Clinical Validation of Boneview for FDA Submission

Clinical Validation of Boneview for FDA Submission: Evaluation of the Ability of the Artificial Intelligence Software, Boneview, to Improve Physicians' and Radiologists' Performances in Detecting Fractures on Bone X-Rays Radiographs.

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).

Study Overview

• Status: Completed
• Conditions: Fracture
• Intervention / Treatment: Device: Diagnosis of fracture on X-Ray Radiographs

• Study Type: Observational
• Enrollment (Actual): 480

Contacts and Locations

Study Locations

• United States
  • Massachusetts
    • Boston, Massachusetts, United States, 02118
      • Boston Imaging Core Lab

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 21 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• 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.

Description

Inclusion Criteria:

• 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.

Exclusion Criteria:

• 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.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
AI- Aided performances	Device: Diagnosis of fracture on X-Ray Radiographs; Diagnosis of fracture on X-Ray Radiographs with and without the assistance of Boneview Software
AI- Unaided performances	Device: Diagnosis of fracture on X-Ray Radiographs; Diagnosis of fracture on X-Ray Radiographs with and without the assistance of Boneview Software

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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 Outcome Measures

Outcome Measure	Measure Description	Time Frame
Time needed for diagnosis via measurement of the time before submission of the diagnosis	measurement of the time and comparison between the two cohorts	1 month

Collaborators and Investigators

• Sponsor: Gleamer
• Investigators: Study Chair: Nor-Eddine Regnard, MD, Gleamer

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2020
• Primary Completion (Actual): May 10, 2021
• Study Completion (Actual): July 26, 2021

Study Registration Dates

• First Submitted: August 25, 2020
• First Submitted That Met QC Criteria: August 25, 2020
• First Posted (Actual): August 31, 2020

Study Record Updates

• Last Update Posted (Actual): August 12, 2021
• Last Update Submitted That Met QC Criteria: August 6, 2021
• Last Verified: August 1, 2021

More Information

Terms related to this study

• Keywords: artificial intelligence; fracture; x-rays radiographs
• Additional Relevant MeSH Terms: Wounds and Injuries; Fractures, Bone
• Other Study ID Numbers: BCK-CEP

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: no sharing of our IPD

Drug and device information, study documents

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