Clinical Validation of Boneview for FDA Submission

NCT04532580 | Completed FDA Device

• 1 other identifier: BCK-CEP
• Study Type: observational
• Target: 480
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this clinical validation is to assess comparative performances of physicians with and without the assistance of BoneView for the diagnosis of fractures on radiographs. The performances are evaluated in terms of accuracy (primary endpoint with the pair specificity/sensitivity and the secondary endpoint PPV/NPV) and in terms of time needed for diagnosis (secondary endpoint with the measurement of time on each case).

Conditions

Fracture

Keywords

fracture; artificial intelligence; x-rays radiographs

Outcome Measures

Primary Outcomes (1)

• measurement of diagnosis performances via calculation of sensitivity, specificity, NPV, PPV

  calculation of sensitivity, specificity, NPV, PPV and comparison between the two cohorts

  1 month

Secondary Outcomes (1)

• Time needed for diagnosis via measurement of the time before submission of the diagnosis

  1 month

Study Arms (2)

AI- Aided performances

Device: Diagnosis of fracture on X-Ray Radiographs

AI- Unaided performances

Device: Diagnosis of fracture on X-Ray Radiographs

Interventions

Diagnosis of fracture on X-Ray Radiographs DEVICE

Diagnosis of fracture on X-Ray Radiographs with and without the assistance of Boneview Software

AI- Aided performances; AI- Unaided performances

Eligibility Criteria

• Age: 21 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

The cases are consecutively sampled considering (non-)inclusion criteria (see below), and following these constraints: * At least 60 exams for the foot/ankle region, 60 exams for the knee/leg region, 60 exams for the hip/pelvis region, 60 exams for the hand/wrist region, 60 exams for the elbow/arm region, 60 exams for the shoulder/clavicula region, 60 exams of the rib cage region, 60 exams of the dorsolumbar spine region * 50% of exams of each region being positive: namely presenting one or multiple fracture(s) and 50% of exams of each region being negative: namely presenting no fracture * 50% of positive exams of each anatomical region presenting at least a "non-obvious" fracture and 50% with only "obvious" fracture(s). The determination of the "obvious" and "non-obvious" nature of the fractures would be determined during the Ground Truth determination process. The two osteo-articular experts that are performing the Ground Truth have to state the nature of the fracture.

You may qualify if:

• Anonymized standard X-ray exams of extremity/pelvis/rib cage/dorsolumbar spine not containing or containing fracture(s).
• Adult patient, with minimum age of 21 years old.

You may not qualify if:

• Exams with one or more images including a body part not concerned by the intended use of BoneView (skull and cervical spine)
• Cases with one or more images being used for model design and development.
• Exams with one or more images being of poor quality (lossy), which prevent a proper interpretation by the readers.
• Cases not containing a medically relevant number of views for correct diagnosis.

Sponsors & Collaborators

• Gleamer: lead

Study Sites (1)

Boston Imaging Core Lab

Boston, Massachusetts, 02118, United States

Location

MeSH Terms

Conditions

Fractures, Bone

Condition Hierarchy (Ancestors)

Wounds and Injuries

Study Officials

• Nor-Eddine Regnard, MD

  Gleamer

  STUDY CHAIR

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 25, 2020
• First Posted: August 31, 2020
• Study Start: September 1, 2020
• Primary Completion: May 10, 2021
• Study Completion: July 26, 2021
• Last Updated: August 12, 2021

Record last verified: 2021-08

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)