AI-support in Emergency Medicine

NCT07766863 | Recruiting

• 1 other identifier: K 2024-7038
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 1

Brief Summary

The purpose of this study is to investigate whether the use of generative artificial intelligence (AI) as a support tool can improve physicians' ability to establish accurate differential diagnoses in emergency care. The main questions it aims to answer are:

• Is AI-assisted differential diagnosis more accurate than the differential diagnosis performed by physicians?
• Does physicians' differential diagnosis change - in terms of the number of correct diagnoses - when they have access to AI-assisted differential diagnosis?

Conditions

Emergency Medicine; AI (Artificial Intelligence); Differential Diagnosis

Keywords

emergency medicine; AI (artificial intelligence); Differential diagnosis

Outcome Measures

Primary Outcomes (2)

• The proportion of cases in which the final diagnosis is ranked highest by the physician and by the AI support, respectively

  Considering the final diagnosis after discharge from the hospital.

  At discharge from the hospital

• The proportion of physicians' differential diagnosis that change, in terms of the number of correct diagnoses, when they have access to AI-assisted differential diagnosis

  This is meassured after the patient has been discharged from the hospital

  After discharge from the hospital

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients admitted to the hospital via the emergency department at Karolinska University Hospital in Huddinge and Solna, Sweden.

You may qualify if:

• Adult patients \>18 years admitted through the emergency departments at Karolinska University Hospital in Huddinge and Solna.

You may not qualify if:

• Children \<18 years
• Patients without a recorded final diagnosis

Sponsors & Collaborators

• Region Stockholm: lead
• Karolinska Institutet: collaborator
• Karolinska University Hospital: collaborator

Study Sites (1)

Karolinska University Hospital

Stockholm, Huddinge, 14186, Sweden

RECRUITING

Central Study Contacts

Maria Ygland Rödström, PI

CONTACT

+46 702653628; maria.ygland.rodstrom@ki.se

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER GOV
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Specialist in Emergency Medicine, PI, PhD

Study Record Dates

• First Submitted: May 6, 2026
• First Posted: August 17, 2026
• Study Start: June 8, 2026
• Primary Completion (Estimated): June 1, 2029
• Study Completion (Estimated): June 1, 2029
• Last Updated: August 17, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share

Locations

SE (1)