Inference of Dependency Knowledge Graph for Electronic Health Records

TL;DR

This paper introduces a novel statistical inference framework for constructing sparse, reliable knowledge graphs from Electronic Health Records, improving interpretability and feature selection in healthcare data analysis.

Contribution

It presents the first inferential method with statistical guarantees for dependency knowledge graphs derived from EHR data, addressing privacy and data limitations.

Findings

Scalable SVD-based estimation of KG embeddings

Asymptotic normality enabling controlled edge recovery

Successful application to real-world EHR data

Abstract

The effective analysis of high-dimensional Electronic Health Record (EHR) data, with substantial potential for healthcare research, presents notable methodological challenges. Employing predictive modeling guided by a knowledge graph (KG), which enables efficient feature selection, can enhance both statistical efficiency and interpretability. While various methods have emerged for constructing KGs, existing techniques often lack statistical certainty concerning the presence of links between entities, especially in scenarios where the utilization of patient-level EHR data is limited due to privacy concerns. In this paper, we propose the first inferential framework for deriving a sparse KG with statistical guarantee based on the dynamic log-linear topic model proposed by \cite{arora2016latent}. Within this model, the KG embeddings are estimated by performing singular value decomposition on the empirical pointwise mutual information matrix, offering a scalable solution. We then establish entrywise asymptotic normality for the KG low-rank estimator, enabling the recovery of sparse graph edges with controlled type I error. Our work uniquely addresses the under-explored domain of statistical inference about non-linear statistics under the low-rank temporal dependent models, a critical gap in existing research. We validate our approach through extensive simulation studies and then apply the method to real-world EHR data in constructing clinical KGs and generating clinical feature embeddings.