Intelligent LLM-assisted structured handoffs for inpatient hospitalists

Structured Handoff Using Intelligent Framework for Transitions (SHIFT) Trial: A Randomized Controlled Trial of AI-Assisted End-of-Rotation Handoff Between Hospitalists

Not applicable Interventional University of Pennsylvania · NCT07251907

This project will try an AI feature that drafts end-of-rotation handoffs for inpatient general medicine attendings to see if it reduces time spent writing handoffs and work exhaustion.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment90 (estimated)
Ages18 Years and up
SexAll
SponsorUniversity of Pennsylvania Academic / other
Locations1 site (Philadelphia, Pennsylvania)
Trial IDNCT07251907 on ClinicalTrials.gov

What this trial studies

The SHIFT trial is a pragmatic, parallel-group randomized controlled trial that will randomize general medicine attending hospitalists 1:1 to an AI-assisted handoff or usual handoff workflow. The intervention provides a "Draft Handoff" button in the Carelign platform that uses a tuned large language model to generate an editable end-of-rotation handoff draft from recent EHR notes, and clinicians are required to review and edit drafts before finalizing. Clinicians randomized to the control arm will continue standard Carelign handoff workflows without AI assistance. Approximately 90 attendings contributing about 120 eligible rotations across the Hospital of the University of Pennsylvania and Penn Presbyterian Medical Center over 12 weeks will be studied, with primary outcomes including minutes spent drafting the end-of-rotation handoff and measures of documentation burden and work exhaustion.

Who should consider this trial

Good fit: Eligible participants are attending hospitalists on general medicine services at HUP or PPMC who are scheduled for at least five consecutive days on service.

Not a fit: Patients cared for by clinicians who do not use Carelign, clinicians outside HUP/PPMC, or clinicians who do not use the AI-generated drafts are unlikely to experience direct benefit from this intervention.

Why it matters

Potential benefit: If successful, the tool could shorten handoff documentation time and improve communication at transitions, potentially reducing errors and improving patient continuity of care.

How similar studies have performed: Pilot and observational work on AI-assisted clinical summarization suggests time savings and improved documentation quality, but randomized evidence for LLM-generated handoffs in real-world hospital settings is limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* General medicine attending physicians at HUP (Medicine, Solid Oncology) or PPMC (Medicine) services.
* Scheduled for ≥5 consecutive days on service.

Exclusion Criteria:

\- Jeopardy attendings and moonlighters

Where this trial is running

Philadelphia, Pennsylvania

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Electronic Medical RecordTransitions of CarePhysician WorkflowArtificial IntelligenceLarge Language Model
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.