← Back to Search

AI Decision Support for Gastrointestinal Bleeding

N/A
Recruiting
Led By Dennis Shung, MD
Research Sponsored by Yale University
Eligibility Criteria Checklist
Specific guidelines that determine who can or cannot participate in a clinical trial
Must have
Timeline
Screening 3 weeks
Treatment Varies
Follow Up approximately 60 minutes
Awards & highlights

Study Summary

This trial assesses how providers interact with machine learning algorithms and decision support systems for upper GIB. Simulation scenarios are used to analyze optimal implementation and see if it increases utilization and improves outcomes.

Who is the study for?
This trial is for Internal Medicine and Emergency Medicine residency trainees at the study institution. It's designed to evaluate how a machine learning algorithm, with or without a large language model interface, helps in managing upper gastrointestinal bleeding.Check my eligibility
What is being tested?
The study tests the impact of a large language model (LLM) interface on the use of a clinical decision support system for upper gastrointestinal bleeding. Participants will be randomly assigned to use either just the algorithm or the algorithm plus LLM in simulated scenarios.See study design
What are the potential side effects?
Since this trial involves simulation training rather than drug interventions, traditional side effects are not applicable. However, participants may experience stress or fatigue from simulation exercises.

Timeline

Screening ~ 3 weeks
Treatment ~ Varies
Follow Up ~approximately 60 minutes
This trial's timeline: 3 weeks for screening, Varies for treatment, and approximately 60 minutes for reporting.

Treatment Details

Study Objectives

Outcome measures can provide a clearer picture of what you can expect from a treatment.
Primary outcome measures
Change in Attitudes Towards Machine Learning Algorithms in Clinical Care using UTAUT
Clinician Decision Making of Triage of GI bleeding

Trial Design

2Treatment groups
Experimental Treatment
Active Control
Group I: Large Language Model-based InteractionExperimental Treatment1 Intervention
LLM-powered chatbot with the machine learning dashboard to provide the risk assessment and provide rationale based on interpretability metrics provided by the dashboard in which study participants can directly interact with using natural language. Participants will be provided the Generative Pre-trained Transformer (GPT) chatbot powered machine learning model dashboard.
Group II: Machine Learning DashboardActive Control1 Intervention
Machine learning algorithm output with an interactive dashboard that can be used to explain, or interpret the input factors that contribute most towards the generated risk score. Participants will have access to the machine learning dashboard only.

Find a Location

Who is running the clinical trial?

Yale UniversityLead Sponsor
1,853 Previous Clinical Trials
2,738,476 Total Patients Enrolled
National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)NIH
2,359 Previous Clinical Trials
4,314,507 Total Patients Enrolled
Dennis Shung, MDPrincipal InvestigatorYale School of Medicine Section of Digestive Diseases

Frequently Asked Questions

These questions and answers are submitted by anonymous patients, and have not been verified by our internal team.

Are there still open positions in this clinical experimentation?

"This study, which was initially added to clinicaltrials.gov on May 23rd 2023 and edited last on April 14th of the same year is no longer seeking candidates. However, there remain 365 other studies open for enrollment at this moment in time."

Answered by AI
~23 spots leftby Aug 2024