Clinical Decision SupportNCT07889063
Artificial Intelligence (AI)-Initiated Clinical Decision Support in Hospitalist Practice
A study testing AI Clinical Decision Support: Automated EHR Data Retrieval and AI Clinical Decision Support: Admission H&P Note in people with Clinical Decision Support, run by Cedars-Sinai Medical Center at 2 sites in United States.
Trial summary
This study will evaluate the feasibility of using artificial intelligence (AI)-generated clinical decision support during routine inpatient hospital medicine care. Participating hospitalist physicians may receive AI-generated recommendations for eligible hospitalized patients under their care. Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Clinical Decision Support
- What is being tested?
- AI Clinical Decision Support: Automated EHR Data Retrieval and AI Clinical Decision Support: Admission H&P Note
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 20 participants
- Where
- 2 sitesUnited States
- Study dates
- Oct 2026to Oct 2027
- Phase
- Interventional
- 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
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Age 18 years or older.
- Attending physician providing inpatient hospital medicine care at a participating Cedars-Sinai Health System site.
- Expected to provide clinical care during the study period.
- Willing and able to provide informed consent.
Who cannot join
- Declines to provide or withdraws informed consent.
- Not actively providing attending-level inpatient care on a participating hospitalist service during the study period.
- Unable to complete study procedures.
Trial locations and contacts
2 sites in 1 country. Contact the study team or a site near you to ask about taking part.
United States2 sites
Cedars-Sinai Medical Center
Los Angeles, California, 90048
Huntington Hospital
Pasadena, California, 91105
About this study
Official title: A Three-Arm Randomized Feasibility Trial of AI-Initiated Clinical Decision Support in Routine Hospitalist Practice
This study will evaluate the feasibility of using artificial intelligence (AI)-generated clinical decision support during routine inpatient hospital medicine care. Participating hospitalist physicians may receive AI-generated recommendations for eligible hospitalized patients under their care. Eligible patient cases will be randomly assigned to one of three AI prompting strategies that differ in the clinical information provided to the AI system. After reviewing each recommendation, participating physicians will complete a brief survey assessing the clinical usefulness of the recommendation, how they interpreted it, and whether it was or will be incorporated into patient management.
The study will assess whether AI-generated recommendations can be successfully generated and delivered during routine clinical care and whether physicians complete the study surveys and adopt the recommendations. It will also provide preliminary information about physicians' perceptions of AI-generated recommendations across the three prompting strategies. The findings will be used to inform the design of a future larger randomized trial of AI-initiated clinical decision support.
Read the detailed description
This is a three-arm randomized feasibility trial evaluating AI-initiated clinical decision support in routine inpatient hospital medicine practice. Eligible patient cases cared for by participating hospitalist physicians will be randomized to one of three AI prompting strategies: automated electronic health record (EHR) data retrieval, automated EHR data retrieval with explicit inclusion of the admission history and physical (H\&P) note, or the admission H\&P note alone. OpenEvidence will generate a clinical decision support recommendation for each randomized case.
The recommendation will be delivered to the attending hospitalist, who will then complete a brief electronic survey assessing the clinical utility and interpretation of the recommendation and whether it was implemented or planned for implementation. The study will assess the feasibility of generating and delivering AI-initiated recommendations during routine clinical care, physician survey completion, timely survey completion, and recommendation adoption. Findings from this feasibility trial will inform the design of a future larger randomized trial.
- Conditions
- Clinical Decision Support
- Being tested
- AI Clinical Decision Support: Automated EHR Data Retrieval, AI Clinical Decision Support: Admission H&P Note
- Keywords
- Artificial Intelligence, Hospital Medicine, Hospitalists, Generative Artificial Intelligence, OpenEvidence
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI Clinical Decision Support: Automated EHR Data RetrievalOther
OpenEvidence generates an AI-based clinical decision support recommendation using automated retrieval of available EHR data.
AI Clinical Decision Support: Admission H&P NoteOther
The admission H\&P note is explicitly provided to OpenEvidence as clinical context for generation of the AI-based clinical decision support recommendation.
| Study group | Role | What they receive |
|---|---|---|
| Arm D: Automated Electronic Health Record Data Retrieval Only | Experimental | Arm D (Data Retrieval Only): Eligible patient cases assigned to this arm will have the OpenEvidence recommendation generated using automated electronic health record (EHR) data retrieval without explicit inclusion of the admission history and physical (H\&P) note. Receives: Other: AI Clinical Decision Support: Automated EHR Data Retrieval |
| Arm DH: Automated EHR Data Retrieval + Admission H&P Note | Experimental | Arm DH (Data Retrieval + History and Physical): Eligible patient cases assigned to this arm will have the OpenEvidence recommendation generated using automated EHR data retrieval with explicit inclusion of the admission H\&P note. Receives: Other: AI Clinical Decision Support: Automated EHR Data Retrieval; Other: AI Clinical Decision Support: Admission H&P Note |
| Arm H: Admission H&P Note Only | Experimental | Arm H (History and Physical Only): Eligible patient cases assigned to this arm will have the OpenEvidence recommendation generated using the admission H\&P note only, without automated EHR data retrieval. Receives: Other: AI Clinical Decision Support: Admission H&P Note |
What is being measured
The primary outcome is the main question the study is designed to answer.
Successful AI Recommendation Delivery Rate
Proportion of randomized patient cases in which an AI-generated recommendation is successfully delivered to the attending hospitalist.
Measured: Within 24 hours of hospital admission
Physician Survey Completion Rate
Proportion of successfully delivered AI-generated recommendations for which the attending hospitalist completes the electronic physician survey.
Measured: Within 48 hours after AI recommendation delivery
Timely Physician Survey Completion Rate
Proportion of successfully delivered AI-generated recommendations for which the attending hospitalist completes the electronic physician research survey within 12 hours of recommendation delivery.
Measured: Within 12 hours of AI recommendation delivery
Recommendation Adoption Rate
Proportion of AI-generated recommendations that the attending hospitalist reports as implemented or planned for implementation. Responses will be recorded separately as implemented, planned but not yet implemented, or not adopted.
Measured: Within 48 hours after AI recommendation delivery
Secondary outcomes (3)
Physician-Perceived Clinical Utility
Physician-perceived clinical utility of the AI-generated recommendation, assessed at the patient-case level using a single-item 0-10 numeric rating scale, with anchors at 0 ("Not at all useful"), 5 ("Moderately useful"), and 10 ("Extremely useful").
Measured: Within 48 hours after AI recommendation delivery
Interpretation of AI-Generated Recommendations
Physician interpretation of the AI-generated recommendation, assessed using six predefined response categories in the physician research survey.
Measured: Within 48 hours after AI recommendation delivery
Physician-Reported Recommendation Adoption Status
Physician-reported adoption of the AI-generated recommendation, categorized as implemented, planned but not yet implemented, or not adopted.
Measured: Within 48 hours after AI recommendation delivery
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted22 Oct 2026
- Study startOct 2026 (estimated)
- Primary completionOct 2027 (estimated)
- Study completionOct 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Clinical Decision SupportStudies of the same condition, open and under way.
- More trials run by Cedars-Sinai Medical CenterThe 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
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind
- Who is masked
- Care provider
- Enrolment
- 20 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Cedars-Sinai Medical Center
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Josh Pevnick, Cedars-Sinai Medical Center
- Investigators
- Joshua M Pevnick, MD, Principal investigator, Cedars-Sinai Medical Center
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07889063
- Sponsor's protocol ID
- STUDY00005216
- Status last verified
- Oct 2026
- First submitted
- 3 Oct 2026
- Last updated
- 22 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data are not planned for public sharing as part of this feasibility study.
Study at a glance
From the registry record, last updated by the sponsor on 22 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Three-Arm Randomized Feasibility Trial of AI-Initiated Clinical Decision Support in Routine Hospitalist Practice
- ClinicalTrials.gov ID
- NCT07889063
- Acronym / sponsor ID
- STUDY00005216
- Conditions
- Clinical Decision Support
- Keywords
- Artificial Intelligence, Hospital Medicine, Hospitalists, Generative Artificial Intelligence, OpenEvidence
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 20 participants (estimated)
- Lead sponsor
- Cedars-Sinai Medical CenterUniversity, hospital or other
- Study start
- Oct 2026 (estimated)
- Primary completion
- Oct 2027 (estimated)
- Study completion
- Oct 2027 (estimated)
- First posted
- 22 Oct 2026 (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 study will evaluate the feasibility of using artificial intelligence (AI)-generated clinical decision support during routine inpatient hospital medicine care. Participating hospitalist physicians may receive AI-generated recommendations for eligible hospitalized patients under their care. Eligible patient cases will be randomly assigned to one of three AI prompting strategies that differ in the clinical information provided to the AI system. After reviewing each recommendation, participating physicians will complete a brief survey assessing the clinical usefulness of the recommendation, how they interpreted it, and whether it was or will be incorporated into patient management.
The study will assess whether AI-generated recommendations can be successfully generated and delivered during routine clinical care and whether physicians complete the study surveys and adopt the recommendations. It will also provide preliminary information about physicians' perceptions of AI-generated recommendations across the three prompting strategies. The findings will be used to inform the design of a future larger randomized trial of AI-initiated clinical decision support.
Detailed description
This is a three-arm randomized feasibility trial evaluating AI-initiated clinical decision support in routine inpatient hospital medicine practice. Eligible patient cases cared for by participating hospitalist physicians will be randomized to one of three AI prompting strategies: automated electronic health record (EHR) data retrieval, automated EHR data retrieval with explicit inclusion of the admission history and physical (H\&P) note, or the admission H\&P note alone. OpenEvidence will generate a clinical decision support recommendation for each randomized case.
The recommendation will be delivered to the attending hospitalist, who will then complete a brief electronic survey assessing the clinical utility and interpretation of the recommendation and whether it was implemented or planned for implementation. The study will assess the feasibility of generating and delivering AI-initiated recommendations during routine clinical care, physician survey completion, timely survey completion, and recommendation adoption. Findings from this feasibility trial will inform the design of a future larger randomized trial.
Study design
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind (care provider)
- Number of arms
- 3
| Arm | Type | Receives |
|---|---|---|
| Arm D: Automated Electronic Health Record Data Retrieval Only | Experimental | Other: AI Clinical Decision Support: Automated EHR Data RetrievalArm D (Data Retrieval Only): Eligible patient cases assigned to this arm will have the OpenEvidence recommendation generated using automated electronic health record (EHR) data retrieval without explicit inclusion of the admission history and physical (H\&P) note. |
| Arm DH: Automated EHR Data Retrieval + Admission H&P Note | Experimental | Other: AI Clinical Decision Support: Automated EHR Data Retrieval, Other: AI Clinical Decision Support: Admission H&P NoteArm DH (Data Retrieval + History and Physical): Eligible patient cases assigned to this arm will have the OpenEvidence recommendation generated using automated EHR data retrieval with explicit inclusion of the admission H\&P note. |
| Arm H: Admission H&P Note Only | Experimental | Other: AI Clinical Decision Support: Admission H&P NoteArm H (History and Physical Only): Eligible patient cases assigned to this arm will have the OpenEvidence recommendation generated using the admission H\&P note only, without automated EHR data retrieval. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (4 listed)
- Age 18 years or older.
- Attending physician providing inpatient hospital medicine care at a participating Cedars-Sinai Health System site.
- Expected to provide clinical care during the study period.
- Willing and able to provide informed consent.
Key exclusion criteria (3 listed)
- Declines to provide or withdraws informed consent.
- Not actively providing attending-level inpatient care on a participating hospitalist service during the study period.
- Unable to complete study procedures.
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 |
|---|---|---|
| AI Clinical Decision Support: Automated EHR Data RetrievalOpenEvidence generates an AI-based clinical decision support recommendation using automated retrieval of available EHR data. | Other | Arm D: Automated Electronic Health Record Data Retrieval Only, Arm DH: Automated EHR Data Retrieval + Admission H&P Note |
| AI Clinical Decision Support: Admission H&P NoteThe admission H\&P note is explicitly provided to OpenEvidence as clinical context for generation of the AI-based clinical decision support recommendation. | Other | Arm DH: Automated EHR Data Retrieval + Admission H&P Note, Arm H: Admission H&P Note Only |
Primary outcome
Successful AI Recommendation Delivery Rate
Time frame: Within 24 hours of hospital admission
Proportion of randomized patient cases in which an AI-generated recommendation is successfully delivered to the attending hospitalist.
Physician Survey Completion Rate
Time frame: Within 48 hours after AI recommendation delivery
Proportion of successfully delivered AI-generated recommendations for which the attending hospitalist completes the electronic physician survey.
Timely Physician Survey Completion Rate
Time frame: Within 12 hours of AI recommendation delivery
Proportion of successfully delivered AI-generated recommendations for which the attending hospitalist completes the electronic physician research survey within 12 hours of recommendation delivery.
Recommendation Adoption Rate
Time frame: Within 48 hours after AI recommendation delivery
Proportion of AI-generated recommendations that the attending hospitalist reports as implemented or planned for implementation. Responses will be recorded separately as implemented, planned but not yet implemented, or not adopted.
3 secondary outcomes
Physician-Perceived Clinical Utility
Time frame: Within 48 hours after AI recommendation delivery
Interpretation of AI-Generated Recommendations
Time frame: Within 48 hours after AI recommendation delivery
Physician-Reported Recommendation Adoption Status
Time frame: Within 48 hours after AI recommendation delivery
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 22 Oct 2026.
- Individual participant dataSharing planned: No. Individual participant data are not planned for public sharing as part of this feasibility study.
Related trials for Clinical Decision Support
Recruiting
CirrhosisRx CDS System
Cirrhosis, Decision Support Systems, Clinical
Not yet recruiting
AI-Assisted vs Conventional Teleglaucoma Referral
Glaucoma
Recruiting
GenAI-Assisted Rheumatoid Arthritis Bone Erosion Risk Assessment and DMARD Selection
Rheumatoid Arthritis
Not yet recruiting
EHR Nudges: Optimizing a Clinical Decision Support System for Evidence-Based Statin Medication Prescribing to Reduce the Risk of Cardiovascular Disease
Atherosclerotic Cardiovascular Disease
Recruiting
Clinical Decision Support for SGLT2i After AKI in Type 2 Diabetes
Type 2 Diabetes Mellitus, Acute Kidney Injury
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.
Joshua M Pevnick, MD principal investigator
Cedars-Sinai Medical Center
2 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing AI Clinical Decision Support: Automated EHR Data Retrieval and AI Clinical Decision Support: Admission H&P Note in people with Clinical Decision Support, run by Cedars-Sinai Medical Center at 2 sites 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 4 inclusion and 3 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 22 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 2 sites 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.
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 Joshua M Pevnick, MD (310-423-4683, Joshua.Pevnick@csmc.edu), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Successful AI Recommendation Delivery Rate (time frame: Within 24 hours of hospital admission). The study lists 4 primary outcomes in all. 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 22 Oct 2026.