K Number
K212017
Device Name
Thermeo System
Date Cleared
2022-04-08

(284 days)

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

Thermeo powder / Thermeo liquid is a heat cured, moldable, acrylic compound system for use in the fabrication of dental appliances such as mouthguards, bruxism and TMJ splint appliances, and bite splints.

The Thermeo blank is a disc intended for the fabrication of dental appliances such as mouthguards, buxism and TMJ splint appliances, and bite splints using CAD/CAM milling machines.

Device Description

The Thermeo powder/Thermeo liquid is a two-compound mixable device, containing a powder component and a liquid component. The device is heat cured for the fabrication of dental appliances.

The Thermeo blanks are pre-made by pro3dure using the two-part mixable device. The Thermeo blank is intended to be used in conjunction with CAD/CAM milling technology systems.

AI/ML Overview

The provided document is an FDA 510(k) Premarket Notification for a dental device, the "Thermeo System." It is a regulatory submission for establishing substantial equivalence to existing devices, not a study reporting on the performance of an AI/ML diagnostic system.

The request asks for information typically found in clinical validation studies for AI/ML-driven medical devices, such as:

  1. Acceptance criteria and device performance table.
  2. Sample size and data provenance for test sets.
  3. Number and qualifications of experts for ground truth.
  4. Adjudication method.
  5. MRMC study details and effect size.
  6. Standalone algorithm performance.
  7. Type of ground truth used.
  8. Training set sample size.
  9. Ground truth establishment for training set.

This document, however, describes a physical dental material system (Thermeo powder/liquid and Thermeo blank for dental appliances) and its substantial equivalence to predicate devices based on material properties, manufacturing processes, and safety (biocompatibility, shelf life), not on the diagnostic performance of an algorithm.

Therefore, most of the information requested, which pertains to the validation of an AI/ML diagnostic algorithm, cannot be extracted from this document, as it is not relevant to the Thermeo System's 510(k) submission.

Here's what can be gathered, addressing the relevant parts of your request within the context of this device:

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

The document indicates that performance testing was conducted according to ISO 20795-2 for the "Thermeo System." This standard covers dental base polymers. The specific mechanical properties measured were:

  • Flexural modulus
  • Flexural Strength
  • Tensile Strength
  • Elongation at Break

However, the document does not provide a table with specific acceptance criteria values (e.g., minimum flexural strength) nor the numerical results (reported device performance) for these tests. It only states that testing was "performed in accordance with" the standard. For a 510(k), demonstrating compliance with a recognized standard often suffices without explicitly listing all raw data in the summary.

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

  • Sample Size: Not specified in the provided text.
  • Data Provenance: The device manufacturer, Pro3dure Medical GmbH, is located in Germany. Testing would likely be conducted at their facilities or a contracted lab. The document does not specify if the testing was retrospective or prospective in terms of data collection for this type of material performance test.

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

  • Not Applicable. This is a physical material compliance test, not a diagnostic algorithm requiring expert ground truth for images. Performance is measured using standardized mechanical and chemical testing methods.

4. Adjudication method for the test set:

  • Not Applicable. See point 3.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

  • No. This is not an AI/ML diagnostic device, so an MRMC study is not relevant.

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

  • Not Applicable. This is a physical material, not an algorithm.

7. The type of ground truth used:

  • For the performance testing (flexural modulus, strength, etc.), the "ground truth" is established by physical measurement results obtained through standardized testing protocols (ISO 20795-2).
  • For biocompatibility, the "ground truth" is established by biocompatibility testing in accordance with ISO 10993-1, which assesses biological responses.
  • For shelf-life, the "ground truth" is established by accelerated aging and real-time stability testing per ASTM F1980-16.

8. The sample size for the training set:

  • Not Applicable. There is no "training set" as this is not a machine learning device.

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

  • Not Applicable. See point 8.

In summary, the provided document is a regulatory submission for a physical dental product, and the requested performance evaluation criteria are primarily applicable to AI/ML diagnostic software, which is not the subject of this 510(k).

N/A