Early Prediction of Sepsis in Hospitalized Patients Using a Machine Learning Algorithm, a Randomized Clinical Validation Trial.
Trial Snapshot
- Phase
- Not Applicable
- Status
- Completed
- Sponsor
- Enrollment
- 320
- Locations
- 1
- Primary Endpoint
- Validate the prognostic accuracy of the algorithm at predicting sepsis.
Study Overview
Brief Summary
In this clinical trial a novel Medical Device Software will be validated prospectively. The software incorporates a machine learning algorithm capable of predicting sepsis by using routine clinical variables in adult patients at Intensive Care Units.
Study Design
- Study Type
- Interventional
- Allocation
- Randomized
- Intervention Model
- Parallel
- Primary Purpose
- Diagnostic
- Masking
- Triple (Participant, Care Provider, Investigator)
Eligibility Criteria
- Ages
- 18 Years to — (Adult, Older Adult)
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Adult patient (age ≥18 years).
- •Patient is admitted to the ICU during the recruitment period of the trial.
Exclusion Criteria
- •Patient is participating in another interventional clinical trial which, as judged by the investigator, could potentially impact variables used by the sepsis prediction algorithm or has participated in such interventional clinical trial within the last 30 days.
- •Patient is known to be pregnant.
- •Death is deemed imminent and inevitable, at the investigator's discretion.
- •Patient has, due to chronic reduced mental capacity, been assessed by the investigator as incapable of making an informed decision
- •Patient has previously been enrolled in this trial.
Arms & Interventions
Standard of Care
Subjects are monitored for potential development of sepsis according to the local established clinical management guidelines.
Intervention: Blinded AlgoDx Sepsis Prediction Algorithm (Other)
Standard of Care + AlgoDx Sepsis Prediction Algorithm
Subjects are monitored for potential development of sepsis according to the local established clinical management guidelines, and sepsis prediction algorithm alerts are unblinded to clinical staff.
Intervention: Unblinded AlgoDx Sepsis Prediction Algorithm (Device)
Outcomes
Primary Outcomes
Validate the prognostic accuracy of the algorithm at predicting sepsis.
Time Frame: Up to 30 days (ICU hospitalization period)
In order to clinically validate the sepsis prediction performance the following endpoints have been selected: * accuracy, * specificity, and * sensitivity of the AlgoDx Sepsis Prediction Algorithm in the SoC group (not possible to assess these in the SoC + Algorithm cohort).
Secondary Outcomes
No secondary outcomes reported