Passive Evaluation in Operational Environment of the AI Clinician Decision Support System for Sepsis Treatment

NCT05287477 | Unknown

• 1 other identifier: 20HH6297
• Study Type: observational
• Target: 15
• Locations: 1 country
• Sites: 2

Brief Summary

Sepsis, or systemic infection, is a common reason for ICU admission and death throughout the world. Despite advances in the way we treat this condition, it remains a significant economic and healthcare burden. A key part of the treatment of sepsis is the administration of IV fluids and blood pressure medication. However, there is huge uncertainty around dosing of these drugs in an individual patient. A tool to personalise these medications could improve patient survival. The study team has developed a new method to automatically and continuously review and recommend the correct medication doses to doctors, which was created using artificial intelligence (AI) techniques applied to large medical databases. The researchers' previous work has shown it has the potential to improve patient survival rates. The tool will be capable of processing patient data within the electronic patient record of NHS hospitals in real-time to suggest a course of action. This tool will be evaluated and refined in simulation studies and then be tested in two NHS Trusts in "shadow mode" (results not provided to duty clinicians). This will allow comparison of actual decisions made and recommended decisions from the AI system. The second stage of this clinical evaluation will display the recommendations to clinicians to assess the acceptability of the tool and confirm technical feasibility to inform future clinical trials. The long-term expected benefits of this project are numerous: improved patient survival, reduced use of precious intensive care resources and reduction in healthcare costs.

Conditions

Sepsis

Keywords

Artificial Intelligence

Outcome Measures

Primary Outcomes (5)

• Data Availability

  Data availability: what percentage of essential and optional data fields are available 24/7.

  18 months

• Anonymised patients' data

  Patient demographics (age in years, gender, primary diagnosis) Outcomes: organ function (hourly SOFA), ICU and hospital mortality

  18 months

• Rate of intravenous fluids administered to patients

  Rate of intravenous fluids (millilitres per hour) and vasopressors (noradrenaline equivalent, in micrograms per kilogram per minute) administered to patients.

  18 months

• Evaluators' data (the doctors assessing the AI in the background)

  The evaluator's grade and seniority (i.e. A custom-made interface linked to a database will capture and record the following: * What rate of intravenous fluids (millilitres per hour) and vasopressors (noradrenaline equivalent, in micrograms per kilogram per minute) they would recommend, before and after seeing the AI suggested dose. * Agreement with the AI suggested dose on a Likert scale including the following labels: "the AI suggested dose is:" "certainly too low", "possibly too low","likely appropriate","possibly too high", "certainly too high". After collecting this data, we will report the median difference (with interquartile range) between the AI suggested doses and the evaluator suggested doses, as well as the proportion of AI decisions in each agreement category ("certainly too low", "possibly too low","likely appropriate","possibly too high", "certainly too high").

  18 months

• System Availability

  System availability: delays in generating response 24/7. Number and nature of technical issues (drop-outs, freezes).

  18 months

Eligibility Criteria

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

Study Population

* Patients: adult septic patients in intensive care. * Human Evaluators: senior registrars, ICU fellows and consultants.

You may qualify if:

• 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

You may not qualify 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 both patients and evaluators:
• Declined participation No patient consent is required

Sponsors & Collaborators

• Imperial College London: lead
• National Institute for Health Research, United Kingdom: collaborator

Study Sites (2)

Univeristy College London Hospitals NHS Foundation Trust

London, NW1 2PG, United Kingdom

NOT YET RECRUITING

Imperial College Hospitals NHS Trust

London, W2 1BL, United Kingdom

RECRUITING

MeSH Terms

Conditions

Sepsis

Condition Hierarchy (Ancestors)

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

Central Study Contacts

Anthony C Gordon

CONTACT

02033126328; anthony.gordon@imperial.ac.uk

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: March 1, 2022
• First Posted: March 18, 2022
• Study Start: March 24, 2022
• Primary Completion: August 31, 2024
• Study Completion: August 31, 2024
• Last Updated: October 27, 2023

Record last verified: 2023-10

Data Sharing

• IPD Sharing: Will not share

Locations

GB (2)