Introducing {\delta}-XAI: a novel sensitivity-based method for local AI explanations

TL;DR

This paper introduces delta-XAI, a sensitivity-based local explanation method for AI models that assesses feature impact on individual predictions, showing promising results compared to Shapley values especially with extreme feature values.

Contribution

The paper presents delta-XAI, a novel local explanation technique extending the delta index, providing intuitive and sensitive feature impact assessments for individual predictions in ML models.

Findings

Delta-XAI aligns well with Shapley values in general cases.

It detects dominant features more sensitively, especially with extreme feature values.

Provides intuitive explanations using probability density functions.

Abstract

Explainable Artificial Intelligence (XAI) is central to the debate on integrating Artificial Intelligence (AI) and Machine Learning (ML) algorithms into clinical practice. High-performing AI/ML models, such as ensemble learners and deep neural networks, often lack interpretability, hampering clinicians' trust in their predictions. To address this, XAI techniques are being developed to describe AI/ML predictions in human-understandable terms. One promising direction is the adaptation of sensitivity analysis (SA) and global sensitivity analysis (GSA), which inherently rank model inputs by their impact on predictions. Here, we introduce a novel delta-XAI method that provides local explanations of ML model predictions by extending the delta index, a GSA metric. The delta-XAI index assesses the impact of each feature's value on the predicted output for individual instances in both regression and classification problems. We formalize the delta-XAI index and provide code for its implementation. The delta-XAI method was evaluated on simulated scenarios using linear regression models, with Shapley values serving as a benchmark. Results showed that the delta-XAI index is generally consistent with Shapley values, with notable discrepancies in models with highly impactful or extreme feature values. The delta-XAI index demonstrated higher sensitivity in detecting dominant features and handling extreme feature values. Qualitatively, the delta-XAI provides intuitive explanations by leveraging probability density functions, making feature rankings clearer and more explainable for practitioners. Overall, the delta-XAI method appears promising for robustly obtaining local explanations of ML model predictions. Further investigations in real-world clinical settings will be conducted to evaluate its impact on AI-assisted clinical workflows.