Search Results

Red light: Treatment of full- face wrinkles.
Blue light (only suitable model M226 and MN1 LED Facial Mask): Treatment of mild to moderate inflammatory acne.
Infrared light: Provide topical heating for the purpose of elevating tissue temperature; arthritis and muscle spasm; relieving stiffness; promoting the relaxation of muscle tissue; and to temporarily increase local blood circulation.
Mixed light: Treatment of full face wrinkles.

The subject device LED Therapy Mask is a home use wearable LED phototherapy device whose purpose is to produce an even and narrowband of light for the treatment of cosmetic indications including facial wrinkles and acnes.
The subject device consists of a mask body unit that contains light emitting diodes (LEDs), a controller, straps and Type-C charging cable. And the device is powered by built-in rechargeable lithium battery on the controller.

It appears there's a misunderstanding of the provided FDA 510(k) clearance letter. The document is for an LED Therapy Mask, which is a physical device used for cosmetic and therapeutic purposes, not an AI/software-based medical device.

Therefore, the concepts of acceptance criteria, test sets, ground truth establishment by experts, MRMC studies, standalone algorithm performance, and training sets are not applicable to this type of device submission. These concepts are relevant for AI/ML-driven medical devices that output diagnostic or prognostic information, where the performance of an algorithm needs to be validated against clinical ground truth.

The provided FDA letter and 510(k) summary describe:

• Device Name: LED Therapy Mask (MN1, M226)
• Regulation Number: 21 CFR 878.4810 (Laser Surgical Instrument For Use In General And Plastic Surgery And In Dermatology)
• Regulatory Class: Class II
• Product Code: OHS, ILY, OLP
• Indications for Use: Treatment of full-face wrinkles (Red/Mixed light), mild to moderate inflammatory acne (Blue light), and providing topical heating for various muscular/joint relief (Infrared light).
• Performance Data: The data provided relates to the physical and electrical safety, biocompatibility, eye safety, software verification & validation (for the device's control software, not AI), and usability of the LED mask itself.

Since the request asks for information about acceptance criteria and studies proving the device meets acceptance criteria, and the provided device is an LED mask (not an AI algorithm), I will interpret "acceptance criteria" based on the documentation provided for this specific device.

Here's an analysis based on the provided document, clarifying that AI/ML specific criteria are not applicable:

Device: LED Therapy Mask (MN1, M226)

Nature of the Device: Physical LED light therapy device for cosmetic and therapeutic applications, primarily using light emission for treatment. It is not an AI/ML algorithm-based diagnostic or prognostic device.

Therefore, the concepts of a "test set" for algorithm performance, "ground truth" for clinical accuracy, "experts" for labeling data, "adjudication," "MRMC studies," "standalone algorithm performance," and "training sets" in the context of AI/ML are NOT APPLICABLE to this device.

The "acceptance criteria" for this device relate to its safety, electrical performance, biocompatibility, and functional integrity as a light-emitting medical device.

Table of Acceptance Criteria and Reported Device Performance (Based on provided document):

Responses to Specific Questions (with clarifications on applicability):

1. A table of acceptance criteria and the reported device performance: See table above. These are the engineering, safety, and performance criteria relevant to a hardware medical device like an LED mask.

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

   • Sample Size: Not applicable in the context of a "test set" for an AI/ML algorithm. The "tests" here refer to standard engineering and biological safety tests on the device's components and system. These typically involve a limited number of device units or material samples. The document does not specify the number of units/samples tested for each battery of tests (e.g., biocompatibility samples, electrical safety units).
   • Data Provenance: The tests are standard laboratory/bench testing performed on the physical device and its materials. The document does not specify the country of origin for the test data itself, beyond the manufacturer being based in Shenzhen, China. This is not retrospective or prospective in the clinical AI sense; it's product validation testing.

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

   • Not Applicable. "Ground truth" in the AI/ML sense (e.g., radiologist labels for images) does not apply here. The "ground truth" for this device's performance is established by objective physical measurements (e.g., light output, electrical parameters) and standardized biological test results performed by qualified laboratories, often certified to conduct such tests (e.g., ISO-certified labs).

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

   • Not Applicable. Adjudication methods like 2+1 or 3+1 are used for establishing consensus "ground truth" from multiple human experts for AI model evaluation. This device is not an AI model requiring such clinical ground truth.

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 Applicable. MRMC studies are specific to evaluating diagnostic AI systems where human readers interpret medical images or data. This device is a direct treatment device, not an interpretative AI.

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

   • Not Applicable. This is not an AI algorithm. Its "standalone performance" refers to its ability to emit light at specified wavelengths and intensities, which is part of the electrical and performance testing. The "software verification and validation" mentioned is for the device's control software, ensuring it functions correctly, not for an AI algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

   • Not Applicable in the AI/ML context. For a physical device, "ground truth" typically refers to:
     • Standardized Test Methods: Biocompatibility (ISO 10993 series), Electrical Safety (IEC 60601 series), Photobiological Safety (IEC 62471). These international standards define the acceptable performance and safety limits, which serve as the "ground truth" for compliance.
     • Physical Measurements: Wavelengths and intensities of light emitted are physically measured and compared against specifications and predicate devices.

8. The sample size for the training set:

   • Not Applicable. This is not an AI/ML device that requires a "training set."

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

   • Not Applicable. No training set is used for this device.

Ask a specific question about this device

LED MASK PLATINUM MD is an over the counter device that is indicated for the treatment of full face wrinkles.

This product irradiates the skin with red light in the wavelength range of 630 to 690 nm and infrared light in the wavelength range of 820 to 880 nm. Treatment of wrinkles all over the face. This product is designed as a portable personal medical device with a built-in battery, not a wired power supply. It is a mask-type product that is worn on the face. The operating mode of the product can be easily changed by hand. After connecting the charging adapter to the cradle, attach the main unit to the cradle to wirelessly charge the main unit with only the cradle. In addition, eye shield (for eye protection, opening/closing covers, vacuum cleaner towels, power cables, etc. are provided for convenient service use.

This document is a 510(k) summary for the LED MASK PLATINUM MD, a device indicated for the treatment of full face wrinkles. The submission aims to demonstrate substantial equivalence to legally marketed predicate devices.

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied by the comparison to predicate devices, particularly K180856, and by conforming to established safety standards for LED-based devices. The "reported device performance" section focuses on technical specifications and safety compliance rather than direct clinical efficacy metrics.

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

The document does not describe a clinical study with a "test set" in the traditional sense of evaluating device efficacy on patients. The performance data presented relates to non-clinical tests (measurement of wavelength, output power, total irradiance, and safety compliance). Therefore, no sample size for a test set or data provenance from patient data is applicable or reported for this type of submission.

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

Not applicable. As no clinical "test set" data is presented for efficacy, there is no mention of experts establishing ground truth for such a set. The expertise involved would be in the engineering and safety testing domains, not clinical adjudication.

4. Adjudication Method for the Test Set

Not applicable. No clinical test set requiring adjudication 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

Not applicable. This device is an LED mask for wrinkle treatment, not an AI-assisted diagnostic tool. An MRMC study is not relevant to this device's regulatory pathway.

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

Not applicable. This is not an algorithmic device. The device's performance is standalone in the sense that it directly emits light for treatment, not that it's an algorithm.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is established through physical measurements and compliance with recognized consensus standards.

• For technical specifications (wavelength, power, energy dose): The ground truth is the direct measurement of these physical properties using calibrated equipment.
• For safety: The ground truth is established by demonstrating compliance with the referenced IEC and ISO standards (e.g., IEC 60601-1 for basic safety, IEC 62471 for photobiological safety, ISO 14971 for risk management).
• For substantial equivalence: The ground truth is the regulatory determination that the device's technical characteristics, intended use, and performance are sufficiently similar to a legally marketed predicate device to be considered equally safe and effective.

8. The Sample Size for the Training Set

Not applicable. This device does not involve a "training set" as it is not an AI/machine learning device.

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

Not applicable. No training set is described.

Ask a specific question about this device