LLM Tool for Physician Workflow
(SHIFT Trial)
What You Need to Know Before You Apply
What is the purpose of this trial?
This trial tests a new tool designed to assist doctors with paperwork. The tool uses advanced technology to draft handoff notes, which are crucial for maintaining patient care during shift changes. The study aims to determine if this tool can reduce the time doctors spend on paperwork and alleviate their exhaustion. Doctors working in general medicine with shifts of at least five consecutive days may be suitable candidates for this trial. As an unphased trial, it offers a unique opportunity to contribute to innovative solutions that could enhance healthcare efficiency.
Do I need to stop my current medications for this trial?
The trial information does not specify whether you need to stop taking your current medications.
What prior data suggests that this LLM tool is safe for physician workflow?
Research has shown that tools like the one studied in this trial are generally safe for use in medical settings. These tools assist in creating drafts for patient handoffs, which are summaries provided when transferring a patient from one doctor to another.
Safety checks from these studies indicate that users receive notes created by these tools positively. No reports have linked harmful effects directly to using these tools. Thus, while the tool saves time by drafting handoff notes, it does not pose a risk to users.
However, doctors must review and edit these drafts before finalization. This step ensures the information is accurate and meets the quality expected in medical documentation.12345Why are researchers excited about this trial?
Researchers are excited about the LLM tool because it has the potential to streamline physician workflows by using AI to draft handoff documents. Unlike the standard practice, where doctors manually prepare these documents, the LLM tool offers automated draft generation, saving time and reducing the risk of errors. This innovative approach allows physicians to focus more on patient care by minimizing administrative burdens.
What evidence suggests that the LLM tool is effective for reducing documentation burden?
Studies have shown that large language models (LLMs) can help doctors save time when writing patient handoff notes. Automated tools rate these AI-generated drafts highly for quality, and doctors can edit them to meet their standards. In this trial, participants in the intervention arm will use an LLM-assisted draft generation feature, which research indicates is practical and effective in reducing the time doctors spend on paperwork. Surveys also show that more doctors recognize the benefits of using LLMs in their work. Overall, this suggests that LLM tools could make writing handoffs faster and less tiring for doctors.12346
Are You a Good Fit for This Trial?
This trial is for general medicine attending physicians at HUP (Medicine, Solid Oncology) or PPMC (Medicine) services who are scheduled to work for 5 or more consecutive days. It excludes 'jeopardy attendings' and moonlighters.Inclusion Criteria
Exclusion Criteria
Timeline for a Trial Participant
Screening
Participants are screened for eligibility to participate in the trial
Intervention
Hospitalists use the AI-assisted draft generation feature within Carelign for handoff preparation
Control
Hospitalists continue using standard handoff workflows without AI assistance
Follow-up
Participants are monitored for documentation burden and work exhaustion
What Are the Treatments Tested in This Trial?
Interventions
- LLM tool
Trial Overview
The trial tests an AI-powered LLM tool designed to draft medical handoffs within Carelign, a communication tool adjacent to electronic health records. Physicians will be randomly assigned to use the AI feature and must review and edit any drafts before finalizing them.
How Is the Trial Designed?
2
Treatment groups
Experimental Treatment
Active Control
The intervention arm will have access to an LLM-assisted draft generation feature within Carelign. This will generate a draft of the handoff, which the provider will then edit as necessary before finalizing.
The control arm will continue usual care without access to the AI drafting feature. Attendings will prepare handoffs themselves using current workflows within Carelign.
Find a Clinic Near You
Who Is Running the Clinical Trial?
University of Pennsylvania
Lead Sponsor
Citations
Developing and Evaluating Large Language Model ...
... handoff tools as feasible, efficient, and effective. In ... Automated Evaluation Scores, Large Language Model (LLM)–Generated and Physician- ...
Developing and Evaluating Large Language Model ...
... handoff tools as feasible, efficient, and effective. In April ... Automated Evaluation Scores, Large Language Model (LLM)–Generated and Physician- ...
3.
emed.weill.cornell.edu
emed.weill.cornell.edu/news/ai-written-patient-handoff-notes-may-save-physicians-timeAI-Written Patient Handoff Notes May Save Physicians Time
Though using large language models (LLM) that drive artificial ... When AI tools that measure text similarity evaluated the LLM ...
Shifts in emergency physicians' attitudes toward large ...
A survey of clinicians' views of the utility of large Language models. ... Developing and evaluating large Language model–generated emergency ...
5.
clinicaltrials.gov
clinicaltrials.gov/study/NCT07251907?locStr=United+States&country=United+States&aggFilters=status%3AStructured Handoff Using Intelligent Framework for ...
The AI feature uses a large language model (LLM) ... Electronic Medical RecordTransitions of CarePhysician WorkflowArtificial Intelligence (AI) ...
6.
news-medical.net
news-medical.net/news/20241206/AI-generated-handoff-notes-Study-assesses-safety-and-accuracy-in-emergency-medicine.aspxAI-generated handoff notes: Study assesses safety and ...
Researchers develop and evaluate the accuracy, safety, and utility of large language model-generated emergency medicine handoff notes.
Unbiased Results
We believe in providing patients with all the options.
Your Data Stays Your Data
We only share your information with the clinical trials you're trying to access.
Verified Trials Only
All of our trials are run by licensed doctors, researchers, and healthcare companies.