REM: An Integrative Rule Extraction Methodology for Explainable Data Analysis in Healthcare

Abstract

Deep learning models are receiving increasing attention in clinical decision-making, however the lack of interpretability and explainability impedes their deployment in day-to-day clinical practice. We propose REM, an interpretable and explainable methodology for extracting rules from deep neural networks and combining them with other data-driven and knowledge-driven rules. This allows integrating machine learning and reasoning for investigating applied and basic biological research questions. We evaluate the utility of REM on the predictive tasks of classifying histological and immunohistochemical breast cancer subtypes from genotype and phenotype data. We demonstrate that REM efficiently extracts accurate, comprehensible and, biologically relevant rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches. REM provides explanation facilities for predictions and enables the clinicians to validate and calibrate the extracted rulesets with their domain knowledge. With these functionalities, REM caters for a novel and direct human-in-the-loop approach in clinical decision making.

Artificial Intelligence You Can Trust: What Matters Beyond Performance When Applying Artificial Intelligence to Renal Histopathology?

“…To address this, boosting algorithms can advance the performance of random forest–based models by using them to approximate the workings of highly performant neural networks 54 . Post hoc , researchers aim to extract nodes from the forest that are most important to its performance and use these key rules to provide explanations of “why” a particular choice was made 55 . Alternatively, key nodes could be used to select “concepts” that are provided to a neural network model during its training.…”

“…54 Post hoc, researchers aim to extract nodes from the forest that are most important to its performance and use these key rules to provide explanations of "why" a particular choice was made. 55 Alternatively, key Figure 3. The same artery is sectioned in two different planes according to its orientation when the cut is made.…”

Explainable Machine Learning with Prior Knowledge: An Overview

“…Formalized Priors for Explanations Shams et al [67] propose a methodology which extracts conditional rules from deep neural networks and combines them with other data-driven and knowledge-driven ones. Clinicians are able to directly validate and calibrate the extracted rules with their domain knowledge to yield more precise and acceptable explanations.…”