Search Results
Found 1 results
510(k) Data Aggregation
(113 days)
Adravision Perio is a radiological semi-automated image processing software device intended to aid dental professionals in the measurements of mesial and distal bone levels associated with each tooth from bitewing and periapical radiographs. It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis.
The intended users of Adravision Perio are trained professionals including, but not limited to, dental hygienists.
The intended patient population of the device is patients living in the United States, who are 22 years old or older, and that do not have any remaining primary teeth. Adra Corporation has not evaluated the performance of the device on primary dentition.
Adravision Perio is a Software as a Medical Device (SaMD intended to aid dentists in the measurement of mesial and dista bone levels associated with each tooth on bitewing and periapical dental radiographs of permanent teeth in patients 22 years of age or older.
The device provides assistance to dentists by suggesting the measurement of interproximal bone levels. The device recommendations are for reference only and the user should review associated radiographs, view annotations and modify annotations if needed. The device is not intended as a replacement for a complete clinician's review or their clinical judgment because users can take into account other relevant information from the image, intraoral exam or patient history.
The Adravision Perio device provides semi-automated image processing software to aid dental professionals in measuring mesial and distal bone levels from bitewing and periapical radiographs. This analysis details the acceptance criteria and the study proving the device meets these criteria.
1. Acceptance Criteria and Reported Device Performance
The core performance of the device was assessed using two main metrics related to bone level measurements from radiographs: Object Key Similarity (OKS) and Length Measurement.
OKS Assessment Acceptance Criteria & Performance:
| Metric | Acceptance Criteria (Not Explicitly Stated, Inferred from Performance) | Reported Device Performance (Bitewing) | Reported Device Performance (Periapical) |
|---|---|---|---|
| Precision | High (e.g., >80-85%) | 91.0% | 84.8% |
| Recall | High (e.g., >85-90%) | 94.0% | 89.3% |
Note: The document doesn't explicitly state quantitative acceptance criteria for Precision and Recall, but the reported performance values indicate that the device met internal thresholds for demonstrating sufficient accuracy in key point detection.
Length Measurement Assessment Acceptance Criteria & Performance:
| Metric | Acceptance Criteria (Not Explicitly Stated, Inferred from Performance) | Reported Device Performance (Bitewing) | Reported Device Performance (Periapical) |
|---|---|---|---|
| Sensitivity | High (e.g., >85-90%) | 90.7 % | 92.5 % |
| Specificity | High (e.g., >85-90%) | 94.3 % | 86.8 % |
| Mean Absolute Error | Low (e.g., 90%) | 91.8% | |
| Overall Tooth Number Classification Accuracy (Length Assessment) | High (e.g., >90%) | 93.2% |
2. Sample Sizes and Data Provenance
- OKS Assessment Test Set: 340 dental radiographs (bitewing and periapical radiographs).
- Length Measurement Assessment Test Set: 78 dental radiographs.
- Data Provenance: The radiographs were "collected retrospectively." No specific country of origin is mentioned, but the intended patient population is stated as "patients living in the United States."
3. Number of Experts and Qualifications for Ground Truth
- OKS Assessment: "a ground truther" (singular). No specific qualifications are listed for this individual.
- Length Measurement Assessment: "three (3) ground truthers." No specific qualifications are listed for these individuals.
4. Adjudication Method for the Test Set
- OKS Assessment: Not explicitly stated, but implies a single ground truther, so no formal adjudication method (e.g., 2+1, 3+1) is indicated.
- Length Measurement Assessment: The document states "consensus CAL length measurements labeled by three (3) ground truthers," implying an adjudication process to reach a consensus, but the specific method (e.g., simple majority, discussion to resolve discrepancies) is not detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study was mentioned or performed. The studies described are standalone performance evaluations against established ground truths, not studies comparing human reader performance with and without AI assistance.
6. Standalone Performance
Yes, a standalone (algorithm only without human-in-the-loop performance) was performed. The "Bench Testing" section describes evaluations of the Adravision Perio device's performance against ground truth data, focusing on precision, recall, sensitivity, specificity, and mean absolute error, which are metrics typically used for standalone algorithm performance.
7. Type of Ground Truth Used
The ground truth for both OKS and Length Measurement assessments was based on expert labeling/consensus.
- For OKS, it was "key points labeled by a ground truther."
- For Length Measurement, it was "consensus CAL length measurements labeled by three (3) ground truthers."
8. Sample Size for the Training Set
The document does not provide information on the sample size used for the training set. It only describes the test sets used for performance evaluation.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth was established for the training set. The descriptions are limited to the establishment of ground truth for the test sets.
Ask a specific question about this device
Page 1 of 1