Clin2
NCT07632859Likely a fitCompleted

AI accuracy in reading Turkish emergency department notes

Emergency MedicineDiagnostic ErrorsArtificial Intelligence (AI) in Diagnosis

This study tests whether two artificial intelligence systems (GPT-4o and Claude) can accurately read and understand emergency department patient notes written in Turkish. The research uses your existing medical records to see if AI can help doctors work faster and more accurately.

Summary written for real people, not researchers, by Clin2.

Phase
N/A
Enrollment
600 people
Ages
18 years and older
Study type
Observational

Who can take part

  • You are 18 years old or older
  • You came to the emergency department at this hospital
  • Your medical record has a detailed note about your visit, including your main complaint, symptoms, and medical history
  • A doctor assigned a final diagnosis code to your visit
  • Your emergency department note is substantial (more than 50 words of real clinical information)
  • Your medical information can be fully de-identified (names and identifying details removed) for privacy

View the official record on ClinicalTrials.gov

Quick eligibility check

Answer a few plain-language questions, based on this study's own requirements, to get a preliminary sense of fit.

Similar studies

Other trials that look related to this one.

NCT07626060Recruiting
AI Tools for Chest Pain Risk Assessment

This study tests whether artificial intelligence (AI) programs can accurately calculate a chest pain risk score to help doctors decide who needs urgent heart tests. You'll be monitored for 30 days to see if the AI's predictions were correct.

Istanbul, Istanbul
NCT07766863Recruiting
AI support for adult emergency room patients

This trial tests an artificial intelligence (AI) support tool in emergency rooms at Karolinska University Hospital. The AI may help doctors make faster or more accurate decisions, which could improve care for adult patients.

Stockholm, Huddinge
NCT07352475Recruiting
AI feedback to improve kidney doctor reasoning

This trial tests if feedback from an AI system can help doctors and medical trainees improve their reasoning when solving kidney-related case scenarios. You participate online and get a chance to practice with real-world cases.

Lille
NCT07378358Recruiting
AI for urology diagnosis and treatment

This study is testing how well AI can help with diagnosis and treatment by looking at medical records of patients from four hospitals, specifically those with urological conditions. It's a way to see if AI can improve care without needing any new tests or visits.

Fuzhou
NCT06473558Not yet recruiting
Using AI to screen for depression and anxiety in the ER

This study tests if artificial intelligence can help identify depression and anxiety in patients visiting the emergency department. It may help doctors better understand and treat these conditions early.

Cleveland, Ohio
NCT07727590Not yet recruiting
ER study testing AI to read ECGs and chest X-rays

This study is testing whether an AI tool can help doctors better understand ECGs and chest X-rays together to quickly diagnose heart and lung problems in the ER. If you join, your medical information will be used to train and check the AI's accuracy.

Seoul

Hear when a new Emergency Medicine trial opens

We’ll email you when one opens — at most once a week, no account needed, unsubscribe anytime.