NCT05495438 (ICU) is a clinical trial of Hypothetical AI in Sepsis, sponsored by Imperial College London.

Who is sponsoring NCT05495438?

NCT05495438 is sponsored by Imperial College London.

What drugs are being tested in NCT05495438?

Interventions in NCT05495438: Hypothetical AI.

Is NCT05495438 still recruiting?

NCT05495438 is currently completed. Last updated 27 February 2023.

Last reviewed 2023-02-27 · How we verify

NCT05495438: ICU

Name: Drug Landscape Pharmaceutical Database
Creator: Drug Landscape
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

Impact and Safety of AI in Decision Making in the ICU: a Simulation Experiment

Completed Last updated 27 February 2023

What this trial tests

trial testing Hypothetical AI in Sepsis in 38 participants. Completed in 31 October 2022.

Timeline

22 July 2022

Primary endpoint
31 October 2022

31 October 2022

Quick facts

Lead sponsor	Imperial College London
Status	Completed
Study type	OBSERVATIONAL
Enrollment	38
Start date	22 July 2022
Primary completion	31 October 2022
Estimated completion	31 October 2022
Sites	1 location across United Kingdom

Drugs / interventions tested

Hypothetical AI

Conditions studied

Sepsis — all drugs for Sepsis →

Sponsor

Imperial College London

Who can join

18 and older, any sex, with Sepsis. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

The impact of deploying artificial intelligence (AI) in healthcare settings in unclear, in particular with regards to how it will influence human decision makers. Previous research demonstrated that AI alerts were frequently ignored (Kamal et al., 2020 ) or could lead to unexpected behaviour with worsening of patient outcomes (Wilson et al., 2021 ). On the other hand, excessive confidence and trust placed in the AI could have several adverse consequences including ability to detect harmful AI decisions, leading to patient harm as well as human deskilling. Some of these aspects relate to automation bias. In this simulation study, the investigators intend to measure whether medical decisions in areas of high clinical uncertainty are modified by the use of an AI-based clinical decision support tool. How the dose of intravenous fluids (IVF) and vasopressors administered by doctors in adult patients with sepsis (severe infection with organ failure) in the ICU), changes as a result of disclosing the doses suggested by a hypothetical AI will be measured. The area of sepsis resuscitation is poorly codified, with high uncertainty leading to high variability in practice. This study will not specifically mention the AI Clinician (Komorowski et al., 2018). Instead, the investigators will describe a hypothetical AI for which there is some evidence of effectiveness on retrospective data in another clinical setting (e.g. a model that was retrospectively validated using data from a different country than the source data used for model training) but no prospective evidence of effectiveness or safety. As such, it is possible for this hypothetical AI to provide unsafe suggestions. The investigators will intentionally introduce unsafe AI suggestions (in random order), to measure the sensitivity of our participants at detecting these.

Publications & conference data

No peer-reviewed publications indexed yet for this trial. Completed trials usually publish results within 12-18 months.

Verify or expand the search:

Other recruiting trials for Sepsis

Currently open trials in the same condition.

NCT07507877 — Infraclavicular Axillary Vein Collapsibility Index as a Predictor of Fluid Responsiveness · recruiting
NCT07154615 — Assessing Immune Dysfunction in Sepsis · recruiting
NCT07419802 — OxiCLEAR (Oxiris Cytokines and Endotoxin Adsorption Rate) Study · recruiting
NCT07351344 — African Survey on Sepsis Knowledge (ASK) · recruiting
NCT07448805 — Accuracy and Safety of the Syai Tag System for Continuous Glucose Monitoring in Intensive Internal Care Unit · NA · recruiting

Other Imperial College London trials

Trials by the same sponsor.

NCT06035861 — Endothelial Cell Activation and Total Pulmonary Resistance in PAH · NA · not yet recruiting
NCT07397455 — Development of a Controlled Human Infection Model for Assessment of SARS-CoV-2 Omicron Subvariants · Phase 1 · not yet recruiting
NCT07422532 — A Multi-centre Trial to Assess the Efficacy and Safety of the Omnipod 5 System in People With Type 2 Diabetes Undergoing · NA · not yet recruiting
NCT07389031 — Maralixibat for Intrahepatic Cholestasis of Pregnancy · Phase 2 · not yet recruiting
NCT07358897 — Gender Affirming Hormone Therapy and Immune Function in Trans Individuals - The GIFT Study · not yet recruiting

Verify against primary sources

ClinicalTrials.gov — authoritative US registry record
WHO ICTRP — international registry index
EU Clinical Trials Register
Sponsor press releases (Google)

Data sources for this page

Trial protocol + status: ClinicalTrials.gov NCT05495438 (US National Library of Medicine, public domain)
Drug + disease cross-links: matched in real time against Drug Landscape's normalised drug + company + condition tables
Sponsor: as reported to ClinicalTrials.gov by Imperial College London
Last refreshed: 27 February 2023

Drug Landscape aggregates and links these public records for informational use only. Always verify against the primary source before clinical or regulatory decisions. Canonical URL: https://druglandscape.com/trial/NCT05495438.

Primary sources · FDA · ClinicalTrials.gov · EMA · SEC EDGAR · ChEMBL · Wikidata · full sourcing