SepsisICUNCT05495438
Impact and Safety of AI in Decision Making in the ICU: a Simulation Experiment
An observational study of Sepsis, run by Imperial College London at 1 site in United Kingdom.
Trial summary
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… Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Sepsis
- What is being tested?
- Hypothetical AI
- How many people
- 38 participants
- Where
- 1 siteUnited Kingdom
- Study dates
- 22 Jul 2022to 31 Oct 2022
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Study population: Junior (senior house officer) or senior (registrar/fellow/consultant) ICU doctor
Who may be able to join
- Junior (senior house officer) or senior (registrar/fellow/consultant) ICU doctor
Who cannot join
- Participants not meeting the inclusion criteria.
Trial locations and contacts
1 site in 1 country.
United Kingdom1 site
Imperial College Hospitals NHS Trust
London, W2 1PG
About this study
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.
Read the detailed 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.
The investigators will examine what participant characteristics are linked with an increase likelihood of being influenced by the AI, and conduct a number of pre-specified subgroup analyses, e.g. junior versus senior ICU doctors, and separating those with a positive or a negative attitude towards AI.
- Conditions
- Sepsis
- Being tested
- Hypothetical AI
- Keywords
- Artificial Intelligence
- Medical subject headings
- Sepsis
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Hypothetical AIOther
n/a - There is no intervention. Clinicians will review the suggestions of a hypothetical AI
| Study group | Role | What they receive |
|---|---|---|
| ICU Clinicians | Not described Receives: Other: Hypothetical AI |
What is being measured
The primary outcome is the main question the study is designed to answer.
Influence of AI on ICU Clinicians
Influence of AI on ICU Clinicians, this will be divided into the following categories: overall and stratified by safe/unsafe, junior/senior and positive/negative attitude towards AI.
Measured: 3 months
Secondary outcomes (4)
Participants' characteristics
What are the characteristics of those taking part in the simulation and how does this affect decision making.
Measured: 3 months
Trust in AI
How much do ICU clinicians trust the AI system.
Measured: 3 months
Confidence in participants' decisions
How much confidence do clinicians place in the AI system
Measured: 3 months
Proportion of time with attention on AI explanation
Where is attention focused during the simulation
Measured: 3 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted10 Aug 2022
- Study start22 Jul 2022
- Primary completion31 Oct 2022
- Study completion31 Oct 2022
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for SepsisStudies of the same condition, open and under way.
- More trials run by Imperial College LondonThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Other
- Time perspective
- Prospective
- Enrolment
- 38 participants (actual)
Sponsor and investigators
- Lead sponsor
- Imperial College London
- Sponsor type
- University, hospital or other
- Collaborators
- University of York
- Responsible party
- Sponsor
- Investigators
- Matthieu Komorowski, MD, PhD, Principal investigator, Imperial College London
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT05495438
- Sponsor's protocol ID
- 22CX7592
- Acronym
- ICU
- Status last verified
- Feb 2023
- First submitted
- 4 Aug 2022
- Last updated
- 27 Feb 2023
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data will only be reviewed by the study team.
Study at a glance
From the registry record, last updated by the sponsor on 27 Feb 2023. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Impact and Safety of AI in Decision Making in the ICU: a Simulation Experiment
- ClinicalTrials.gov ID
- NCT05495438
- Acronym / sponsor ID
- ICU / 22CX7592
- Conditions
- Sepsis
- Keywords
- Artificial Intelligence
- Study type
- Observational
- Recruitment status
- Completed
- Enrolment
- 38 participants (actual)
- Lead sponsor
- Imperial College LondonUniversity, hospital or other
- Collaborators
- University of York
- Study start
- 22 Jul 2022 (actual)
- Primary completion
- 31 Oct 2022 (actual)
- Study completion
- 31 Oct 2022 (actual)
- First posted
- 10 Aug 2022 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Detailed 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.
The investigators will examine what participant characteristics are linked with an increase likelihood of being influenced by the AI, and conduct a number of pre-specified subgroup analyses, e.g. junior versus senior ICU doctors, and separating those with a positive or a negative attitude towards AI.
Study design
- Observational model
- Other
- Time perspective
- Prospective
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| ICU Clinicians | – | Other: Hypothetical AI |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
- Study population
- Junior (senior house officer) or senior (registrar/fellow/consultant) ICU doctor
Key inclusion criteria (1 listed)
- Junior (senior house officer) or senior (registrar/fellow/consultant) ICU doctor
Key exclusion criteria (1 listed)
- Participants not meeting the inclusion criteria.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Hypothetical AIn/a - There is no intervention. Clinicians will review the suggestions of a hypothetical AI | Other | ICU Clinicians |
Primary outcome
Influence of AI on ICU Clinicians
Time frame: 3 months
Influence of AI on ICU Clinicians, this will be divided into the following categories: overall and stratified by safe/unsafe, junior/senior and positive/negative attitude towards AI.
4 secondary outcomes
Participants' characteristics
Time frame: 3 months
Trust in AI
Time frame: 3 months
Confidence in participants' decisions
Time frame: 3 months
Proportion of time with attention on AI explanation
Time frame: 3 months
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 27 Feb 2023.
- Individual participant dataSharing planned: No. Individual participant data will only be reviewed by the study team.
Related trials for Sepsis
Not yet recruitingPhase 2/3
A Pivotal Safety and Immunogenicity GBS-NN/NN2 Vaccine Maternal Immunisation Trial
Streptococcus Agalactiae Infection, Neonatal Sepsis
Active, not recruiting
CT for Personalized Mechanical Ventilation
Ventilator-Induced Lung Injury, Sepsis Syndrome
RecruitingPhase 4
A Study to Compare the Efficacy and Safety of Extended and Intermittent Infusion of Beta-lactams in Critically Ill Paediatric Patients
Infection, Sepsis
Not yet recruiting
Double Plasma Separation and Adsorption in Acute-on-Chronic Liver Failure (DPMAS-ACLF Trial)
Acute-on-Chronic Liver Failure (ACLF)
Active, not recruitingPhase 4
Thymosin Alpha 1 and IgM Levels in Sepsis
Sepsis, Septic Shock
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Matthieu Komorowski, MD, PhD principal investigator
Imperial College London
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Sepsis, run by Imperial College London at 1 site in United Kingdom.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 1 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 27 Feb 2023. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in United Kingdom. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Influence of AI on ICU Clinicians (time frame: 3 months). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 27 Feb 2023.