LCS-DIVE: An Automated Rule-based Machine Learning Visualization Pipeline for Characterizing Complex Associations in Classification

TL;DR

LCS-DIVE is an automated pipeline that interprets rule-based machine learning models, specifically Learning Classifier Systems, to uncover complex associations in biomedical data, enhancing interpretability and discovery.

Contribution

The paper introduces LCS-DIVE, a novel automated interpretation pipeline for rule-based ML models, integrating feature importance, association patterns, and subgroup analysis in biomedical classification.

Findings

Successfully differentiated complex associations in simulated datasets.

Effectively characterized associations in pancreatic cancer data.

Demonstrated scalability and interpretability of LCS-DIVE.

Abstract

Machine learning (ML) research has yielded powerful tools for training accurate prediction models despite complex multivariate associations (e.g. interactions and heterogeneity). In fields such as medicine, improved interpretability of ML modeling is required for knowledge discovery, accountability, and fairness. Rule-based ML approaches such as Learning Classifier Systems (LCSs) strike a balance between predictive performance and interpretability in complex, noisy domains. This work introduces the LCS Discovery and Visualization Environment (LCS-DIVE), an automated LCS model interpretation pipeline for complex biomedical classification. LCS-DIVE conducts modeling using a new scikit-learn implementation of ExSTraCS, an LCS designed to overcome noise and scalability in biomedical data mining yielding human readable IF:THEN rules as well as feature-tracking scores for each training sample. LCS-DIVE leverages feature-tracking scores and/or rules to automatically guide characterization of (1) feature importance (2) underlying additive, epistatic, and/or heterogeneous patterns of association, and (3) model-driven heterogeneous instance subgroups via clustering, visualization generation, and cluster interrogation. LCS-DIVE was evaluated over a diverse set of simulated genetic and benchmark datasets encoding a variety of complex multivariate associations, demonstrating its ability to differentiate between them and then applied to characterize associations within a real-world study of pancreatic cancer.