Assessing AI-Supported Fracture Detection in Emergency Care Units
Trial statusRecruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
AgeNot listed
SponsorSalzburger Landeskliniken
About this trial
Brief Summary The purpose of this study is to determine if artificial intelligence (AI) can assist doctors in detecting broken bones, effusions, dislocations and bone lesions more quickly and accurately in an emergency room setting. The study will also evaluate whether AI can save time and reduce costs in healthcare.
The main questions to be addressed are:
* Does AI improve the accuracy of detecting broken bones/dislocations/effusions/bone lesions? * Can AI expedite the process of diagnosing broken bones/dislocations/effusions/bone lesions? * Does AI reduce healthcare costs by enhancing efficiency?
To investigate these questions, two groups of patients will be compared. One group will follow the traditional diagnostic approach, while the other group will utilize AI to assist in diagnosing X-rays.
Participants in the study will:
Undergo standard X-ray imaging of injured arms or legs, as part of routine care.
Have X-rays reviewed by doctors with or without AI support, depending on the assigned group.
The study will include patients of all ages presenting to the emergency room with an isolated injury or joint complaints. No additional tests or treatments beyond standard care will be involved.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Presenting to the emergency department with an isolated injury or joint complaint
Patients able and willing to provide informed consent.
Disqualifiers
Patients with injuries or complaints involving multiple body regions
Patients with prior imaging of the affected extremity or region within the past 6 months
Contraindications to X-ray imaging (e.g., pregnancy or severe instability)
Patients with other ongoing studies that may interfere with this study
Trial design
Design model
Parallel
Treatments tested in this trial
AI-Assisted Fracture Detection System
Diagnostic testThe intervention involves the use of an AI-assisted fracture detection system (Aidoc or Gleamer BoneView), which is integrated into the hospital's Picture Archiving and Communication System (PACS). These AI tools analyze X-ray images in real time, highlighting potential fracture sites for physician review. The AI output serves as an additional aid, while the final diagnosis remains the responsibility of the physician.
Standard Physician-Interpreted Fracture Detection
Diagnostic testPhysicians interpret X-ray images using their standard diagnostic practices without any assistance from AI. This represents the traditional approach to diagnosing fractures.
Treatment groups
4,800 Participants
are divided into 2 treatment groupsGroup A: Diagnostics without AIActive comparator 1 intervention
Group B: Diagnostics with AIExperimental treatment 1 intervention
Trial outcomes
Primary outcomes
1
Diagnostic Accuracy of Fracture/Dislocation/Effusion/Bone Lesion Detection
The primary outcome measures the diagnostic accuracy of detecting broken bones/dislocations/effusions/bone lesions using sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). Diagnostic accuracy will be compared between the AI-assisted diagnostic approach and the standard physician-only approach. The gold standard for comparison will be determined by expert consensus based on independent review by a radiologist and an orthopedic specialist.
Time frame
At the time of initial diagnosis, within 2 hours of patient presentation to the orthopedic emergency unitSecondary outcomes
1
Time to Diagnosis
The time required to establish a diagnosis, measured from the moment the patient undergoes X-ray imaging to the time the final diagnosis is recorded. This will compare the efficiency of the AI-assisted diagnostic workflow with the standard physician-only workflow.
Time frame
During the patient's emergency department visit, typically within 4 hours of presentation.2
Physician Diagnostic Confidence
The level of confidence reported by physicians in their diagnostic decisions, measured on a Likert scale (1-10). This will compare how confident physicians feel when using AI assistance versus relying solely on their expertise.
Time frame
Measured immediately after the diagnosis3
Cost-Efficiency of Diagnostic Workflow
A cost analysis evaluating the total costs associated with the diagnostic process in each group, including personnel time, resource utilization, and any additional procedures required. This will determine whether AI-assisted diagnostics reduce overall healthcare costs compared to standard practices.
Time frame
Calculated at the end of the study for all enrolled participants, approximately 6 months from study initiation.Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Salzburger Landeskliniken
Lead sponsor
Klinikum Nürnberg
Collaborator
Source ClinicalTrials.gov