Inpatient Internal Medicine PatientsDRAFT-AINCT07866001
A Pragmatic Trial of AI-Assisted Discharge Summary Generation
A study testing Epic Discharge Summary Hospital Course Generator in people with Inpatient Internal Medicine Patients and Patient Discharge, run by Unity Health Toronto.
Trial summary
The goal of this study is to learn whether an artificial intelligence (AI) tool built into the electronic health record helps hospital physicians write discharge summaries. A discharge summary is the document that tells a patient's family doctor and other providers what happened during a hospital stay. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Inpatient Internal Medicine Patients, Patient Discharge, Documentation
- What is being tested?
- Epic Discharge Summary Hospital Course Generator
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 80 participants
- Where
- No sites listed yet
- Study dates
- 7 Oct 2026to Feb 2027
- Phase
- Interventional
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
- Healthcare provider at participating hospital on a hospitalist ward (teaching or non-teaching ward)
- English speaking
Who cannot join
- Planned leave during study period
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
About this study
Official title: An EHR-embedded Pragmatic Parallel-group, Operationally-driven Clinical Trial of AI-assisted Discharge Summary Generation
The goal of this study is to learn whether an artificial intelligence (AI) tool built into the electronic health record helps hospital physicians write discharge summaries. A discharge summary is the document that tells a patient's family doctor and other providers what happened during a hospital stay.
The main questions this study aims to answer are:
Read more
Does access to the AI tool reduce the time physicians spend writing discharge summaries? Does it change the quality of discharge summaries or how soon they are completed? How does it affect physician workload?
Physicians will be randomly assigned to either have access to the AI tool or complete discharge summaries as they usually do. Physicians with access can choose whether to use the tool, and they review and edit any AI-generated text before it becomes part of the discharge summary.
Read the detailed description
Discharge summaries are a key communication tool at care transitions, but they are time-consuming to write and are often delayed or incomplete. Generative AI tools embedded in the electronic health record can draft a summary of the hospital course from existing chart data, but their effect on physician time, documentation quality, and workload has not been evaluated in a randomized trial.
This multicenter pragmatic trial randomizes staff physicians on general medicine/hospitalist services to access to the Epic Hospital Course Generator, a large language model tool that drafts a hospital course narrative on request, or to usual care. Documentation time and completion timing are measured with Epic audit log metadata. Documentation quality is assessed by expert physician review of a sample of discharge summaries and by an automated LLM-as-judge approach using the PDSQI-9. Physician workload and tool usability are assessed by survey.
- Conditions
- Inpatient Internal Medicine Patients, Patient Discharge, Documentation, Artificial Intelligence (AI), Electronic Health Records, Workload
- Being tested
- Epic Discharge Summary Hospital Course Generator
- Keywords
- Discharge Summary, AI Note Writing Tool, Generative artificial intelligence, Large language model, Clinical documentation, Electronic health record, Epic, Documentation burden, Hospital medicine, Physician workload, Pragmatic randomized controlled trial
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Epic Discharge Summary Hospital Course GeneratorOther
A generative AI (large language model) tool embedded in Epic that drafts a narrative of the patient's hospital course from existing chart data, including clinician notes, investigations, and medications and treatments. A draft is generated only when a clinician requests it, can be generated at any time during the hospitalization, and can be regenerated an unlimited number of times. Clinicians can choose a narrative (chronological) format, a problem-based format with a numbered entry for each clinical problem managed during the hospitalization, or an organ system-based format. The draft appears in a separate tab and is not automatically inserted into the discharge summary; clinicians may copy, edit, or disregard it.
| Study group | Role | What they receive |
|---|---|---|
| Epic Hospital Course Generator | Experimental | Staff physicians randomized to this arm, and resident physicians working under them on teaching services, will have access to the Epic Hospital Course Generator within the Epic electronic health record during the study period. Clinicians in this arm will be notified that they have access to the tool and will be given instructions on how to use it. Use of the tool is optional. Clinicians remain responsible for reviewing any AI-generated content and deciding whether and how to incorporate it into the discharge summary. Receives: Other: Epic Discharge Summary Hospital Course Generator |
| Control | No intervention | Staff physicians randomized to this arm, and resident physicians working under them on teaching services, will not have the Epic Hospital Course Generator available for use during the study period and will complete discharge summaries using usual documentation workflows. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Time-in-note (minutes per discharge summary)
Total active time (minutes) spent writing and editing the discharge summary by all clinicians contributing to the note (staff physician and, on teaching services, resident physicians), measured per discharge episode using Epic audit log "time in note" metadata. Includes teaching and non-teaching services.
Measured: Per discharge episode, from note creation to final signature (including staff attestation where applicable), assessed up to 30 days after discharge.
Secondary outcomes (5)
Time from discharge to discharge summary signature (hours)
Time in hours between the patient's recorded hospital discharge and the final signature of the discharge summary, from Epic metadata. Summaries signed before discharge are recorded as negative values.
Measured: Per discharge episode, assessed up to 30 days after discharge.
Expert-rated documentation quality
Blinded manual review of a random sample of 200 discharge summaries (100 per arm), each rated independently by a hospitalist and a primary care physician using the validated and standardized Provider Documentation Summarization Quality Instrument (PDSQI-9). Eight attributes (accurate, cited, comprehensible, organized, succinct, synthesized, thorough, useful) are each rated on a 5-point Likert scale (1 to 5) and summed to a total score ranging from 8 to 40; higher scores indicate better quality. The ninth attribute (free of stigmatizing language) is rated yes/no and reported separately. Reviewers will also verify accuracy against the medical record by chart review in Epic, recording omissions and factual errors in: administrative details (admission and discharge dates), diagnoses, medications and treatments, investigations, and subspecialty consultations.
Measured: Per discharge episode, assessed up to 30 days after discharge.
Automated documentation quality (PDSQI-9, LLM-as-judge)
PDSQI-9 total score for all discharge summaries, assigned by a large language model using the published PDSQI-9 LLM-as-judge approach (Croxford et al., JAMIA 2025). Total score range 9 to 45; higher scores indicate better quality.
Measured: Per discharge episode, assessed up to 30 days after discharge.
Physician task load (PTL-4)
Four NASA-TLX subscales (mental demand, physical demand, temporal demand, effort), each rated 0 to 100 while reflecting on a representative clinical workday in the past 1 to 2 weeks. Subscales are summed into a composite score of 0 to 400; higher scores indicate greater workload. Measured once per clinician.
Measured: Once per clinician, within 2 weeks of completion of an inpatient service block during the active study period (for clinicians completing more than one block, the first completed block).
Frequency of AI tool use
Proportion of discharge summaries in which an AI-generated hospital course draft was generated, reported by arm (use in the control arm measures contamination).
Measured: Per discharge episode during the active study period.
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted8 Oct 2026
- Study start7 Oct 2026 (estimated)
- Primary completionJan 2027 (estimated)
- Study completionFeb 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Inpatient Internal Medicine PatientsStudies 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 N/A
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Multicenter, pragmatic, parallel-group randomized controlled trial with 1:1 allocation of staff (attending) physicians to access to the Epic Hospital Course Generator or usual care. The staff physician is the unit of randomization; resident physicians on teaching services inherit the allocation of their supervising staff physician. Outcomes are measured at the discharge episode level, with clustering by staff physician accounted for in the analysis.
- Masking
- Double blind
- Who is masked
- Investigator, Outcomes assessor
- Enrolment
- 80 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Unity Health Toronto
- Sponsor type
- University, hospital or other
- Collaborators
- University of California, San Diego
- Responsible party
- Sponsor
- Investigators
- Michael Colacci, MD PhD, Principal investigator, Unity Health Toronto
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07866001
- Sponsor's protocol ID
- 26-157
- Acronym
- DRAFT-AI
- Status last verified
- Sep 2026
- First submitted
- 25 Sep 2026
- Last updated
- 8 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data will not be made publicly available. Participants include clinicians enrolled under an opt-out consent model and patients whose health information is used under a waiver of consent; neither consented to external data sharing. Clinician-level outcome data derived from EHR audit logs and free-text discharge documentation carry meaningful re-identification risk and are subject to PHIPA, HIPAA, and institutional data governance at each site. The study protocol, statistical analysis plan, and analytic code will be made publicly available. Requests for aggregate or summary-level data from qualified researchers will be considered by the study steering committee, subject to research ethics board approval and data sharing agreements with participating institutions.