Search Results

Overjet Periapical Radiolucency (PARL) Assist is a radiological, automated, concurrent read computer-assisted detection software intended to aid in the detection of periapical radiolucencies on permanent teeth captured on periapical radiographs. The device provides additional aid for the dentist to use in their identification of periapical radiolucency. The device is not intended as a replacement for a complete dentist's review or their clinical judgment that considers other relevant information from the image or patient history. The system is to be used by professionally trained and licensed dentists.

The Overjet Periapical Radiolucency Assist software is indicated for use on patients 12 years of age or older.

Overjet Periapical Radiolucency "PARL" Assist is a module within the Overjet Platform. The Overjet PARL Assist (OPA) software automatically detects periapical radiolucency on periapical radiographs. It is intended to aid dentists in the detection of periapical radiolucency. It should not be used in lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by professionally trained and licensed dentists. Overjet PARL Assist is a software-only device which operates in three layers: a Network Layer, aPresentation Layer, and a Decision Layer. Images are pulled in from a clinic/dental office, and the Machine Learning model creates predictions in the Decision Layer and results are pushed to the dashboard, which are in the Presentation Layer.

Here's a detailed breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details

2. Sample size used for the test set and the data provenance:

• MRMC Reader Study Test Set: 379 periapical radiographs (190 images with at least 1 PARL and 189 images with no PARL).
  • Data Provenance: Images were obtained from various clinical sites across the U.S. from male and female patients aged 12 years and older. (Retrospective, implied, as it's a collected dataset for testing).
• Standalone Performance Testing Test Set: 763 periapical images + 384 additional images, totaling 1147 images.
  • Data Provenance: Images were obtained from various clinical sites across the U.S. from male and female patients aged 12 years and older. (Retrospective, implied).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: 3
• Qualifications of Experts: Endodontists (specific experience/years not detailed, but their specialty implies relevant expertise).

4. Adjudication method for the test set:

• Adjudication Method: Consensus reference standard established by 3 endodontists. (This implies all three experts agreed on the ground truth for each case; no specific 2+1 or 3+1 method is explicitly stated, but "consensus" suggests agreement among all three).

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• MRMC Comparative Effectiveness Study: Yes, an MRMC fully crossed reader improvement study was conducted.
• Effect Size / Improvement with AI Assistance:
  • Image-level AUC: 4.8% (95% CI: 0.030, 0.066) improvement in assisted readers compared to unassisted readers.
  • Image-level sensitivity: Average increase of 13.6% (0.110, 0.165) for assisted readers.
  • Image-level specificity: Decreased by 7.1% from 83.2% to 76.1% (-0.071 difference, Cls (-0.099, -0.042)).
  • Instance (polygon) level sensitivity: Average increase of 16.2% (0.125, 0.194) for assisted readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Standalone Performance Testing: Yes, standalone performance of the Overjet PARL Assist device was evaluated.

7. The type of ground truth used:

• Ground Truth Type: Expert consensus from 3 endodontists.

8. The sample size for the training set:

• The document does not explicitly state the sample size for the training set. It only provides details for the test sets used in the MRMC reader study and standalone performance testing.

9. How the ground truth for the training set was established:

• The document does not explicitly state how the ground truth for the training set was established. It only describes the ground truth establishment for the test sets via consensus of 3 endodontists.

Ask a specific question about this device