Search Results

Videa Dental Assist is a computer-assisted detection (CADe) device that analyzes intraoral radiographs to identify and localize the following features. Videa Dental Assist is indicated for the review of bitewing, periapical, and panoramic radiographs acquired from patients aged 3 years or older. Suspected Dental Findings: Caries, Attrition, Broken/Chipped Tooth, Restorative Imperfections, Pulp Stones, Dens Invaginatus, Periapical Radiolucency, Widened Periodontal Ligament, Furcation, Calculus. Historical Treatments: Crown, Filling, Bridge, Post and Core, Root Canal, Endosteal Implant, Implant Abutment, Bonded Orthodontic Retainer, Braces. Normal Anatomy: Maxillary Sinus, Maxillary Tuberosity, Mental Foramen, Mandibular Canal, Inferior Border of the Mandible, Mandibular Tori, Mandibular Condyle, Developing Teeth, Erupting Teeth, Non-matured Erupted Teeth, Exfoliating Teeth, Impacted Teeth, Crowding Teeth.

Videa Dental Assist (VDA) software is a cloud-based AI-powered medical device for the automatic detection of the features listed in the Indications For Use statement in dental radiographs. The device itself is available as a service via an API (Application Programming Interface) behind a firewalled network. Provided proper authentication and an eligible bitewing, periapical or panoramic image, the device returns a set of bounding boxes representing the suspect dental finding, historical treatment or normal anatomy detected. VDA is accessed by the dental practitioner through their dental image viewer. From within the dental viewer the user can upload a radiograph to VDA and then review the results. The device outputs a binary indication to identify the presence of findings for each indication. If findings are present the device outputs the number of findings by finding type and the coordinates of the bounding boxes for each finding. If no findings are present the device outputs a clear indication that there are no findings identified for each indication. The device output will show all findings from one radiograph regardless of the number of teeth present.

Here's a breakdown of the acceptance criteria and study details for the Videa Dental Assist device, as provided in the document:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that all listed sensitivity, specificity, and AFROC FOM results met their acceptance criteria, but generally does not explicitly list the specific numerical acceptance criteria. For the purpose of this table, "Met Acceptance Criteria" will be used when the text indicates it.

2. Sample Sizes Used for the Test Set and Data Provenance

• Standalone Performance Assessment (Bench Testing):
  • Sample Size: 1,445 radiographs
  • Data Provenance: Collected from more than 35 US sites (retrospective).
• Clinical Testing (MRMC Study):
  • Sample Size: 378 radiographs
  • Data Provenance: Collected from over 25 US locations spread across the country (retrospective).

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Standalone Performance Assessment (Bench Testing):
  • Number of Experts: Three
  • Qualifications: US board-certified dentists.
• Clinical Testing (MRMC Study):
  • Number of Experts: Not explicitly stated for the initial labeling, but labels were established by US licensed dentists. One US licensed dentist then adjudicated those labels.
  • Qualifications: US licensed dentists.

4. Adjudication Method for the Test Set

• Standalone Performance Assessment (Bench Testing): The document states the dataset was "ground-truthed by three US board-certified dentists." It doesn't specify a formal adjudication method (e.g., 2+1, 3+1). It implies a consensus or majority approach by multiple experts.
• Clinical Testing (MRMC Study): US licensed dentists labeled the data, and then one US licensed dentist adjudicated those labels to establish a reference standard for the study. This suggests a single adjudicator to resolve discrepancies or confirm final ground truth after initial labeling.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• Yes, an MRMC comparative effectiveness study was done.
• Effect Size (Average Percentage Improvement in AFROC FOM with VDA):
  • Attrition: 28.5% improvement (0.171 AFROC FOM increase)
  • Broken or Chipped: 15.3% improvement (0.105 AFROC FOM increase)
  • Calculus: 23.0% improvement (0.163 AFROC FOM increase)
  • Caries: 4.3% improvement (0.024 AFROC FOM increase)
  • Dens Invaginatus: 36.8% improvement (0.236 AFROC FOM increase)
  • Furcation: 29.7% improvement (0.199 AFROC FOM increase)
  • Periapical Radiolucency: 11.5% improvement (0.092 AFROC FOM increase)
  • Pulp Stone: 35.4% improvement (0.211 AFROC FOM increase)
  • Restorative Imperfection: 27.9% improvement (0.164 AFROC FOM increase)
  • Widened Periodontal Ligament: 28.4% improvement (0.141 AFROC FOM increase)

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Yes, a Standalone Performance Assessment was conducted.

7. The Type of Ground Truth Used

• Expert Consensus/Expert Review: For both the standalone performance assessment and the clinical study, the ground truth was established by multiple US board-certified or licensed dentists, either through direct ground-truthing or through labeling followed by adjudication. This falls under expert consensus or expert review.

8. The Sample Size for the Training Set

• The document mentions that "Videa Dental Assist artificial intelligence algorithms were trained with bitewing, periapical and panoramic radiographs" and "trained with that patient population" (referring to pediatric). However, the specific sample size of the training set is NOT provided in the document.

9. How the Ground Truth for the Training Set Was Established

• The document implies that the algorithms were "trained" with data, but does not explicitly describe how the ground truth for the training set was established. It can be inferred that it would also involve expert labeling, similar to the test sets, but no details are given.

Ask a specific question about this device