CRTRE: Causal Rule Generation with Target Trial Emulation Framework

TL;DR

The paper introduces CRTRE, a novel framework combining causal rule generation with target trial emulation to improve interpretability and causal inference in biomedical prediction tasks, demonstrating superior performance across multiple healthcare datasets.

Contribution

CRTRE is a new method that applies trial design principles to generate causal association rules for better interpretability and causal effect estimation in nonlinear biomedical data.

Findings

Achieved a $eta$ error of 0.907, outperforming DWR and SVM.

Attained high accuracy on disease prediction datasets, e.g., 0.789 for Esophageal Cancer.

Secured AUC scores of 92.8 and 96.7 on MIMIC-III and MIMIC-IV, surpassing state-of-the-art models.

Abstract

Causal inference and model interpretability are gaining increasing attention, particularly in the biomedical domain. Despite recent advance, decorrelating features in nonlinear environments with human-interpretable representations remains underexplored. In this study, we introduce a novel method called causal rule generation with target trial emulation framework (CRTRE), which applies randomize trial design principles to estimate the causal effect of association rules. We then incorporate such association rules for the downstream applications such as prediction of disease onsets. Extensive experiments on six healthcare datasets, including synthetic data, real-world disease collections, and MIMIC-III/IV, demonstrate the model's superior performance. Specifically, our method achieved a $\beta$ error of 0.907, outperforming DWR (1.024) and SVM (1.141). On real-world datasets, our model achieved accuracies of 0.789, 0.920, and 0.300 for Esophageal Cancer, Heart Disease, and Cauda Equina Syndrome prediction task, respectively, consistently surpassing baseline models. On the ICD code prediction tasks, it achieved AUC Macro scores of 92.8 on MIMIC-III and 96.7 on MIMIC-IV, outperforming the state-of-the-art models KEPT and MSMN. Expert evaluations further validate the model's effectiveness, causality, and interpretability.