We'd like your feedback
Your feedback is important to us. It will help us improve the quality of the study information on this site. Please answer both questions.
Contact the study team using the details below to take part. If there are no contact details below please ask your doctor in the first instance.
Elizabeth
Fagbodun
e.fagbodun@imperial.ac.uk
Matthieu
Komorowski
m.komorowski14@imperial.ac.uk
Other bacterial diseases
This information is provided directly by researchers, and we recognise that it isn't always easy to understand. We are working with researchers to improve the accessibility of this information. In some summaries, you may come across links to external websites. These websites will have more information to help you better understand the study.
The cornerstone of sepsis resuscitation is the administration of intravenous fluids (IVF) and/or vasopressors (drugs that squeeze the blood vessels to increase blood pressure) to maintain blood flow to prevent organ failure. However, there is huge uncertainty around the individual dosing of these drugs in an individual patient, partially due to high sepsis heterogeneity. The current guidelines provide recommendations at a population-level but fail to individualise the decisions. Wrong decisions lead to poorer outcomes and increased intensive care unit (ICU)-resource use. A tool to personalise these medications could improve patient survival.
We have developed a new method to automatically and continuously review and recommend the correct dose of these medications to doctors, which was created using artificial intelligence (AI) techniques applied to large medical databases. The method we used is called reinforcement learning, and we call the technology the “AI Clinician”.
In the AI Clinician XP1, we tested the safety of the AI Clinician when running in “shadow mode”, i.e. data was presented to off-duty ICU clinicians. This enabled us to 1) develop methods and software to connect to real-time electronic health record (EHR); 2) check the safety of the algorithm when used in a contemporary UK ICU patient cohort.
In XP2, the AI Clinician will be running in real-time on dedicated computers at the bedside of actual patients in 4 ICUs across 2 NHS Trusts (Three ICUs at ICHT and one ICU at UCLH).
This present experiment will test the feasibility of running the AI Clinician in real-time in operational ICUs, in preparation for a future large scale multi-centre randomised trial that will test for an improvement in clinically relevant outcomes. At this stage and in the interest of focusing on prescribers first, we will only be testing the use of the system by ICU doctors.
Start dates may differ between countries and research sites. The research team are responsible for keeping the information up-to-date.
The recruitment start and end dates are as follows:
Observational type: Qualitative;
You can take part if:
You may not be able to take part if:
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 clinician participants:  - Declined participation
Below are the locations for where you can take part in the trial. Please note that not all sites may be open.
The study is sponsored by Imperial College of Science, Technology and Medicine and funded by NIHR Central Commissioning Facility (CCF) .
Your feedback is important to us. It will help us improve the quality of the study information on this site. Please answer both questions.
Read full details
for Trial ID: CPMS 54978
You can print or share the study information with your GP/healthcare provider or contact the research team directly.
