AI tool for personalized sepsis treatment recommendations
Official title: Passive Evaluation in Operational Environment of the AI Clinician Decision Support System for Sepsis Treatment
Run by Imperial College London · NCT05287477 · Data updated 2026-05-14
This study is no longer in our active list. It may have stopped recruiting or finished. The details below are as of 2026-05-14 and are kept for reference. Check ClinicalTrials.gov for its current status, or see similar studies below.
This study is testing an AI tool that helps doctors give the right medication doses for sepsis treatment in ICU patients to see if it can improve their care.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 15 (estimated) |
| Sponsor | Imperial College London Academic / other |
| Locations | 2 sites (London and 1 other locations) |
| Trial ID | NCT05287477 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates include adults over 18 years old who are admitted to an ICU with a likely or confirmed diagnosis of sepsis and have an expected ICU stay of more than 24 hours.
✕Probably not a fit
Patients who are not for full active care, expected to survive less than 24 hours, or those admitted for elective surgery will not benefit from this study.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational study evaluates an artificial intelligence clinician decision support system designed to personalize medication dosing for sepsis treatment in ICU patients. The AI tool continuously analyzes patient data from electronic health records to recommend optimal intravenous fluids and vasopressor doses, addressing the significant variability in sepsis treatment. By leveraging reinforcement learning techniques, the system aims to improve patient outcomes and reduce the economic burden of sepsis care. The study will refine the tool based on real-world operational feedback from ICU doctors.
Why it matters
Potential benefit: If successful, this AI tool could significantly improve survival rates for sepsis patients by providing tailored treatment recommendations.
How similar studies have gone: Previous studies have shown promise in using AI for clinical decision support in sepsis treatment, indicating potential for success in this novel approach.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: For patients: * Adult patient \> 18 years old * Admitted to an intensive care unit * Likely or confirmed diagnosis of sepsis as per sepsis-3 definition (as defined in the glossary) * ICU length of stay \> 24h For Evaluators: - ICU doctors at the senior registrar, ICU fellow or consultant level Exclusion Criteria: For patients: * Not for full active care, e.g. not for vasopressors * Not expected to survive more than 24h * Elective surgical admission (these patients are regularly on antibiotics but given as a prophylaxis, with no sepsis) * Opted-out for use of their data for research (NHS and NHS-X website) For both patients and evaluators: Declined participation No patient consent is required
Where it's running
-
Imperial College Hospitals NHS Trust
London, United Kingdom Recruiting -
Univeristy College London Hospitals NHS Foundation Trust
London, United Kingdom Not yet recruiting
Study contacts
- Study coordinator: Anthony C Gordon
- Email: anthony.gordon@imperial.ac.uk
- Phone: 02033126328
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Ruta C and Vitamin C in Sepsis: Adding antioxidants to standard care
This trial tests whether adding Ruta C (rutin plus vitamin C) or vitamin C alone to standard sepsis treatment helps adults in the ICU stay shorter and recover better.
-
Early detection of sepsis-related blood clotting problems in severe burn patients
This study tests how well the JAAM-2 score can detect sepsis-induced coagulopathy early in adults with severe burns who develop sepsis in the ICU.
-
Neutrophil EMR3 as a biomarker for sepsis in ICU patients
Researchers will test whether measuring EMR3 on neutrophils helps diagnose sepsis, monitor progression, and predict outcomes in adults in Chinese ICUs.
-
Thymalfasin added to standard care for adults with sepsis and immune dysfunction
This study tests whether thymosin alpha-1 helps restore immune function in adults with sepsis who have weakened immunity.
-
Multicenter group study of sepsis and ARDS in China
This study tests how sepsis and ARDS differ among adults across several Chinese hospitals and builds a biobank to understand why some patients do better or worse.
-
Non-invasive hemodynamic guidance for sepsis care on medical wards
This trial tests whether guiding fluid and vasopressor therapy for sepsis using non-invasive hemodynamic measurements works better than standard care.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.