Explaining black-box text classifiers for disease-treatment information extraction

TL;DR

This paper presents a post-hoc explanation method using confident itemsets to interpret black-box neural network classifiers in biomedical text analysis, improving understanding of disease-treatment information extraction.

Contribution

It introduces a novel explanation approach that incorporates medical concepts and semantics, enhancing interpretability and fidelity over existing methods.

Findings

Outperforms perturbation-based explanators in fidelity.

Provides more interpretable explanations for biomedical NLP tasks.

Effective in approximating black-box classifier behavior.

Abstract

Deep neural networks and other intricate Artificial Intelligence (AI) models have reached high levels of accuracy on many biomedical natural language processing tasks. However, their applicability in real-world use cases may be limited due to their vague inner working and decision logic. A post-hoc explanation method can approximate the behavior of a black-box AI model by extracting relationships between feature values and outcomes. In this paper, we introduce a post-hoc explanation method that utilizes confident itemsets to approximate the behavior of black-box classifiers for medical information extraction. Incorporating medical concepts and semantics into the explanation process, our explanator finds semantic relations between inputs and outputs in different parts of the decision space of a black-box classifier. The experimental results show that our explanation method can outperform perturbation and decision set based explanators in terms of fidelity and interpretability of explanations produced for predictions on a disease-treatment information extraction task.