June 27, 2024Advanced Intelligent SystemsOpen Access

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

View Full Paper

Ask AI

Bookmark

Explainability outputs from popular tools vary considerably across models, and feature collinearity severely distorts feature importance in myocardial infarction classification.
Case study evaluation in myocardial infarction classification analyzes how machine learning architectures alter explainability metrics under severe feature collinearity.
Highlights the urgent need for caution when deploying explainable artificial intelligence tools, as misleading feature attributions may compromise clinical decision-making.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Perspective analysis reveals that SHAP and LIME explanations are distorted by feature collinearity in myocardial infarction classification, highlighting caution when interpreting black-box models.

Cite This Study

Salih et al. (2024) studied this question.

synapsesocial.com/papers/68e62ea5b6db6435875c13bb https://doi.org/10.1002/aisy.202400304

View Full Paper

Ask AI

Bookmark

Implication

Perspective analysis reveals that SHAP and LIME explanations are distorted by feature collinearity in myocardial infarction classification, highlighting caution when interpreting black-box models.

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

Key Points

Discussion

Implication

Cite This Study

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider