Assessing AI-Supported Fracture Detection in Emergency Care Units

Evaluating the Cost-Efficiency and Workflow Impact of AI-Supported Fracture Detection in an Orthopedic Emergency Care Unit

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.

Study Overview

• Status: Recruiting
• Conditions: Fractures, Bone; Effusion Joint; Dislocation; Bone Lesion
• Intervention / Treatment: Diagnostic test: Standard Physician-Interpreted Fracture Detection; Diagnostic test: AI-Assisted Fracture Detection System

Detailed Description

This clinical trial aims to evaluate the cost-efficiency and workflow impact of AI-assisted fracture detection in an orthopedic emergency care unit. The study is designed as a prospective, randomized, controlled trial to assess whether integrating AI technology can improve diagnostic accuracy, streamline workflow, and reduce healthcare costs compared to the traditional diagnostic approach.

Study Objectives

Primary Objectives:

The primary objective of the SMART Fracture Trial is to assess the impact of AI-assisted X-ray interpretation on physician decision-making and clinical workflows. The study will therefore provide deeper insights into AI's potential benefits and limitations beyond theoretical performance metrics.

Secondary Objectives:

While the primary focus of the SMART Fracture Trial is on AI's clinical integration, the study will also comprehensively assess diagnostic accuracy and classification performance - key factors that influence real-world implementation. By analyzing these secondary objectives, the study will provide deeper insights into AI's theoretical performance metrics.

Study Design

This is a prospective, randomized, controlled trial conducted as an international multi-center study. It includes two parallel arms:

Control Group: Standard diagnostic procedures without AI assistance. Intervention Group: AI-based diagnostic tools assist in interpreting radiological images.

Both groups will follow the same diagnostic imaging protocol, including standard X-ray imaging in two planes. The AI software, pre-validated for fracture detection, will be integrated into the hospital's Picture Archiving and Communication System (PACS).

Intervention Details

The AI fracture detection systems (Aidoc, Gleamer) are designed to identify fracture patterns, bone lesions, effusion and dislocations on X-rays and highlight areas of potential concern for physician review. The software operates in real time, providing marked-up images to physicians. The AI output serves as a diagnostic aid, with final diagnoses made by the attending physician.

Population and Sampling

Population: Patients of all ages presenting to the emergency care unit with isolated extremity injuries or isolated joint complaints.

Sample Size: Approximately 4,800 participants (2400 per group) to ensure sufficient statistical power for primary outcomes.

Randomization: Participants will be randomly assigned to the control or intervention group using a 1:1 allocation ratio.

Outcome Measures

Primary Outcome Measures:

Diagnostic accuracy: Sensitivity, specificity, and AUC of AI-assisted vs. traditional diagnosis.

Time to diagnosis: Total time from patient triage to final diagnosis.

Secondary Outcome Measures:

Cost analysis: A detailed cost comparison of the diagnostic process in both groups.

Diagnostic confidence: Assessed using a Likert scale (1-10) completed by physicians after reviewing each case.

Study Procedures

Baseline Data Collection: Demographics, clinical history, and presenting symptoms will be recorded at enrollment. Standard radiological imaging will be conducted for all participants.

AI Integration (Intervention Group): Radiological images will be processed by AI software, providing annotated images to physicians. AI-assisted diagnostic workflows will be compared to standard workflows.

Outcome Assessment: All diagnoses will be independently reviewed by a panel of experts, including an experienced radiologist and orthopedic surgeon, to establish a reference standard for comparison.

Ethical Considerations

The study adheres to the principles of the Declaration of Helsinki and has received approval from the local ethics committee. Written informed consent will be obtained from all participants before enrollment. Data will be pseudonymized to maintain confidentiality.

Expected Impact

This study aims to provide robust evidence regarding the effectiveness of AI in improving diagnostic workflows in emergency care settings. Findings may inform the future integration of AI tools into clinical practice, improving patient outcomes and optimizing resource utilization in high-volume emergency care environments.

• Study Type: Interventional
• Enrollment (Estimated): 4800
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Martin Breitwieser, MD, MBA, BSc; Phone Number: 54705 +43 5 7255; Email: m.breitwieser@salk.at

Study Locations

• Austria
  • Hallein, Austria, 5400
    • Not yet recruiting
    • Landesklinik Hallein, Salzburger Landeskliniken
    • Contact: Sebastian Filipp, MD; Phone Number: +43 57 25544 55354; Email: s.filipp@salk.at
  • Salzburg, Austria, 5020
    • Recruiting
    • University Hospital Salzburg, Salzburger Landeskliniken
    • Contact: Martin Breitwieser, MD, MBA, BSc; Phone Number: +43 57 2550 54705; Email: m.breitwieser@salk.at
• Germany
  • Nuremberg, Germany, 90471
    • Recruiting
    • University Hosptial Nuremberg, Klinikum Nürnberg
    • Contact: Thomas Reuter, MD; Phone Number: +49 911 3982600; Email: thomas.reuter@klinikum-nuernberg.de

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Presenting to the emergency department with an isolated injury or joint complaint
• Patients able and willing to provide informed consent.

Exclusion Criteria:

• 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
• Patients unable to provide consent due to cognitive impairment or language barriers without an available representative.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Diagnostics without AI; Standard diagnostic approach where physicians interpret X-ray images without AI assistance.	Diagnostic test: Standard Physician-Interpreted Fracture Detection; Physicians interpret X-ray images using their standard diagnostic practices without any assistance from AI. This represents the traditional approach to diagnosing fractures.
Experimental: Diagnostics with AI; Diagnostic approach where physicians are supported by an AI system (Aidoc or Gleamer BoneView) for fracture detection on X-ray images.	Diagnostic test: AI-Assisted Fracture Detection System; The 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	At the time of initial diagnosis, within 2 hours of patient presentation to the orthopedic emergency unit

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	During the patient's emergency department visit, typically within 4 hours of presentation.
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.	Measured immediately after the diagnosis
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.	Calculated at the end of the study for all enrolled participants, approximately 6 months from study initiation.

Collaborators and Investigators

• Sponsor: Salzburger Landeskliniken
• Collaborators: Klinikum Nürnberg

Publications and helpful links

General Publications

• Breitwieser M, Zirknitzer S, Poslusny K, Freude T, Scholsching J, Bodenschatz K, Wagner A, Hergan K, Schaffert M, Metzger R, Marko P. AI in Fracture Detection: A Cross-Disciplinary Analysis of Physician Acceptance Using the UTAUT Model. Diagnostics (Basel). 2025 Aug 21;15(16):2117. doi: 10.3390/diagnostics15162117.

Study record dates

Study Major Dates

• Study Start (Actual): March 31, 2025
• Primary Completion (Estimated): April 30, 2026
• Study Completion (Estimated): April 30, 2026

Study Registration Dates

• First Submitted: December 9, 2024
• First Submitted That Met QC Criteria: December 20, 2024
• First Posted (Actual): December 31, 2024

Study Record Updates

• Last Update Posted (Actual): January 22, 2026
• Last Update Submitted That Met QC Criteria: January 20, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Diagnostic Accuracy; Effusion; Emergency Care; Dislocation; Fracture Detection; Cost-Efficiency; AI-Assisted Diagnosis; Orthopedic Diagnostics; Bone Lesion
• Additional Relevant MeSH Terms: Musculoskeletal Diseases; Wounds and Injuries; Joint Diseases; Fractures, Bone; Joint Dislocations; Hydrarthrosis
• Other Study ID Numbers: KI-FRACTURE_001_2024-11-27

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES

IPD Plan Description

Upon written request access to data will be provided. All shared data will be fully anonymized to remove any identifying information, including names, dates of birth, and any other personal identifiers, in compliance with data protection regulations (e.g., GDPR). The data will be shared only for research purposes and under appropriate data-sharing agreements to protect patient privacy.

The following anonymized individual patient data (IPD) will be shared:

• Demographic Data: Age, sex
• Diagnostic Data: Anatomical Location, Clinician findings, AI findings, Radiologist findings
• Outcome Data: Time to diagnosis, sensitivity, specificity
• Survey Data: Physician diagnostic confidence scores

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No