SEPSys and RESCUE Scores for Sepsis Prediction

Not yet recruiting at 7 trial locations

Overseen By Jason Heavner, MD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Maryland, Baltimore

Disqualifiers: Pediatric, Psychiatric, Sepsis, High RESCUE, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests two new risk scores to predict serious health events like sepsis (a severe infection) or sudden health deterioration in hospital patients. The goal is to increase doctors' awareness of these risks by using the SEPSys (UMMS Sepsis Early Prediction Score) and RESCUE scores. These tools estimate the likelihood of a patient encountering these issues within four hours. Suitable candidates for this trial are adult patients admitted to a participating hospital unit who have not been diagnosed with sepsis. As an unphased trial, this study allows patients to contribute to innovative research that could improve early detection and intervention strategies in hospitals.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial coordinators or your doctor.

What prior data suggests that these risk scores are safe for predicting sepsis and deterioration?

Research has shown that the RESCUE Score and SEPSys predict the risk of sepsis and other serious health issues in patients. These scores are not treatments or medications, so they lack the safety concerns associated with drugs. Instead, they assist doctors in evaluating a patient's risk of developing sepsis or facing severe health problems.

These tools use data to predict risks, and studies have demonstrated that similar models can provide early warnings. This enables healthcare providers to act quickly if a patient's condition might worsen. It's important to understand that these scores support, not replace, a doctor's professional judgment.

As prediction tools, not physical treatments, they do not directly cause side effects. However, correct usage and accurate interpretation of their results are crucial to ensure patient safety. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the SEPSys and RESCUE Scores because they offer a new way to predict sepsis early. Unlike current methods that rely heavily on clinical assessments and lab results often available only after a delay, these scores aim to provide quicker, data-driven insights. SEPSys focuses on analyzing patient data to identify early signs of sepsis, while RESCUE uses a distinct algorithm to enhance prediction accuracy. This could lead to faster interventions and potentially improve outcomes for patients at risk of sepsis.

What evidence suggests that the SEPSys and RESCUE scores are effective for predicting sepsis and patient deterioration?

In this trial, participants will be assessed using different scoring systems to predict health risks. Research has shown that the SEPSys score, used for some participants, employs advanced computer techniques to predict the risk of sepsis within four hours. It is highly accurate, particularly with methods like the Random Forest, a type of computer program. The RESCUE Score, used for other participants, predicts the risk of serious events such as cardiac arrest or death within the same timeframe. Although information about RESCUE is limited, these tools can help doctors act quickly to prevent worse outcomes. Some participants will be assessed using both SEPSys and RESCUE together, potentially providing a more complete view of a patient's immediate health risks. ^{1 2 5 6 7}

Are You a Good Fit for This Trial?

This trial is for patients at risk of sepsis or sudden health decline, including conditions like umbilical sepsis and pre-eclampsia. Specific inclusion and exclusion criteria are not detailed here.

Inclusion Criteria

Additional RESCUE Encounter Inclusion Criteria: Encounter has a RESCUE Score

Hospital Unit Inclusion Criteria: Units are part of a member hospital of the University of Maryland Medical System (UMMS)

Units agree to participate in the study

Exclusion Criteria

Additional RESCUE Encounter Exclusion Criteria: Encounter is admitted with a high RESCUE Score (RESCUE Score of 4)

My treatment center focuses on children under 18.

I was admitted to the hospital with sepsis.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Baseline

Hospitals operate without SEPSys or RESCUE Scores to establish baseline data

Varies

Intervention

Hospitals are randomized to receive either SEPSys or RESCUE Score, followed by both scores

Several months

Follow-up

Participants are monitored for safety and effectiveness after intervention

Up to 24 hours post-elevation of risk scores

What Are the Treatments Tested in This Trial?

Interventions

• RESCUE Score
• UMMS Sepsis Early Prediction Score (SEPSys)

Trial Overview

The study tests two new scores: SEPSys predicts the four-hour risk of developing sepsis, while RESCUE predicts the same timeframe risk of deterioration (like cardiac arrest). It aims to alert healthcare providers early.

How Is the Trial Designed?

Group I: SEPSys+RESCUE Experimental Treatment 2 Interventions

Cluster has both SEPSys \& RESCUE Scores

Group II: SEPSys Experimental Treatment 1 Intervention

Cluster has SEPSys Score only

Group III: RESCUE Experimental Treatment 1 Intervention

Cluster has RESCUE Score only

Group IV: Baseline Active Control 1 Intervention

Cluster has neither SEPSys nor RESCUE

Who Is Running the Clinical Trial?

University of Maryland, Baltimore

Lead Sponsor

Trials

729

Recruited

540,000+

University of Maryland Medical System

Collaborator

Trials

2

Recruited

150,000+

Citations

1.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC11973177/

A methodological systematic review of validation and ...

Sepsis real-time prediction models (SRPMs) provide timely alerts and may improve patient outcomes but face limited clinical adoption due to ...

2.

withpower.com

withpower.com/trial/phase-sepsis-2-2025-acc7b

SEPSys and RESCUE Scores for Sepsis Prediction

The primary outcome will be the time from when the risk score becomes elevated to when vital signs such as heart rate or blood pressure are measured, suggesting ...

3.

ai.nejm.org

ai.nejm.org/doi/full/10.1056/AIoa2400867

FDA-Authorized AI/ML Tool for Sepsis Prediction

The Sepsis ImmunoScore demonstrated high overall diagnostic accuracy for predicting sepsis, with an AUC in the derivation set of 0.85 (95% ...

4.

nature.com

nature.com/articles/s41598-025-85121-z

Interpretable machine learning for predicting sepsis risk in ...

The study aimed to develop and validate a sepsis prediction model using structured electronic medical records (sEMR) and machine learning ...

5.

jamanetwork.com

jamanetwork.com/journals/jamainternalmedicine/fullarticle/2781307

External Validation of a Widely Implemented Sepsis ...

This cohort study externally validates the Epic Sepsis Model in the prediction of sepsis and evaluates its potential clinical impact ...

6.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC12166316/

Intelligent Prediction Platform for Sepsis Risk Based on Real ...

This platform provides real-time dynamic warnings for sepsis risk in critically ill ICU patients, supporting timely clinical decision-making.

7.

trial.medpath.com

trial.medpath.com/clinical-trial/7ae8a9eea438d0f5/nct06779617-sepsis-prediction-rescue-score-trial

UMMS Sepsis Early Prediction Score (SEPSys) and RESCUE ...

An elevated SEPSys or RESCUE Score is defined as a current SEPSys or RESCUE Score of 3 or 4 (highest risk) when the previous Score was a 1 (lowest risk) or 2.