Search Results

The Invisalign System is intended for the orthodontic treatment of malocclusion.

The subject device, Invisalign System with Pre-Formed Attachments (PFA) System, is a modification to the predicate device, the Invisalign System (K220287, cleared on April 7th, 2022). The Invisalign System with PFA system consists of removable orthodontic appliances (aligners), proprietary treatment planning 3D software, attachment templates and/or PFA system.

Like the predicate device, the Invisalign system with PFA (subject device) consists of a series of doctor prescribed, customized, thin, clear plastic aligners that gently move the patient's teeth in small increments from their original state to a more optimal, treated state to address dental malocclusion. The Invisalian system aligners are used in patients with primary, mixed (primary and permanent), and permanent dentition. The Invisalign system aligners with mandibular advancement feature(s) are used in patients with mixed and permanent dentition to correct Class II malocclusions. The Invisalign system is intended to treat dental and skeletal malocclusion in patients with Class I, II and III including Antero-Posterior (A-P), vertical (open bite, deep bite), transverse (narrow arch or jaw, crossbite), or inter-arch (spacing and crowding) correction at all severity levels. In some cases, surgical intervention, or addition of other appliances in addition to Invisalign treatment may be needed at the doctor's discretion.

The proprietary ClinCheck (CC) 3-D software is inclusive of both dental practitioner-facing functions and internal Align personnel-facing functions. The Align facing software enables Align's computer-aided design (CAD) designers to create a treatment plan based on a doctor's prescription and inputs (e.g., dental scans). The treatment plans created using the Align personnel-facing software are then reviewed and approved by doctors before the aligners are manufactured. The doctors' reviews and approvals are exchanged via ClinCheck software (dental practitioner-facing software). Once the treatment plan is approved by the dental practitioner, the information is sent to the manufacturing facility for creation of the aligners.

When attachments are prescribed as part of the treatment plan, the subject device has the option of delivering them preformed with PFA system or with a disposable attachment template. The attachment templates are disposable polyurethane appliances which match the patient's existing dentition and include wells for the placement of dental composite (sold separately). During the first visit, the dental practitioner uses the template in bonding dental composite to the tooth surface to create attachments on the teeth. These attachments help create forces on the tooth which can assist aligner retention or optimized aligner force system for tooth movement.

The PFAs are made of a fully cured proprietary photo-polymerizable methacrylate-based resin (similar to dental composite material). PFA system is intended to enable correct placement of attachments and bond attachments to the tooth surface for aligner retention and to optimize aligner force system for tooth movement.

The patient-customized PFA are manufactured using additive manufacturing technologies and configured to individual patient's treatment plans and teeth anatomy using a proprietary internal facing 3D device-generation manufacturing software.

Based on the provided text, the device in question is the "Invisalign System with Pre-Formed Attachment System" (PFA System), which is an alternative attachment delivery mechanism for the existing Invisalign System. The 510(k) submission seeks clearance for this addition.

The provided text does NOT describe a typical AI/ML-based medical device performance study with acceptance criteria related to sensitivity, specificity, accuracy, or human reader improvement. Instead, it describes a modification to an existing medical device and demonstrates its substantial equivalence to a predicate device. The "performance data" section focuses on engineering and biocompatibility testing for the new component, not diagnostic performance metrics or human-AI interaction.

Therefore, many of the requested points related to AI/ML study design (such as sample size for test/training sets, expert ground truth establishment, MRMC studies, standalone performance, etc.) are not applicable to this specific submission, as it focuses on an engineering modification rather than an AI/ML diagnostic algorithm.

Here's a breakdown based on the information available:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes performance testing for the new PFA system, but it does not specify quantitative acceptance criteria in a table format with corresponding numerical performance results for each criterion. Instead, it makes a general statement that the testing outcomes support substantial equivalence.

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

• Sample Size: Not specified for the performance testing. The study is not a clinical trial or an AI/ML algorithm evaluation using patient data. It's an engineering and biocompatibility assessment of a new component.
• Data Provenance: Not applicable in the context of patient data. The "data" refers to the results of engineering and lab tests (e.g., measuring bond strength, stain resistance).

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

• Not Applicable. This is not an AI/ML diagnostic device where experts establish ground truth for images or clinical cases. The "ground truth" for this device modification is based on engineering specifications and regulatory standards (e.g., successful bond strength test, ISO biocompatibility compliance).

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not Applicable. As there are no human readers establishing ground truth for diagnostic decisions, no adjudication method is described.

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. An MRMC study was not done. This submission is about a mechanical/material modification (Pre-Formed Attachment system), not a diagnostic AI that assists human readers. No effect size on human reader improvement is relevant or reported.

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

• Not Applicable / Not a standalone AI algorithm. The new component is an alternative delivery mechanism for attachments in an orthodontic system that relies on a doctor's prescription and approval of treatment plans. It's not a standalone AI algorithm producing a diagnostic output. While there is "proprietary, 3D device-generation manufacturing software," its V&V is mentioned, but its performance is not assessed as a standalone diagnostic tool.

7. The type of ground truth used:

• Engineering Specifications and Standardized Biocompatibility Testing Protocols. The ground truth for this kind of device modification is established by meeting predefined physical/mechanical properties and complying with established biocompatibility standards (e.g., ISO 10993-1, ISO 7405).

8. The sample size for the training set:

• Not Applicable. This is not an AI/ML device that requires a "training set" of data in the sense of machine learning. The term "training set" usually refers to data used to train an algorithm. Performance assessment here relates to manufacturing processes and material properties.

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

• Not Applicable. (See point 8).

In Summary:

The provided document describes a 510(k) submission for a non-AI device modification. The "study that proves the device meets the acceptance criteria" is a series of engineering, materials, and software verification and validation tests (bond strength, stain resistance, wear, force measurement, volume precision, usability, biocompatibility per ISO standards, and software V&V per IEC standards), rather than a clinical performance study evaluating an AI algorithm using patient data and expert ground truth. The acceptance criteria are implicitly met if the test outcomes validate that the new component "does not impact the current safety and effectiveness profile of the Invisalign System" and allows for a finding of "substantial equivalence" to the predicate device.

Ask a specific question about this device