JMIR Publications

ABSTRACT

Background:

Recent attempts at clinical phenotyping for sepsis have shown promise in identifying groups of patients with distinct treatment responses. Nonetheless, the replicability and actionability of these phenotypes remains an issue since the patient trajectory is a function of both the patient’s physiological state as well as the interventions they receive.

Objective:

We aimed to develop a novel approach for deriving clinical phenotypes using unsupervised learning and transition modeling.

Methods:

Forty commonly used clinical variables from the electronic health record were used as inputs to a feed-forward neural network trained to predict the onset of sepsis. Using spectral clustering on the representations from this network we derived and validated consistent phenotypes across a diverse cohort of sepsis patients. We modeled phenotype dynamics as a Markov decision process with transitions as a function of the patient’s current state and the interventions they received.

Results:

Four consistent and distinct phenotypes were derived from over 11,500 adult patients who were admitted from the UCSD ED with sepsis between January 1, 2016 - January 31, 2020. Over 2,000 adult patients admitted from the UCI ED with sepsis between November 4, 2017 - August 4, 2022 were used for external validation. We demonstrate that sepsis phenotypes are not static and evolve in response to physiological factors and based on interventions. We show that roughly 45% of patients change phenotype membership within the first 6 hours of ED arrival. We observe consistent trends in patient dynamics as a function of interventions including early administration of antibiotics.

Conclusions:

We derive and describe 4 sepsis phenotypes present within 6 hours of triage in the ED. We observe that the administration of a 30 mL/kg fluid bolus may be associated with worse outcomes in certain phenotypes whereas prompt antimicrobial therapy is associated with improved outcomes.