K Number
K203302
Device Name
GentleWave X
Manufacturer
Date Cleared
2021-02-05

(88 days)

Product Code
Regulation Number
872.4850
Panel
Dental
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Sonendo Gentle Wave X System is intended to prepare, clean, and irrigate teeth indicated for root canal therapy. When used with the Sonendo GentleWave Molar Procedure Instrument or Molar CrossFire™ Procedure Instrument, the System is indicated for 1st and 2nd molar teeth. When used with the Sonendo Gentle Wave Anterior/Premolar Procedure Instrument, the System is indicated for anterior and premolar teeth. When used with the Sonendo Gentle Wave Premolar CrossFire™ Procedure Instrument, the system is indicated for premolar teeth.

Device Description

The Sonendo GentleWave X System is a medical device intended to prepare, clean and irrigate root canals. The Sonendo GentleWave X System is comprised of a Console, and disposable single-use Handpieces and accessories. The Handpiece is offered for molar, anterior and premolar treatments. A Molar Handpiece (original or CrossFire™ model) is intended to be used on 1st and 2nd molar teeth. An Anterior/Premolar (APM) Handpiece is intended to be used on anterior and pre-molar teeth and CrossFire™ Premolar Handpiece is intended for pre-molar teeth only. The Sonendo GentleWave X System delivers a stream of treatment fluids into the pulp chamber of the tooth. The treatment fluids delivered to the tooth are 3% Sodium Hypochlorite (NaOCl) solution and an 8% Ethylenediaminetetraacetic acid (EDTA) utilized in traditional endodontic treatments.

AI/ML Overview

Based on the provided text, the device in question is the Sonendo GentleWave X System, an ultrasonic scaler used for root canal therapy.

Here's an analysis of the acceptance criteria and the study proving the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in numerical targets (e.g., "accuracy > 90%"). Instead, it focuses on demonstrating substantial equivalence to a predicate device (Sonendo GentleWave System cleared under K160905). The acceptance is therefore based on showing that the new device performs as intended and equivalently to the predicate device through various non-clinical performance tests.

Here's a table summarizing the performance tests conducted (which imply the acceptance criteria are to pass these tests) and the reported outcome:

Test CategorySpecific TestImplied Acceptance Criteria (Pass/Fail)Reported Device Performance
Performance VerificationThermal testPass (demonstrates proper thermal operation)"performed and passed"
Cavitation testPass (demonstrates effective cavitation)"performed and passed"
Hydroacoustic testPass (demonstrates effective hydroacoustic action)"performed and passed"
Cleaning testPass (demonstrates effective cleaning)"performed and passed"
Apical pressure testPass (demonstrates acceptable apical pressure)"performed and passed"
Apical extrusion testPass (demonstrates acceptable apical extrusion)"performed and passed"
Human FactorsHuman Factor Evaluation (per FDA Guidance)Pass (demonstrates safe and effective usability)"performed and passed"
Software ValidationSoftware Validation (moderate level of concern)Pass (demonstrates software functions as intended)"performed and passed"
BiocompatibilityCytotoxicity, Sensitization, IrritationPass (demonstrates biological safety)"performed and passed"
Material Mediated PyrogenicityPass (demonstrates non-pyrogenic materials)"performed and passed"
Acute Systemic ToxicityPass (demonstrates no acute systemic toxicity)"performed and passed"
Safety & EMCElectromagnetic Compliance & Electrical SafetyPass (demonstrates compliance with safety standards)"performed and passed"

2. Sample Size Used for the Test Set and Data Provenance

  • Sample Size for Test Set: The document does not specify exact sample sizes for each of the non-clinical performance tests (e.g., how many units were tested for the thermal test, or how many simulated canals were cleaned for the cleaning test). It simply states that "All necessary performance testing has been conducted."
  • Data Provenance: The data is all non-clinical bench testing. The country of origin is not explicitly stated for the testing, but the company (Sonendo, Inc.) is located in California, USA. The testing is prospective in the sense that it was conducted specifically to support this premarket notification.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts

  • This is not applicable (N/A) because the study relies on non-clinical bench testing and engineering verification, not human expert assessment of medical images or patient outcomes. The "ground truth" for these engineering tests are established engineering specifications and measurement standards.

4. Adjudication Method for the Test Set

  • N/A. Since the testing is automated or standardized bench testing with objective measurements (e.g., temperature, pressure, electrical parameters), there is no need for human adjudication of results in the way it would be applied to clinical image readings. The results are typically compared against pre-defined engineering limits or specifications.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and effect size of human readers improvement with AI vs. without AI assistance.

  • No. The document explicitly states: "No clinical data is submitted in support of this Premarket Notification." This means no MRMC study was conducted, and therefore no effect size for human reader improvement with AI assistance is reported. The device is not an AI-assisted diagnostic tool; it is a physical medical device for root canal therapy.

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

  • N/A (for "algorithm only"). The device's performance is not primarily based on an "algorithm only" in the sense of a standalone AI diagnostic tool. It's a system with hardware and software. The "performance verification" tests assess the overall device's functional performance standalone, in a bench setting, against its specifications. The software validation is for the embedded software controlling the device, not a standalone AI diagnostic algorithm.

7. The Type of Ground Truth Used

  • The ground truth for this device's acceptance is based on engineering specifications, recognized consensus standards (e.g., ISO, IEC), and established physical principles. For example, the "cleaning test" would likely have a pre-defined objective measure of cleanliness that constitutes "ground truth" for successful cleaning. Similarly, pressure and temperature measurements have objective "ground truth" values defined by physics and instrumentation. There is no biological or clinical ground truth (like pathology or outcomes data) used in this submission.

8. The Sample Size for the Training Set

  • N/A. As no clinical data or AI/machine learning model dependent on a training dataset was used or submitted for this premarket notification, there is no "training set" in the context of AI model development.

9. How the Ground Truth for the Training Set Was Established

  • N/A. (See point 8).

§ 872.4850 Ultrasonic scaler.

(a)
Identification. An ultrasonic scaler is a device intended for use during dental cleaning and periodontal (gum) therapy to remove calculus deposits from teeth by application of an ultrasonic vibrating scaler tip to the teeth.(b)
Classification. Class II.