(87 days)
The Ortho Aligner System is indicated for the treatment of tooth malocclusion in patients with permanent dentition (i.e. all second molars). The Ortho Aligner System positions teeth by way of continuous gentle force.
The Ortho Aligner System is comprised of a series of clear, thin, thermoformed removable aligner trays that are designed to correct tooth malocclusions without the use of conventional wire and bracket orthodontic technology. The aligners are provided non-sterile and are customized for each patient according to the dental practitioner's prescription.
Physical impressions or digital intraoral scans of the patient's teeth are provided to Ortho Lab Services. A treatment plan consisting of 3D models is created from the impressions or scans, by Ortho Lab Services using the OrthoWare software. Upon approval of the treatment plan by the treating dental practitioner using OrthoPortal and issuance of an electronic prescription, the clear aligners are manufactured using thermoforming methods.
The finished, customized aligners are shipped based on the dental practitioner's order and confirmed for patient fit and design.
The aligner trays are held in place by pressure and can be removed by the patient at any time.
The provided document is a 510(k) Premarket Notification from the FDA for the Ortho Aligner System. It asserts substantial equivalence to a predicate device, focusing on material, design, manufacturing process, and safety testing rather than a standalone performance study with specific acceptance criteria related to clinical efficacy metrics (like sensitivity, specificity, or reader improvement with AI).
Therefore, based only on the provided text, a comprehensive answer to your request regarding acceptance criteria and a study proving device performance against those criteria (especially in the context of an AI-driven device with human-in-the-loop performance) cannot be fully provided.
Here's an attempt to answer based on the information available, and highlighting what is not present where your questions are relevant to AI/diagnostic performance studies:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not present a formal table of "acceptance criteria" in the way a diagnostic AI device would (e.g., target accuracy, sensitivity, specificity). Instead, it focuses on demonstrating equivalence to the predicate device through various non-clinical tests.
| Category | Acceptance Criteria (Implied Equivalence) | Reported Device Performance (Ortho Aligner System) |
|---|---|---|
| Biocompatibility | Meet ISO 10993-1, -5 (Cytotoxicity), and -10 (Sensitization/Irritation) requirements for the material and finished device. | Passed: Testing performed for the material supplier and for the finished thermoformed aligner meeting ISO 10993-1, Part 5 (Cytotoxicity), and Part 10 (Sensitization) requirements. All biocompatibility testing passed the test requirements. |
| Software Verification & Validation (V&V) | Software system confirms acceptance to required specifications (per FDA's guidance document). | Confirmed Acceptance: Software V&V testing, using FDA's guidance document, confirmed acceptance to required specifications. |
| Bench Testing (Manufacturing Process Validation) | Ensure accuracy of the final thermoformed aligner compared to the initial digital scans; aligners meet specifications of the testing. | Met Specifications: Testing to validate the manufacturing process was performed. The test results ensured the accuracy of the final thermoformed aligner compared to the initial digital scans. Aligners met the specifications of the testing. |
| Material | Same type of biocompatible material as the predicate (PET-G thermoplastic sheet). | Same Type: Thermoplastic PETG, which is the same material type as the predicate. |
| Manufacturing Process | Standard methods and equipment to thermoform the designed aligners, similar to the predicate. | Similar Methods: Thermoforming on models, which is the same process method as used by the Predicate device manufacturer, using standard methods and equipment. |
| Software Functionality | Same purpose as predicate's software: treatment planning and design via digital scans to generate images of final treated states, intermediate steps, and convert files for aligner production. | Same Purposes/Similar Software: Ortho Lab Services uses OrthoWare software, which is similar to the Predicate manufacturer's Smart Moves Complete 3-D software. Both use digital scans to generate images and produce customized aligners. |
| Indications for Use | Same as the predicate device. | Same: Indicated for the treatment of tooth malocclusion in patients with permanent dentition (i.e., all second molars), positioning teeth by way of continuous gentle force. This is identical to the predicate's indications. |
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Not explicitly stated for performance testing regarding the aligner's ability to correct malocclusion in patients. The "Bench testing" refers to validation of the manufacturing process's accuracy against digital scans, not a patient cohort. Biocompatibility testing results are reported for the material and a finished thermoformed aligner, but specific sample sizes of tested items are not provided.
- Data Provenance: Not specified. The document relates to a 510(k) submission, not a clinical trial report where such details would be standard.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is typically relevant for diagnostic AI devices where expert readings establish ground truth. For the Ortho Aligner System, which is a physical device for orthodontic treatment, "ground truth" relates to material properties, manufacturing accuracy, and the mechanical ability to apply force for tooth movement. The document does not describe expert human readers establishing ground truth. The "treatment plan" is approved by "the treating dental practitioner."
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
Not applicable in the context of this device and the described testing. Adjudication methods are used in diagnostic studies, typically involving multiple readers.
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
No MRMC study was performed or described. This type of study is relevant for AI-assisted diagnostic tools. The Ortho Aligner System itself is an aligner, and its associated software (OrthoWare) is for treatment planning and design, not for diagnostic assistance to human readers in the way an AI medical imaging algorithm would be.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
A standalone software V&V was conducted, confirming the software (OrthoWare) met its specifications. However, this is for the software that designs the aligners, not a standalone diagnostic algorithm whose performance needs to be measured independently of human input. The entire system (aligners + software) is designed to be used by a dental practitioner (human-in-the-loop) for treatment.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
The "ground truth" in this context refers to engineering and manufacturing specifications:
- Biocompatibility: Established by ISO standards.
- Software V&V: Established by defined software requirements and FDA guidance.
- Bench Testing: Established by the "initial digital scans" and "specifications of the testing" for accuracy.
No clinical outcomes data or expert consensus on patient outcomes is presented as "ground truth" for proving efficacy, as the submission relies on substantial equivalence to a legally marketed predicate device. Animal and human clinical performance testing were explicitly stated as not required for this device category.
8. The sample size for the training set
Not applicable. This is not an AI algorithm that learns from a "training set" in the sense of machine learning for diagnostics. The software (OrthoWare) is a design tool based on existing models and algorithms for tooth movement, not a deep learning system trained on a large dataset of tooth malocclusions.
9. How the ground truth for the training set was established
Not applicable (as per point 8).
§ 872.5470 Orthodontic plastic bracket.
(a)
Identification. An orthodontic plastic bracket is a plastic device intended to be bonded to a tooth to apply pressure to a tooth from a flexible orthodontic wire to alter its position.(b)
Classification. Class II.