Comparison of Sepsis Prediction Algorithms

Official title

Prospective Evaluation of Sepsis Prediction Algorithms in a Multi-Hospital Healthcare System

Overview

Sepsis is a severe response to infection resulting in organ dysfunction and often leading to death. More than 1.5 million people get sepsis every year in the U.S., and 270,000 Americans die from sepsis annually. Delays in the diagnosis of sepsis lead to increased mortality. Several clinical decision support algorithms exist for the early identification of sepsis. The research team will compare the performance of three sepsis prediction algorithms to identify the algorithm that is most accurate and clinically actionable. The algorithms will run in the background of the electronic health record (EHR) and the predictions will not be revealed to patients or clinical staff. In this current evaluation study, the algorithms will not affect any part of a patient's care. The algorithms will be deployed across the Emory healthcare system on data from all patients presenting to the emergency department.

Detailed description

The primary goal of this study is to prospectively evaluate three sepsis prediction algorithms that are embedded in the EHR. The models will be deployed in a "shadow" mode, and the results will not be displayed to the treatment team during this study. Two of the algorithms are proprietary algorithms of the EHR provider (Epic). The third algorithm is an internally developed, open-source algorithm.

The algorithms will compute the probability of sepsis at periodic intervals and will continue to run on a patient's data until the patient's discharge, death, or upon initiation of intravenous antibiotics (at which point there is an indirect record of clinical suspicion of an infection).

Interventions

• Other Epic Sepsis Model Version - 1
  The Epic Sepsis Model (ESM) version 1, a proprietary sepsis prediction model.
• Other Epic Sepsis Model Version - 2
  The Epic Sepsis Model (ESM) version 2, a proprietary sepsis prediction model.
• Other Emory Sepsis Model
  Emory internal algorithm

Primary outcome measures

• Patient hospitalization-level area under curve (AUC) for identification of sepsis, [Time frame: Duration of hospital stay (until discharge or death), an expected average of 30 days]

Secondary outcome measures (7)

• Sensitivity, specificity, and Positive and Negative Predictive Value of algorithms [Time frame: Duration of hospital stay (until discharge or death), an expected average of 30 days]
• Lead time to antibiotic administration [Time frame: Duration of hospital stay (until discharge or death), an expected average of 30 days]
• Percent expected increase in unnecessary antibiotics [Time frame: Duration of hospital stay (until discharge or death), an expected average of 30 days]
• Number needed to screen [Time frame: Duration of hospital stay (or death), an expected average of 30 days]
• Number of Total and false alert burden [Time frame: Duration of hospital stay (until discharge or death), an expected average of 30 days]
• Time-horizon based AUCs [Time frame: 4 hours, 8 hours, and 24 hours]
• Accuracy and calibration by subgroup [Time frame: Duration of hospital stay (until discharge or death), an expected average of 30 days]

Eligibility criteria

Inclusion criteria

• All adult patients admitted through the ED

Exclusion criteria

• None

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

United States · 7 centers

• Emory Midtown Hospital — Atlanta
• Emory Saint Joseph's Hospital — Atlanta
• Emory Healthcare System — Atlanta
• Emory Hospital — Atlanta
• Emory Decatur Hospital — Decatur
• Emory Johns Creek Hospital — Johns Creek
• Emory Hillandale Hospital — Lithonia

Identifiers

NCT: NCT05943938 · STUDY00005958 · 2024P008316

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗