KG-TREAT: Pre-training for Treatment Effect Estimation by Synergizing Patient Data with Knowledge Graphs

TL;DR

KG-TREAT introduces a pre-training framework that combines patient data with biomedical knowledge graphs to improve treatment effect estimation, addressing data sparsity and high dimensionality issues.

Contribution

It develops a novel dual-focus knowledge graph construction and a bi-level attention fusion method, along with pre-training tasks, to enhance TEE accuracy.

Findings

Achieves 7% average AUC improvement over existing methods.

Attains 9% higher IF-PEHE, indicating better effect estimation.

Aligns well with clinical trial results, validating effectiveness.

Abstract

Treatment effect estimation (TEE) is the task of determining the impact of various treatments on patient outcomes. Current TEE methods fall short due to reliance on limited labeled data and challenges posed by sparse and high-dimensional observational patient data. To address the challenges, we introduce a novel pre-training and fine-tuning framework, KG-TREAT, which synergizes large-scale observational patient data with biomedical knowledge graphs (KGs) to enhance TEE. Unlike previous approaches, KG-TREAT constructs dual-focus KGs and integrates a deep bi-level attention synergy method for in-depth information fusion, enabling distinct encoding of treatment-covariate and outcome-covariate relationships. KG-TREAT also incorporates two pre-training tasks to ensure a thorough grounding and contextualization of patient data and KGs. Evaluation on four downstream TEE tasks shows KG-TREAT's superiority over existing methods, with an average improvement of 7% in Area under the ROC Curve (AUC) and 9% in Influence Function-based Precision of Estimating Heterogeneous Effects (IF-PEHE). The effectiveness of our estimated treatment effects is further affirmed by alignment with established randomized clinical trial findings.