Sepsis Clinical Decision Support [CDS] Master Enrollment Study Protocol
Sepsis Onset Warning System [SOWS] Master Enrollment Study Protocol
1 other identifier
observational
40,000
1 country
10
Brief Summary
This protocol will collect real-world data retrospectively from the electronic health record (EHR) as data obtained from the delivery of routine medical care to develop a machine learning (ML)-based Clinical Decision Support (CDS) system for severe sepsis prediction and detection.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for all trials
Started Feb 2021
Longer than P75 for all trials
10 active sites
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
Study Start
First participant enrolled
February 15, 2021
CompletedFirst Submitted
Initial submission to the registry
March 23, 2022
CompletedFirst Posted
Study publicly available on registry
March 31, 2022
CompletedPrimary Completion
Last participant's last visit for primary outcome
March 30, 2025
CompletedStudy Completion
Last participant's last visit for all outcomes
December 31, 2026
ExpectedJune 21, 2024
June 1, 2024
4.1 years
March 23, 2022
June 20, 2024
Conditions
Outcome Measures
Primary Outcomes (1)
Severe Sepsis
Identify patients having Severe Sepsis with the use of electronic health data
Within 6 hours from presentation to the emergency department
Secondary Outcomes (3)
Mortality
Within 6hours from presentation to the emergency department
Length of Stay
Within 6hours from presentation to the emergency department
Re-admission Rates
Within 6hours from presentation to the emergency department
Study Arms (1)
Primary Objective: Severe Sepsis
The primary endpoint for this study is defined as the presence of sufficient data for SOWS training and algorithm development to proceed with subsequent validation. To provide sufficient data subsets (severe sepsis EHR encounters) for training and validation of the Sepsis Onset Warning System algorithm. There will not be any interventions administered.
Eligibility Criteria
This protocol has open enrollment to all genders, ages, and health statuses in patients admitted to the hospital or presenting to the ED.
You may qualify if:
- All races, ages and ethnicities
- All patients admitted to the hospital or presenting to the Emergency Department
You may not qualify if:
- Patients not presenting to a hospital setting (e.g. urgent care, outpatient clinic excluded).
Contact the study team to confirm eligibility.
Sponsors & Collaborators
Study Sites (10)
University of California, Irvine
Irvine, California, 92697, United States
Augusta University Medical School
Augusta, Georgia, 30912, United States
Indiana University Health
Indianapolis, Indiana, 46202-5200, United States
University Health/ Truman Medical Center
Kansas City, Missouri, 64108, United States
University of Kansas Medical Center
Kansas City, Missouri, 66103, United States
Hackensack University Medical Center
Hackensack, New Jersey, 07601, United States
WakeMed Health
Raleigh, North Carolina, 27610, United States
University of Cininnati
Cincinnati, Ohio, 45221, United States
MetroHealth Systems
Cleveland, Ohio, 44109, United States
The Ohio State University
Columbus, Ohio, 43210, United States
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Officials
- PRINCIPAL INVESTIGATOR
Elliott Crouser, MD
Ohio State University
Study Design
- Study Type
- observational
- Observational Model
- COHORT
- Time Perspective
- RETROSPECTIVE
- Sponsor Type
- INDUSTRY
- Responsible Party
- SPONSOR
Study Record Dates
First Submitted
March 23, 2022
First Posted
March 31, 2022
Study Start
February 15, 2021
Primary Completion
March 30, 2025
Study Completion (Estimated)
December 31, 2026
Last Updated
June 21, 2024
Record last verified: 2024-06
Data Sharing
- IPD Sharing
- Will not share
Data elements will be retrospectively extracted from electronic health records from the respective sites and fed into the algorithm for performance testing. These data elements will not be shared with other researchers