A Theory of Diagnostic Interpretation in Supervised Classification

TL;DR

This paper presents a formal computational framework for interpretability in supervised classification, defining interpretability as maximal information gain through finite communication, and provides an algorithm to quantify diagnostic interpretability.

Contribution

It introduces a novel theoretical model for diagnostic interpretability that removes subjective bias and does not rely on accuracy-interpretability tradeoffs, with an algorithm to compute interpretability.

Findings

Algorithm successfully calculates diagnostic interpretability in synthetic scenarios.

Interpretability is framed as maximal information gain within finite communication.

The model demonstrates effectiveness across various complexity levels in simulations.

Abstract

Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational formulation of black-box interpretation, general interpretability research rely heavily on subjective bias. Clear decision structure of the medical diagnostics lets us approximate the decision process of a radiologist as a model - removed from subjective bias. We define the process of interpretation as a finite communication between a known model and a black-box model to optimally map the black box's decision process in the known model. Consequently, we define interpretability as maximal information gain over the initial uncertainty about the black-box's decision within finite communication. We relax this definition based on the observation that diagnostic interpretation is typically achieved by a process of minimal querying. We derive an algorithm to calculate diagnostic interpretability. The usual question of accuracy-interpretability tradeoff, i.e. whether a black-box model's prediction accuracy is dependent on its ability to be interpreted by a known source model, does not arise in this theory. With multiple example simulation experiments of various complexity levels, we demonstrate the working of such a theoretical model in synthetic supervised classification scenarios.