Prospective Validation of GRADY: A Machine Learning Model for Early Sepsis and Bacteremia Detection in ICU Patients

NCT07126106 | Recruiting

• 1 other identifier: dogu-24
• Study Type: observational
• Target: 55
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to prospectively validate the GRADY prediction models, which use machine learning algorithms to estimate the risk of gram-negative bacteremia and sepsis in intensive care unit (ICU) patients based on routinely collected vital signs and laboratory data. Sepsis, a life-threatening condition associated with high ICU mortality, requires early diagnosis and treatment-yet current diagnostic methods relying on blood cultures are time-consuming. Existing scoring systems such as SOFA, SIRS, and NEWS2 often lack sufficient sensitivity and specificity in early sepsis detection. Unlike traditional tools, the GRADY models seek to provide earlier and more accurate risk stratification. This study will compare the clinical performance of GRADY models against standard scoring systems and explore their integration as early warning tools to support rapid intervention and improve outcomes in critical care.

Conditions

Bacteremia; Sepsis Bacterial

Keywords

Bloodstream Infection; sepsis; Machine Prediction Methods; external validation

Outcome Measures

Primary Outcomes (1)

• Gram(-) negative bacteremia

  Gram (-) bacteria growth in blood culture

  1-28 days

Secondary Outcomes (3)

• SOFA

  it will be assessed at the time of patient admission.

• SIRS

  they will be assessed at the time of patient admission

• NEWS-2

  it will be assessed at the time of patient admission.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients over the age of 18 who are suspected of having bacteremia while being treated in intensive care will be included in the study.

You may qualify if:

• 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

You may not qualify if:

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

Sponsors & Collaborators

• Sisli Hamidiye Etfal Training and Research Hospital: lead

Study Sites (1)

Sisli etfal research and training hospital

Seyrantepe, Istanbul, 34371, Turkey (Türkiye)

RECRUITING

MeSH Terms

Conditions

Bacteremia; Sepsis

Condition Hierarchy (Ancestors)

Bacterial Infections; Bacterial Infections and Mycoses; Infections; Systemic Inflammatory Response Syndrome; Inflammation; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Central Study Contacts

okan derin

CONTACT

+905053580264; okanderin@gmail.com

ahmet doğukan bayrak

CONTACT

+905453511707; dogukan9653@gmail.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 12 Months
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: principal investigator

Study Record Dates

• First Submitted: August 6, 2025
• First Posted: August 17, 2025
• Study Start: February 1, 2025
• Primary Completion: December 1, 2025
• Study Completion: January 1, 2026
• Last Updated: August 17, 2025

Record last verified: 2025-08

Data Sharing

• IPD Sharing: Will not share

Locations

TU (1)