(28 days)
BRIUS Planner is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, treatment simulation and virtual appliance design options (Patient-Specific Nitinol Wires, Sequential Aligners, Export of Models, Indirect Bonding Transfer Media) based on 3D models of the patient's dentition before the start of an orthodontic treatment. It can also be applied during the treatment to inspect and analyze the progress of the treatment. It can be used at the treatment to evaluate if the outcome is consistent with the planned/desired treatment objectives.
The use of the BRIUS Planner requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.
The BRIUS Planner Software is an orthodontic appliance design and treatment simulation software. This software is used as a manufacturing software for orthodontic appliances. It is also used by professional technicians or physicians to design solutions for patients. Digital scans (3D) of a patient denture can be loaded into the software and a technician or physician can then create treatment plans for each individual patient and their needs. After approval by the patient's physician, the system can be used to fabricate dental appliances using standard stereolithographic (STL) for the design of custom shape-set nitinol appliances or clear aligners.
The provided document is a 510(k) summary for the BRIUS Planner Software, asserting its substantial equivalence to a predicate device (BRIUS Software Suite K191720). This type of regulatory submission focuses on demonstrating equivalence rather than proving novel clinical effectiveness through extensive studies with specific acceptance criteria and detailed performance metrics.
Therefore, the document does not contain the detailed information typically found in a clinical study report that proves a device meets specific acceptance criteria. It primarily relies on demonstrating functional similarity and software validation.
Below is an analysis of the provided text in relation to your request, highlighting what information is available and what is not.
Request Analysis and Available Information:
The document clearly states: "Utilizing FDA Guidance document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (issued May 11, 2015), BRIUS Planner Software underwent appropriate integration, verification, and validation testing."
This indicates software verification and validation (V&V) was performed, which is a form of performance testing for software. However, the document does not provide specific acceptance criteria or detailed results of these V&V activities beyond a general statement of completion. It does not present a clinical study comparing the device's output to ground truth established by experts, nor does it conduct a multi-reader, multi-case study. The focus is on demonstrating substantial equivalence to an existing cleared device.
Given this context, I cannot directly provide a table of performance against acceptance criteria in the clinical sense you've described for an AI/CADe device. The "performance" being demonstrated here is primarily the software's functional similarity and reliability in its intended use, as opposed to a diagnostic accuracy or efficacy metric.
Here's a breakdown of what can and cannot be extracted from the provided text according to your numbered questions:
-
A table of acceptance criteria and the reported device performance:
- Not Available directly. The document provides "Functional Specification Comparison" (Table 1) and "Feature Comparison Table" (Table 2) comparing the new device to its predicate. These tables describe functions and features, not quantitative performance metrics against specific acceptance criteria for outputs (e.g., accuracy of a measurement, classification performance). The acceptance criteria for the software V&V are not explicitly detailed, nor are the specific results of those tests beyond the general statement that testing was "appropriate."
-
Sample sizes used for the test set and the data provenance:
- Not Available. The document does not mention sample sizes for any test sets (e.g., patient cases or dental models). It also does not specify the provenance of data used for any testing (e.g., country of origin, retrospective/prospective). This information is typically detailed in a separate test report, not usually summarized in a 510(k) letter or summary unless a specific clinical performance study was conducted that required it.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not Applicable/Available. Since no clinical study proving diagnostic/measurement accuracy against expert-established ground truth is described, there's no mention of experts establishing ground truth for a test set. The software is a "front-end device" for treatment planning, not a diagnostic AI. The document does state, "The use of the BRIUS Planner requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software," indicating that the end-user (a trained orthodontist) is responsible for the clinical decisions.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not Applicable/Available. No such adjudication method is mentioned as no clinical performance study involving expert reads is described.
-
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 described. The software is for planning and design, not an AI assisting human reader interpretation in the diagnostic sense.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not explicitly detailed in terms of quantitative performance. The software is inherently a "human-in-the-loop" tool, as it requires "the user to have the necessary training and domain knowledge in the practice of orthodontics." While software V&V would test its internal functions independently, specific "standalone performance" metrics (like area under the curve for a diagnostic AI) are not presented because the device's function is not a standalone diagnostic output.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not Applicable/Available. No ground truth in the context of clinical accuracy is mentioned, as the submission focuses on functional equivalence and software V&V.
-
The sample size for the training set:
- Not Applicable/Available. The document doesn't mention a training set, which would typically be relevant for machine learning algorithms. The device's description (treatment simulation, virtual appliance design) suggests it's a rule-based or model-based software, not necessarily a deep learning AI requiring large training sets in the typical sense.
-
How the ground truth for the training set was established:
- Not Applicable/Available. No training set or associated ground truth establishment process is mentioned.
In summary, the provided FDA 510(k) summary focuses on demonstrating "substantial equivalence" of the BRIUS Planner Software to a legally marketed predicate device (BRIUS Software Suite K191720) based on similar indications for use, technological features, and confirmation of software validation (V&V). It does not present a performance study with detailed acceptance criteria and reported results in the manner one would expect for a new AI/CADe device proving its diagnostic or analytical accuracy via clinical data.
§ 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.