prediction?
⚠ Common exam trap
Candidates may confuse SHAP with LIME because both provide local, model-agnostic explanations, but LIME fits a surrogate model (e.g., linear regression) around the prediction, whereas SHAP uses Shapley values from game theory.
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
✓
LIME
LIME (Local Interpretable Model-agnostic Explanations) is the correct technique because it generates local explanations by fitting a simple, interpretable surrogate model (e.g., linear regression or decision tree) around a specific prediction. It is model-agnostic, meaning it works with any black-box classifier, and it perturbs the input data near the instance of interest to understand which features most influenced the 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.
- ✗
SHAP values
Why it's wrong here
SHAP values attribute a prediction using Shapley values from cooperative game theory, not by fitting a simple surrogate model around it. They are tempting because SHAP is model-agnostic and local, and would be correct when the requirement is additive feature-attribution values rather than an interpretable surrogate.
- ✓
LIME
Why this is correct
LIME fits a sparse linear surrogate around each individual prediction, so clinicians receive a local, model-agnostic explanation of which features drove that specific readmission risk score, satisfying the interpretability requirement without exposing the underlying model's internals.
- ✗
Attention visualisation
Why it's wrong here
Attention visualisation exposes internal weights of transformer architectures, so it is model-specific and not a surrogate fitted around a prediction. It is tempting because attention maps look like local explanations, and would be correct when interpreting a transformer's own token weighting rather than any black-box model.
- ✗
Model cards
Why it's wrong here
Model cards are static documentation describing a model's intended use, performance and limitations; they generate no per-prediction surrogate. They are tempting because model cards do support transparency and governance, and would be correct when the requirement is documented model-level reporting rather than local explanations.
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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.