GRADY: a computer tool to detect early sepsis and gram-negative bloodstream infection in ICU patients

Prospective Validation of the GRADY Bacteremia/Sepsis Prediction Model in Intensive Care Unit Patients: Clinical Performance and Feasibility as an Early Warning System

Observational Sisli Hamidiye Etfal Training and Research Hospital · NCT07126106

The GRADY tool will be tested to see if routine vital signs and lab results can detect early sepsis and gram-negative bloodstream infection in adult ICU patients.

Quick facts

Study typeObservational
Enrollment55 (estimated)
Ages18 Years and up
SexAll
SponsorSisli Hamidiye Etfal Training and Research Hospital Academic / other
Locations1 site (Seyrantepe, Istanbul)
Trial IDNCT07126106 on ClinicalTrials.gov

What this trial studies

This is a prospective, single-center validation of the GRADY machine-learning models using routinely collected vital signs and laboratory data from adult ICU patients. The study will enroll patients who remain in the ICU at least 48 hours and have blood cultures taken, and will compare GRADY's predictions to standard scoring systems such as SOFA, SIRS, and NEWS2. Primary outcomes include detection accuracy for gram-negative bacteremia and sepsis versus blood culture-confirmed infection and clinical sepsis definitions. The protocol also explores how GRADY might be integrated as an early warning tool to support more rapid clinical intervention.

Who should consider this trial

Good fit: Adults aged 18 or older who are in the ICU for 48 hours or more, have had blood cultures obtained as part of routine care, and can provide informed consent are the intended participants.

Not a fit: Patients younger than 18, those with ICU stays under 48 hours, or patients who never had blood cultures collected are unlikely to benefit from this study's findings.

Why it matters

Potential benefit: If successful, GRADY could enable earlier identification of patients at risk for gram-negative bacteremia or sepsis, allowing faster targeted treatment and potentially reducing ICU morbidity and mortality.

How similar studies have performed: Previous retrospective studies of machine-learning sepsis prediction tools have shown promise, but prospective external validation of such models remains limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Patients aged 18 years or older
* ICU stay of 48 hours or longer
* Patients from whom blood cultures were obtained during routine monitoring
* Signed informed consent form

Exclusion Criteria:

* Patients younger than 18 years
* ICU stay shorter than 48 hours
* Patients without blood cultures

Where this trial is running

Seyrantepe, Istanbul

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions BacteremiaSepsis BacterialBloodstream InfectionsepsisMachine Prediction Methodsexternal validation
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.