A novel method for Causal Structure Discovery from EHR data, a demonstration on type-2 diabetes mellitus

TL;DR

This paper introduces a new data transformation and causal discovery algorithm tailored for EHR data, demonstrating improved accuracy and stability in uncovering disease mechanisms, specifically applied to type-2 diabetes mellitus.

Contribution

The paper presents a novel data transformation and causal structure discovery method that overcomes EHR data challenges, enhancing causal inference accuracy and robustness.

Findings

Improved causal graph correctness and edge orientation consistency.

Enhanced accuracy, stability, and completeness over existing methods.

Validated generalizability through external dataset validation.

Abstract

Introduction: The discovery of causal mechanisms underlying diseases enables better diagnosis, prognosis and treatment selection. Clinical trials have been the gold standard for determining causality, but they are resource intensive, sometimes infeasible or unethical. Electronic Health Records (EHR) contain a wealth of real-world data that holds promise for the discovery of disease mechanisms, yet the existing causal structure discovery (CSD) methods fall short on leveraging them due to the special characteristics of the EHR data. We propose a new data transformation method and a novel CSD algorithm to overcome the challenges posed by these characteristics. Materials and methods: We demonstrated the proposed methods on an application to type-2 diabetes mellitus. We used a large EHR data set from Mayo Clinic to internally evaluate the proposed transformation and CSD methods and used another large data set from an independent health system, Fairview Health Services, as external validation. We compared the performance of our proposed method to Fast Greedy Equivalence Search (FGES), a state-of-the-art CSD method in terms of correctness, stability and completeness. We tested the generalizability of the proposed algorithm through external validation. Results and conclusions: The proposed method improved over the existing methods by successfully incorporating study design considerations, was robust in face of unreliable EHR timestamps and inferred causal effect directions more correctly and reliably. The proposed data transformation successfully improved the clinical correctness of the discovered graph and the consistency of edge orientation across bootstrap samples. It resulted in superior accuracy, stability, and completeness.