Critical IllnessPhase 1/2POC-AI-ICUNCT07293078
Point-of-Care AI Assistance and Critical Care Outcomes: A Randomized Trial
A Phase 1/2 study testing Point-of-care large language model decision support (ChatGPT-5) in people with Critical Illness and Sepsis, run by MetroWest Artificial Intelligence Research Workgroup at 1 site in United States.
Trial summary
This is a prospective, unmasked, randomized, multicenter clinical trial evaluating the impact of point-of-care large language model (LLM)-based decision support on diagnostic accuracy and clinical outcomes in adult medical intensive care unit (MICU) patients. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Critical Illness, Sepsis, Acute Respiratory Failure (ARF)
- What is being tested?
- Point-of-care large language model decision support (ChatGPT-5)
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 1,000 participants
- Where
- 1 siteUnited States
- Study dates
- 1 Jan 2026to 30 Jun 2029
- Phase
- Phase 1/2
- Are there results?
- Not yet: the study is under way
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
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Adult patients (≥ 18 years) admitted to the medical intensive care unit (MICU) at participating hospitals.
- Direct admissions from the emergency department or transfers from medical wards to the MICU.
- Critically ill patients meeting local ICU admission criteria.
Who cannot join
- Transfers to the MICU from outside hospitals, operating room, or post-anesthesia care unit.
- Age < 18 years.
- Incomplete or missing essential clinical information at admission (e.g., key labs or documentation not yet available).
- Primary surgical or cardiac (e.g., STEMI) patients.
- Pregnant or postpartum women.
- Prisoners.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
United States1 site
Framingham Union Hospital/MetroWest Medical Center
Framingham, Massachusetts, 01702
Eric Silverman, M.D., 508-344-5680, esilverman@pamw.org
Chih-Hsien Wu, M.D., lisa19950421@gmail.com
About this study
Official title: Prospective Evaluation of a Point-of-Care Artificial Intelligence Model in Critical Care Outcomes
This is a prospective, unmasked, randomized, multicenter clinical trial evaluating the impact of point-of-care large language model (LLM)-based decision support on diagnostic accuracy and clinical outcomes in adult medical intensive care unit (MICU) patients.
Consecutive adult ICU admissions at participating community hospitals (initially MetroWest Medical Center and St. Vincent Hospital) will be screened for eligibility. Eligible patients will be randomized 1:1 to standard care or an AI-assisted group. In both arms, initial evaluation and management will follow usual practice. For patients randomized to AI assistance, de-identified admission data (history and physical, labs, imaging reports, and other relevant documentation) will be formatted and submitted to a state-of-the-art LLM (ChatGPT-5) at the time of admission. The AI-generated differential diagnosis and therapeutic recommendations will be provided to the admitting team for consideration. For the standard care arm, LLM output will be generated but not shared with clinicians.
After discharge, a masked chart review will determine the "ground truth" primary diagnosis and extract outcomes including: Primary Outcome - a composite of medical errors (from time of ICU admission through day 7 of ICU stay, or ICU discharge, whichever comes first); Secondary Outcomes - 90-day mortality, ICU and hospital length of stay, and ventilator-free days.
Read the detailed description
The rapid development of large language models (LLMs) such as ChatGPT has created new opportunities and risks for their use in medicine. Although early studies suggest high diagnostic accuracy in complex clinical scenarios and ICU admissions, the impact of LLMs on real-world clinical outcomes and the optimal mode of physician-AI interaction remain uncertain. Published work from our group showed that ChatGPT-4 achieved diagnostic accuracy comparable to board-certified intensivists for ICU admissions in a retrospective study. However, prospective, randomized data on clinical outcomes are lacking.
This trial will evaluate a pragmatic paradigm for integrating LLMs at the time of ICU admission (point-of-care AI). All eligible adult MICU admissions at participating sites will be prospectively randomized to: (1) standard care, or (2) AI-assisted care in which an LLM receives standardized, de-identified admission data and returns a proposed primary diagnosis, ranked differential diagnosis (up to five conditions), suggested additional information, and prioritized therapeutic interventions. Admitting clinicians in the AI-assisted arm will be asked to review and optionally incorporate the AI recommendations and will complete a brief questionnaire regarding perceived utility and any changes in diagnosis or management.
A masked clinical adjudication panel will perform longitudinal chart review to define the "ground truth" primary diagnosis and assess error rates and outcomes. The primary endpoint is a composite of medical errors. The specific time frame will be from the time of ICU admission through day 7 of ICU stay, or ICU discharge, whichever comes first. Secondary endpoints will include 90-day mortality, ICU and hospital length of stay, and ventilator-free days. Other exploratory secondary endpoints will be considered. The trial is designed to enroll approximately 1000 patients across multiple MICUs, with interim analysis at 12 months to assess feasibility, integrity, and futility. The study is minimal risk, uses de-identified data for AI queries, and does not alter standard diagnostic testing or therapeutic options.
- Conditions
- Critical Illness, Sepsis, Acute Respiratory Failure (ARF), Multi-organ Failure, Acute Kidney Injury, Delirium Confusional State
- Being tested
- Point-of-care large language model decision support (ChatGPT-5)
- Keywords
- Critical Care, Intensive Care Unit, Large Language Model, Artificial Intelligence, Diagnostic Accuracy, Clinical Decision Support, Critical Care Outcomes, Sepsis, Shock, Acute Respiratory Failure, Multiorgan Failure
- Medical subject headings
- Critical Illness, Sepsis, Multiple Organ Failure, Acute Kidney Injury, Confusion, Shock
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Point-of-care large language model decision support (ChatGPT-5)Other
Use of a large language model (ChatGPT-5) to analyze de-identified ICU admission data (history, physical examination, laboratory results, imaging reports, and other documentation) at the time of admission. The model generates diagnostic and therapeutic recommendations that are shared with clinicians in the AI-assisted arm only.
| Study group | Role | What they receive |
|---|---|---|
| Standard Care | No intervention | Patients receive usual ICU care per local practice. De-identified admission data may be processed and submitted to the LLM for research purposes, but AI output is not shared with treating clinicians and does not influence real-time management. |
| AI-Assisted Care | Other | Patients receive standard ICU care plus point-of-care LLM-based decision support at admission. De-identified admission data are formatted and submitted to an LLM (ChatGPT-5). The model returns a primary diagnosis, ranked differential diagnosis list, suggested additional information, and prioritized therapeutic recommendations. This output is provided to the admitting team for consideration in ongoing management. Receives: Other: Point-of-care large language model decision support (ChatGPT-5) |
What is being measured
The primary outcome is the main question the study is designed to answer.
Composite of Medical Errors
Proportion of patients with at least one clinically important diagnostic or therapeutic error identified by masked chart review (e.g., missed or delayed critical diagnosis, major guideline-discordant therapy with potential for harm).
Measured: From the time of ICU admission through day 7 of ICU stay or ICU discharge, whichever comes first.
Secondary outcomes (4)
90-day All-Cause Mortality
All-cause mortality within 90 days of index ICU admission, as determined by chart review and available follow-up records.
Measured: 90 days from ICU admission.
ICU Length of Stay
Total number of days spent in the ICU during the index hospitalization.
Measured: From ICU admission to ICU discharge (up to 90 days).
Ventilator-Free Days
Number of days alive and free from invasive mechanical ventilation during the first 28 days after ICU admission.
Measured: Up to 28 days after ICU admission.
Hospital Length of Stay
Total number of days from hospital admission to hospital discharge during the index hospitalization.
Measured: From hospital admission to hospital discharge (up to 90 days).
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted18 Dec 2025
- Study start1 Jan 2026 (estimated)
- Primary completion31 Dec 2028 (estimated)
- Study completion30 Jun 2029 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for Critical IllnessStudies of the same condition, open and under way.
- 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
- Interventional
- Phase
- Phase 1/2
- Primary purpose
- Treatment
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Double blind
- Who is masked
- Participant, Outcomes assessor
- Enrolment
- 1,000 participants (estimated)
Sponsor and investigators
- Lead sponsor
- MetroWest Artificial Intelligence Research Workgroup
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
- Investigators
- Eric Silverman, M.D., Principal investigator, MetroWest Medical Center and St. Vincent Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07293078
- Sponsor's protocol ID
- POC-AI-ICU-001
- Other IDs
- IRB#2025-067
- Acronym
- POC-AI-ICU
- Status last verified
- Dec 2025
- First submitted
- 17 Nov 2025
- Last updated
- 18 Dec 2025
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: De-identified individual participant data will be retained for reanalysis by the study team. There is no current plan for routine public sharing of individual participant-level data, but de-identified datasets may be shared with qualified investigators upon reasonable request and appropriate data use agreements.
Publications
Singh J, Bohra R, Mukhtiar V, Fernandes W, Bhanushali C, Chinnamuthu R, Kanamgode SS, Ellis J, Silverman E. Diagnostic Accuracy of a Large Language Model (ChatGPT-4) for Patients Admitted to a Community Hospital Medical Intensive Care Unit: A Retrospective Case Study. J Intensive Care Med. 2026 May;41(5):413-420. doi: 10.1177/08850666251368270. Epub 2025 Aug 17.
PubMed 40820407
Study at a glance
From the registry record, last updated by the sponsor on 18 Dec 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Prospective Evaluation of a Point-of-Care Artificial Intelligence Model in Critical Care Outcomes
- ClinicalTrials.gov ID
- NCT07293078
- Acronym / sponsor ID
- POC-AI-ICU / POC-AI-ICU-001
- Conditions
- Critical Illness, Sepsis, Acute Respiratory Failure (ARF), Multi-organ Failure, Acute Kidney Injury, Delirium Confusional State
- Keywords
- Critical Care, Intensive Care Unit, Large Language Model, Artificial Intelligence, Diagnostic Accuracy, Clinical Decision Support, Critical Care Outcomes, Sepsis
- Phase
- Phase 1/2
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 1,000 participants (estimated)
- Lead sponsor
- MetroWest Artificial Intelligence Research WorkgroupUniversity, hospital or other
- Study start
- 1 Jan 2026 (estimated)
- Primary completion
- 31 Dec 2028 (estimated)
- Study completion
- 30 Jun 2029 (estimated)
- First posted
- 18 Dec 2025 (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.
This is a prospective, unmasked, randomized, multicenter clinical trial evaluating the impact of point-of-care large language model (LLM)-based decision support on diagnostic accuracy and clinical outcomes in adult medical intensive care unit (MICU) patients.
Consecutive adult ICU admissions at participating community hospitals (initially MetroWest Medical Center and St. Vincent Hospital) will be screened for eligibility. Eligible patients will be randomized 1:1 to standard care or an AI-assisted group. In both arms, initial evaluation and management will follow usual practice. For patients randomized to AI assistance, de-identified admission data (history and physical, labs, imaging reports, and other relevant documentation) will be formatted and submitted to a state-of-the-art LLM (ChatGPT-5) at the time of admission. The AI-generated differential diagnosis and therapeutic recommendations will be provided to the admitting team for consideration. For the standard care arm, LLM output will be generated but not shared with clinicians.
After discharge, a masked chart review will determine the "ground truth" primary diagnosis and extract outcomes including: Primary Outcome - a composite of medical errors (from time of ICU admission through day 7 of ICU stay, or ICU discharge, whichever comes first); Secondary Outcomes - 90-day mortality, ICU and hospital length of stay, and ventilator-free days.
Detailed description
The rapid development of large language models (LLMs) such as ChatGPT has created new opportunities and risks for their use in medicine. Although early studies suggest high diagnostic accuracy in complex clinical scenarios and ICU admissions, the impact of LLMs on real-world clinical outcomes and the optimal mode of physician-AI interaction remain uncertain. Published work from our group showed that ChatGPT-4 achieved diagnostic accuracy comparable to board-certified intensivists for ICU admissions in a retrospective study. However, prospective, randomized data on clinical outcomes are lacking.
This trial will evaluate a pragmatic paradigm for integrating LLMs at the time of ICU admission (point-of-care AI). All eligible adult MICU admissions at participating sites will be prospectively randomized to: (1) standard care, or (2) AI-assisted care in which an LLM receives standardized, de-identified admission data and returns a proposed primary diagnosis, ranked differential diagnosis (up to five conditions), suggested additional information, and prioritized therapeutic interventions. Admitting clinicians in the AI-assisted arm will be asked to review and optionally incorporate the AI recommendations and will complete a brief questionnaire regarding perceived utility and any changes in diagnosis or management.
A masked clinical adjudication panel will perform longitudinal chart review to define the "ground truth" primary diagnosis and assess error rates and outcomes. The primary endpoint is a composite of medical errors. The specific time frame will be from the time of ICU admission through day 7 of ICU stay, or ICU discharge, whichever comes first. Secondary endpoints will include 90-day mortality, ICU and hospital length of stay, and ventilator-free days. Other exploratory secondary endpoints will be considered. The trial is designed to enroll approximately 1000 patients across multiple MICUs, with interim analysis at 12 months to assess feasibility, integrity, and futility. The study is minimal risk, uses de-identified data for AI queries, and does not alter standard diagnostic testing or therapeutic options.
Study design
- Primary purpose
- Treatment
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Double blind (participant, outcomes assessor)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Standard Care | No intervention | –Patients receive usual ICU care per local practice. De-identified admission data may be processed and submitted to the LLM for research purposes, but AI output is not shared with treating clinicians and does not influence real-time management. |
| AI-Assisted Care | Other | Other: Point-of-care large language model decision support (ChatGPT-5)Patients receive standard ICU care plus point-of-care LLM-based decision support at admission. De-identified admission data are formatted and submitted to an LLM (ChatGPT-5). The model returns a primary diagnosis, ranked differential diagnosis list, suggested additional information, and prioritized therapeutic recommendations. This output is provided to the admitting team for consideration in ongoing management. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (3 listed)
- Adult patients (≥ 18 years) admitted to the medical intensive care unit (MICU) at participating hospitals.
- Direct admissions from the emergency department or transfers from medical wards to the MICU.
- Critically ill patients meeting local ICU admission criteria.
Key exclusion criteria (6 listed)
- Transfers to the MICU from outside hospitals, operating room, or post-anesthesia care unit.
- Age < 18 years.
- Incomplete or missing essential clinical information at admission (e.g., key labs or documentation not yet available).
- Primary surgical or cardiac (e.g., STEMI) patients.
- Pregnant or postpartum women.
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 |
|---|---|---|
| Point-of-care large language model decision support (ChatGPT-5)Use of a large language model (ChatGPT-5) to analyze de-identified ICU admission data (history, physical examination, laboratory results, imaging reports, and other documentation) at the time of admission. The model generates diagnostic and therapeutic recommendations that are shared with clinicians in the AI-assisted arm only. | Other | AI-Assisted Care |
Primary outcome
Composite of Medical Errors
Time frame: From the time of ICU admission through day 7 of ICU stay or ICU discharge, whichever comes first.
Proportion of patients with at least one clinically important diagnostic or therapeutic error identified by masked chart review (e.g., missed or delayed critical diagnosis, major guideline-discordant therapy with potential for harm).
4 secondary outcomes
90-day All-Cause Mortality
Time frame: 90 days from ICU admission.
ICU Length of Stay
Time frame: From ICU admission to ICU discharge (up to 90 days).
Ventilator-Free Days
Time frame: Up to 28 days after ICU admission.
Hospital Length of Stay
Time frame: From hospital admission to hospital discharge (up to 90 days).
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 18 Dec 2025.
- Background: PubMed 40820407Singh J, Bohra R, Mukhtiar V, Fernandes W, Bhanushali C, Chinnamuthu R, Kanamgode SS, Ellis J, Silverman E. Diagnostic Accuracy of a Large Language Model (ChatGPT-4) for Patients Admitted to a Community Hospital Medical Intensive Care Unit: A Retrospective Case Study. J Intensive Care Med. 2026 May;41(5):413-420. doi: 10.1177/08850666251368270. Epub 2025 Aug 17.
- Individual participant dataSharing planned: Yes. De-identified individual participant data will be retained for reanalysis by the study team. There is no current plan for routine public sharing of individual participant-level data, but de-identified datasets may be shared with qualified investigators upon reasonable request and appropriate data use agreements.
Related trials for Critical Illness
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
Recruiting
Development and Preliminary Validation of Intelligent Video Laryngoscope for Emergency Use
Critically Ill Patients Requiring Mechanical Ventilation
Active, not recruiting
Weighted Blankets for Agitation in Adults in the Intensive Care Unit
Psychomotor Agitation, Critical Illness
Not yet recruitingObservational study
Core Competencies in General Intensive Care Ultrasound (GenIUS): a Delphi Study
Critical Illness, Ultrasound
RecruitingObservational study
Predicting Extubation Failure Using Machine Learning
Extubation Failure, Critical Illness
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.
Eric Silverman, M.D. principal investigator
MetroWest Medical Center and St. Vincent Hospital
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A Phase 1/2 study testing Point-of-care large language model decision support (ChatGPT-5) in people with Critical Illness and Sepsis, run by MetroWest Artificial Intelligence Research Workgroup at 1 site in United States.
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 3 inclusion and 6 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: opening soon, as of the sponsor's last update on 18 Dec 2025. 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 States. 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.
What does this combined phase mean?
Phase 1 studies test a treatment in a small group of people for the first time or in a new way, mainly to check safety and find the right dose.
Phase 2 studies give the treatment to a larger group to see whether it has the intended effect and to keep checking safety.
Not every study follows the same path, and some studies (observational studies, device studies) have no phase.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Eric Silverman, M.D. principal Investigator, M.D. (508-344-5680, esilverman@pamw.org), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Composite of Medical Errors (time frame: From the time of ICU admission through day 7 of ICU stay or ICU discharge, whichever comes first.). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07293078, which also lists 1 linked publication.
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 18 Dec 2025.