K Number
K201940
Date Cleared
2020-12-03

(143 days)

Product Code
Regulation Number
872.5470
Panel
DE
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Braces on Demand Bracket is intended for use as a clear, plastic bracket system to provide orthodontic movement of natural teeth.

Device Description

The proposed device is a 3D-printed bracket system that directly bonds to either primary teeth, permanent teeth, or mixed dentition to provide for orthodontic treatment for patients with malocclusions. Each bracket is 3D printed using a photopolymer denture resin. The Braces on Demand Bracket System has an integral hook design, which allows for attachment of accessories such as elastics or springs to assist the clinician in producing the desired tooth movement. The hook position on the Braces on Demand brackets can be on the mesial occlusal tiewing or the distal occlusal tiewing, similar to traditional orthodontic brackets. The application and removal of the Braces on Demand brackets are similar to other orthodontic brackets in that it requires orthodontic adhesive for bonding and standard orthodontic tools and techniques for de-bonding. The bonding surface of the bracket is a mechanical dovetail undercut design, allowing the bracket to mechanically retain the adhesive and bond to the facial surface of the tooth.

AI/ML Overview

The provided document is a 510(k) Summary for the "Braces on Demand Bracket." It primarily focuses on demonstrating substantial equivalence to predicate devices based on various characteristics, manufacturing processes, and material properties. However, it does not contain information about acceptance criteria for device performance (such as accuracy, sensitivity, specificity, or other performance metrics typically associated with AI/ML devices), nor does it describe a study specifically designed to prove the device meets such criteria.

The information provided relates to testing for physical properties and biocompatibility, which are different from the performance metrics typically found in studies for AI/ML-driven devices.

Therefore, I cannot provide the requested information about acceptance criteria and a study that proves the device meets them from the given text.

Here's an breakdown of the requested information, indicating why it cannot be extracted:

  1. A table of acceptance criteria and the reported device performance

    • Not found. The document discusses "Bond Strength and Hook Strength testing" and "Dimensional Analysis and Dimensional Stability Tests," stating that the device was found "substantially equivalent" to the predicate. However, it does not provide specific acceptance criteria values (e.g., "bond strength > X MPa") or specific reported performance values. It also doesn't mention any performance metrics related to orthodontic movement efficacy that would typically be assessed in a clinical study.
  2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    • Not found. No information is given about sample sizes for any performance testing, nor about data provenance.
  3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

    • Not found. This section is relevant for studies involving human experts for ground truth assessment (e.g., image interpretation). This document does not describe such a study.
  4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

    • Not found. This is typically associated with ground truth establishment by multiple experts. Not applicable here.
  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

    • Not found. The document explicitly states: "No animal or human testing are required for this product because it is composed of the same materials, is designed similarly, and is manufactured by method similar to the predicate device." Therefore, no MRMC study or study involving human readers with/without AI assistance was conducted or reported.
  6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

    • Not found. While the device involves software for design and manufacturing, the document does not describe a standalone performance study of an algorithm in the context of clinical decision-making or diagnosis. The software verification and validation are for the manufacturing process, not for clinical performance metrics.
  7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

    • Not found. Since performance studies with clinical outcomes are not described, there is no mention of ground truth types.
  8. The sample size for the training set

    • Not found. The document does not describe a machine learning model that would require a training set.
  9. How the ground truth for the training set was established

    • Not found. Not applicable.

In summary, the provided 510(k) Summary focuses on demonstrating substantial equivalence based on technical specifications, materials, manufacturing processes, and static physical property tests, rather than detailing clinical performance studies with specific acceptance criteria and outcome metrics that would be typical for an AI/ML powered device.

§ 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.