A New Interpretable Neural Network-Based Rule Model for Healthcare Decision Making

TL;DR

This paper introduces TT-rules, an interpretable neural network framework that extracts exact rule-based models from deep neural networks, achieving high performance and interpretability in healthcare decision-making tasks.

Contribution

The paper presents TT-rules, a novel method that transforms neural networks into accurate, interpretable rule-based models suitable for large healthcare datasets.

Findings

TT-rules achieves equal or higher performance than state-of-the-art methods.

It is the first rule-based model to accurately fit large tabular datasets.

Demonstrated effectiveness on real-life DNA datasets with over 20K features.

Abstract

In healthcare applications, understanding how machine/deep learning models make decisions is crucial. In this study, we introduce a neural network framework, $\textit{Truth Table rules}$ (TT-rules), that combines the global and exact interpretability properties of rule-based models with the high performance of deep neural networks. TT-rules is built upon $\textit{Truth Table nets}$ (TTnet), a family of deep neural networks initially developed for formal verification. By extracting the necessary and sufficient rules $\mathcal{R}$ from the trained TTnet model (global interpretability) to yield the same output as the TTnet (exact interpretability), TT-rules effectively transforms the neural network into a rule-based model. This rule-based model supports binary classification, multi-label classification, and regression tasks for small to large tabular datasets. After outlining the framework, we evaluate TT-rules' performance on healthcare applications and compare it to state-of-the-art rule-based methods. Our results demonstrate that TT-rules achieves equal or higher performance compared to other interpretable methods. Notably, TT-rules presents the first accurate rule-based model capable of fitting large tabular datasets, including two real-life DNA datasets with over 20K features.