Granger Causal Chain Discovery for Sepsis-Associated Derangements via Continuous-Time Hawkes Processes

TL;DR

This paper introduces a scalable continuous-time Hawkes process model to uncover and interpret causal event chains leading to sepsis using electronic medical record data, enabling early detection of adverse health events.

Contribution

It develops a novel linear multivariate Hawkes process with a ReLU link for inferring causal relationships in EMR data, including both exciting and inhibiting effects, and demonstrates its effectiveness on real patient data.

Findings

Identified interpretable Granger causal chains preceding sepsis.

Proposed a scalable two-phase gradient-based estimation method.

Validated the model's effectiveness through extensive simulations.

Abstract

Modern health care systems are conducting continuous, automated surveillance of the electronic medical record (EMR) to identify adverse events with increasing frequency; however, many events such as sepsis do not have elucidated prodromes (i.e., event chains) that can be used to identify and intercept the adverse event early in its course. Clinically relevant and interpretable results require a framework that can (i) infer temporal interactions across multiple patient features found in EMR data (e.g., Labs, vital signs, etc.) and (ii) identify patterns that precede and are specific to an impending adverse event (e.g., sepsis). In this work, we propose a linear multivariate Hawkes process model, coupled with ReLU link function, to recover a Granger Causal (GC) graph with both exciting and inhibiting effects. We develop a scalable two-phase gradient-based method to obtain a maximum surrogate-likelihood estimator, which is shown to be effective via extensive numerical simulation. Our method is subsequently extended to a data set of patients admitted to Grady hospital system in Atlanta, GA, USA, where the estimated GC graph identifies several highly interpretable GC chains that precede sepsis. The code is available at \url{https://github.com/SongWei-GT/two-phase-MHP}.