Search Results

Luna 4 plus has multiple functions combined in a single device, like RED+NIR LED Treatment for wrinkle reduction. The device emits visible red/IR light (Red: 630nm +/- 10nm.) for elevating tissue temperature in improving appearance of facial wrinkles. Microcurrent to target facial stimulation. Two microcurrent pins at the back for a targeted toning massage, emitting microcurrent electrical therapy to deliver skin stimulation where maximum power delivered to the load is controlled and limited by integral software. Luna 4 plus is a single device powered by a rechargeable battery. A controller is integrated on the back to control the device, such as turn on/off the device, mode buttons. Rechargeable Li-battery contained in the controller with a USB cable accessible to target it. To user should use the controller to operate.

AI/ML Overview

Here's an analysis of the acceptance criteria and supporting study for the Luna 4 plus device, based on the provided FDA 510(k) summary:

The document provided primarily focuses on establishing "substantial equivalence" of the Luna 4 plus to existing predicate devices, rather than defining explicit acceptance criteria and then presenting a study to prove meeting those criteria in the traditional sense of a clinical trial for a novel device. The "acceptance criteria" here are implicitly related to demonstrating that the new device is as safe and effective as the predicate devices through conformance to recognized standards and comparative testing.

The "study" that proves the device meets "acceptance criteria" (i.e., is substantially equivalent to predicates) is a combination of:

Non-clinical testing: Electrical safety, EMC, and biocompatibility, as per applicable standards.
Lab bench performance testing: Characterization of electrical stimulation output, including Anti-Shock System performance and overload conditions.
Usability studies: To demonstrate substantial equivalence given new indications.

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

Since explicit "acceptance criteria" in the format of specific numerical thresholds tied to a single study result are not provided, I will construct a table reflecting the key equivalency demonstrations and comparisons made against the predicate devices. The "reported device performance" will be the "Subject Device" values from the Substantial Equivalence Comparison Table, along with notes on safety and efficacy from the "Conclusion" and "Comparison in details" sections.

Feature Area	Implicit Acceptance Criterion (Demonstrate Substantial Equivalence to Predicate)	Reported Device Performance (Luna 4 plus)
Regulatory Information
Regulation Number	Comparable regulatory classification for similar intended uses.	878.4810 (Laser surgical instrument), 882.5890 (Transcutaneous Electrical Nerve Stimulator). Different from some predicates but within acceptable classifications for its functions.
Intended Use	Indications for facial stimulation and periorbital wrinkle treatment should be similar to predicates.	1. Red + IR light intended to treat periorbital wrinkles. 2. Microcurrent intended for facial stimulation. Similar to predicates.
Safety Mechanism	Possess safety mechanisms (e.g., thermal, electrical protection) equivalent to or better than predicates.	Thermal sensor and heat stabilizer (prevents overheating above 42-43°C). Anti-Shock system (monitors voltage on feedback resistor to ensure stable current). Different from some predicates but detailed to demonstrate safety.
Device Characteristics
Application Area	Face.	Face. Same as predicates.
Use Environment	Home Use, lay users.	Home Use, lay users. Same as predicates.
Power Source	Internal rechargeable battery.	Internal rechargeable Lithium battery. Same as predicates. Tested to IEC 62133-2.
Software/Firmware/Control	Presence of control software.	Yes. Same as predicates.
Patient Override Control	User control over device operation.	Yes. Same as predicates.
Microcurrent Function
Electrical Characteristics	Microcurrent characteristics (e.g., waveform, pulse width, output voltage/current, frequency) should be safe and effective, and differences adequately justified/tested.	Pulsed monophasic, alternating polarity, charge-balanced waveform; Modulated square shape; Pulse width 290 µs; Max RMS Output Voltage 0.28V @500Ω; Max RMS output Current 560μA @500Ω; Max Net Charge 0 µC (charge-balanced). Frequency Range 46Hz. Different from predicates but evaluated via lab bench performance testing to IEC 60601-2-10 to ensure safety and effectiveness, acknowledging lower output power density than one predicate.
LED/NIR Light Function
Optical Characteristics	LED wavelength and power density suitable for stated indications and comparable to predicates.	RED light: 633nm±10nm; Red+IR: 633±10nm / 850nm±10nm. Optical Power Density RED+IR: 63 mW/cm². Differences in wavelength and power density from predicates but supported by usability report and bench evaluation for safety and efficacy.
Compliance & Standards
Biocompatibility	Compliance with relevant ISO 10993 standards.	ISO 10993-5, ISO 10993-10, ISO 10993-23. Similar to predicates.
Electrical Safety	Compliance with relevant IEC 60601 standards.	IEC 60601-1, IEC 60601-1-6, IEC 60601-1-11, IEC 60601-2-10, IEC 60601-2-57. Similar to predicates. Performance testing of Anti-Shock System and under overload conditions also performed.
EMC	Compliance with IEC 60601-1-2.	IEC 60601-1-2. Same as predicates.
21 CFR 898	Compliance with 21 CFR 898 performance standards.	Yes. Same as predicates.

2. Sample size used for the test set and the data provenance

The document does not specify a distinct "test set" in terms of a clinical or image dataset. The testing primarily involved non-clinical lab-based evaluations:

Electrical safety, EMC, and biocompatibility: Tested against applicable standards (e.g., IEC 60601-1, IEC 60601-1-2, ISO 10993 series). This typically involves a single or small number of device units.
Lab bench performance testing: Characterization of electrical stimulation, Anti-Shock System, and overload conditions. This would also involve a small number of physical devices.
Usability studies: These are mentioned, but no specifics on sample size (number of users) or study design (e.g., prospective, retrospective, country of origin) are provided.

Therefore, there isn't a "sample size for the test set" in the context of an AI/algorithm performance study using patient data.

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

This information is not applicable/provided in the document as it does not describe a study involving expert-derived ground truth for a test set of patient data, which is typical for AI/algorithm performance evaluations. The evaluations performed are engineering-based and comparative.

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

This information is not applicable/provided as there is no described test set requiring expert adjudication for 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

There is no indication that a multi-reader multi-case (MRMC) comparative effectiveness study was done. The device (Luna 4 plus) is a physical device for topical aesthetic treatment and does not involve "human readers" interpreting medical cases or AI assistance in diagnostic tasks.

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

The device is a physical, user-operated aesthetic device. While it contains integrated software ("integral software" to control microcurrent and the "Anti-Shock system"), this is part of the device's functional control, not a standalone diagnostic or interpretative algorithm. Therefore, a "standalone algorithm-only performance study" as typically understood for AI/ML devices is not applicable/provided.

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

The concept of "ground truth" as typically used for AI/ML models is not directly applicable here. The "truth" for this device's evaluation is primarily based on:

Reference standards: Adherence to national and international engineering and safety standards (e.g., IEC 60601 series, ISO 10993 series).
Benchmarking against predicate devices: Demonstrating similar or improved safety and functionality compared to legally marketed devices.
Physical measurements: E.g., optical power density, electrical output characteristics.

For the usability studies mentioned, the "ground truth" would likely be user feedback or successful completion of tasks, but details are not provided.

8. The sample size for the training set

This information is not applicable/provided as the document does not describe the development of an AI/ML model that would require a "training set." The integral software is likely rule-based or control-loop driven rather than a machine learning algorithm.

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

This information is not applicable/provided for the reasons stated in point 8.

Ask a Question

Ask a specific question about this device

Page 1 of 1