Evolutionary Causal Discovery with Relative Impact Stratification for Interpretable Data Analysis

TL;DR

This paper introduces Evolutionary Causal Discovery (ECD), a novel method combining genetic programming and impact stratification to improve interpretability and accuracy in causal analysis of complex datasets, especially in healthcare.

Contribution

ECD advances causal discovery by integrating variable relationship parsing with impact stratification, providing interpretable visualizations and robust results on real-world data.

Findings

ECD accurately uncovers variable relationships in synthetic data.

ECD reveals meaningful causal patterns in EHR data.

High stability of ECD across noise levels.

Abstract

This study proposes Evolutionary Causal Discovery (ECD) for causal discovery that tailors response variables, predictor variables, and corresponding operators to research datasets. Utilizing genetic programming for variable relationship parsing, the method proceeds with the Relative Impact Stratification (RIS) algorithm to assess the relative impact of predictor variables on the response variable, facilitating expression simplification and enhancing the interpretability of variable relationships. ECD proposes an expression tree to visualize the RIS results, offering a differentiated depiction of unknown causal relationships compared to conventional causal discovery. The ECD method represents an evolution and augmentation of existing causal discovery methods, providing an interpretable approach for analyzing variable relationships in complex systems, particularly in healthcare settings with Electronic Health Record (EHR) data. Experiments on both synthetic and real-world EHR datasets demonstrate the efficacy of ECD in uncovering patterns and mechanisms among variables, maintaining high accuracy and stability across different noise levels. On the real-world EHR dataset, ECD reveals the intricate relationships between the response variable and other predictive variables, aligning with the results of structural equation modeling and shapley additive explanations analyses.