Search Results

The EndyMed Newa™ is an over-the-counter home use device intended for non-invasive treatment of mild to moderate facial wrinkles for adult women who have Fitzpatrick Skin Types I-IV.

Device Description

The Newa™ is an OTC, home use hand held device generating pulses of radiofrequency (RF) energy that are emitted into the skin. RF energy heats the tissue to improve the appearance of wrinkles and rhytides. It is a non-invasive, non-ablative device consisting of:

User interface
Programmable logic controller (PLC)
RF power module
Power supply
RF electrodes

AI/ML Overview

Acceptance Criteria and Device Performance Study for NEWATM

1. Table of Acceptance Criteria and Reported Device Performance

Special Control (Acceptance Criteria)	Device Performance/Study Findings
Non-clinical Performance Data: Demonstrate meets design specs and performance requirements (over-heating, power accuracy, radiofrequency, pulse cycle, waveform, pulse duration, and device characterization parameters).	Over-heating safety: Device tested to ensure it does not overheat skin. Built-in thermistor monitors skin temperature, stops RF energy delivery when surface temperature exceeds 42°C. Acceptance criterion: temperature on gel/electrodes not to rise above 42±0.5℃. Test result: temperature rose to 42.1℃, then RF energy delivery stopped. Power accuracy: Validated at 10 Watts on a 360Ω load. Acceptance criterion: 10 Watt ±20% (8-12 Watt). Test result: measured total power was 10W. Newa™ parameter validation: Tested for radio frequency, pulse cycle, wave form, and pulse duration. Accepted values: 1 MHz RF, 750ms pulse cycle, modified sine wave (square wave), 300ms pulse duration for "1" mode, and 450ms for "2" mode. Test results: at the declared values.
Label Comprehension and Self-Selection Performance Evaluation: Demonstrate intended OTC users can understand labeling and correctly choose device.	Study: 247 subjects. 195 (78.9%) stated they could use the device; 52 (21.1%) stated they could not. All 52 who said no made correct self-selection decision. Of 195 who said yes, 180 (92.3%) made a correct self-selection decision. Acceptance Criterion: 85% target for self-selection success rate. Result: 92.3% achieved (for those who said they could use it). Validation test (Kappa test) showed strong agreement (k=0.81) between subjects' self-selection and expert opinion.
Usability Performance Evaluation: Demonstrate layman can correctly use device based on directions.	Study: 62 participants. Tasks: 1. Preparing self for treatment (3 tasks): 100% (62/62) completed correctly. 2. Preparing device for treatment (3 tasks): 100% (62/62) completed correctly. 3. Treatment performance (8 tasks): 100% (62/62) completed correctly. Result: All tasks performed correctly by 100% of subjects.
Clinical Performance Evaluation: Demonstrate device performs as intended for aesthetic results.	Study: 69 participants (62 completers). Effectiveness Criterion: At least 75% of patients show a success (≥1 score reduction on Fitzpatrick Wrinkle Severity Scale agreed by ≥2 of 3 dermatologists). Result (at 4-week post-treatment): * Reviewer #1: 91.93% (57/62) * Reviewer #2: 91.93% (57/62) * Reviewer #3: 90.32% (56/62) * ≥2 agree: 95.16% (59/62) Result (at 3-month follow-up): * Reviewer #1: 91.93% (57/62) * Reviewer #2: 96.77% (60/62) * Reviewer #3: 98.39% (61/62) * ≥2 agree: 100% (62/62) Conclusion: Study success criterion for treatment effectiveness was met.
Biocompatibility: Patient-contacting components demonstrated to be biocompatible.	Study: Electrodes and shell (b(4)) are same as Newa™ prescription device (K130793). Tested according to ISO 10993-1 and USP Class VI tests. Result: Met requirements for up to 30 days contact with human tissue.
Instructions for Cleaning: Cleaning instructions validated.	Study: Cleaning validation protocol and report provided. Result: Cleaning instructions are adequate. Device is non-sterile and reusable, for single user.
Electromagnetic Compatibility (EMC) and Electrical Safety: Performance data provided.	Study: Tested against IEC 60601-1:2005/EN 60601-1:2006, IEC 60601-1-2:2007, IEC 60601-1-11:2010. Result: Device passed all relevant testing portions, demonstrating electrical safety for home use.
Software Verification, Validation & Hazard Analysis: Performed per guidelines.	Study: Software is firmware on micro-controller, same as cleared prescription device (K130793). Considered moderate LOC. All elements for moderate LOC devices provided per FDA guidance. V&V testing conducted for system initialization, power button, power down, LEDs, vibration, temperature detection. Result: Satisfactory results. Software development procedures provide assurance of intended performance; all software risks adequately mitigated.
Labeling: Include warnings, precautions, contraindications, and clinical summary.	Content: User Manual, Quick Reference Guide, Box Labeling. Includes: When to use (indication), What is Newa, Who can benefit, Using Newa (regimen), Who cannot use (contraindications), What to do to avoid harm (warnings, precautions), Manufacturer details. <brImage (Figure 12): Skin types I-IV are shown as suitable, V-VI marked with an X as unsuitable. Clinical Summary: A summary of effectiveness and adverse events from the clinical study is specified to be included, along with other required statements like those regarding safety/effectiveness for non-indicated uses.

Since this is a device for aesthetic use and not a diagnostic AI, many of the typical AI/ML study components (like training set details, MRMC studies, standalone performance with explicit metrics for algorithm output) are not directly applicable in the same way. The studies focus on safety, usability, and clinical effectiveness as a treatment device.

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

Clinical Study (Effectiveness & Safety):
- Enrollment: 69 participants (adult women, average age 54.4 ± 8.1 years, range 37-72; Fitzpatrick Skin Types I-IV).
- Completers: 62 participants.
- Provenance: Prospective, single-center study. Country of origin is not explicitly stated but implies the same location as the manufacturer or clinical trial site.
Label Comprehension & Self-Selection Study:
- Sample Size: 247 subjects.
- Provenance: Not explicitly stated but implies a general population capable of reading English, recruited for the study.
Usability Study:
- Sample Size: 62 subjects (these were part of the clinical study participants).
- Provenance: Part of the prospective clinical study.

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

Clinical Study (Effectiveness):
- Number of Experts: Three independent board-certified dermatologists.
- Qualifications: "Board-certified dermatologists." Specific years of experience are not mentioned.
Label Comprehension & Self-Selection Study:
- Medical Expert for Validation: An interviewer (trained in assessing wrinkle severity) made an initial assessment. This was then provided to a "blinded outside expert" for final determination of correct self-selection.
- Qualifications: The interviewer was "trained in assessing wrinkle severity." The "blinded outside expert" qualifications are not further detailed beyond being an "expert."

4. Adjudication Method for the Test Set

Clinical Study (Effectiveness):
- A patient was considered a "success" if at least 2 out of the 3 independent dermatologists agreed that the patient achieved at least one degree of wrinkle score reduction (per Fitzpatrick Wrinkle Severity Scale) when comparing baseline to 4-week follow-up. This is a 2+1 adjudication method.
Label Comprehension & Self-Selection Study:
- The subject's decision and reasons, along with the interviewer's assessment of wrinkle severity, were provided to a "blinded outside expert" for a final determination of whether the subject had correctly self-selected. This implies a single expert adjudicating the correctness of the subject's self-selection, informed by other inputs.

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 a treatment device, not a diagnostic AI. The studies performed were to demonstrate the device's effect on wrinkles, not to enhance human reader performance in diagnosis. The "readers" (dermatologists) in the clinical study evaluated before-and-after photographs, but their role was to assess treatment outcomes, not to interpret an AI's output.

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

Not Applicable. This is a physical device intended for direct human use for treatment, not a standalone AI algorithm. The device itself performs actions (RF energy delivery) rather than providing diagnostic outputs that would be typically associated with a standalone AI algorithm's performance evaluation.

7. The Type of Ground Truth Used

Clinical Study (Effectiveness): Expert Consensus. The ground truth for wrinkle reduction was established by the consensus of at least 2 out of 3 independent board-certified dermatologists, who assessed high-resolution photographs using the Fitzpatrick Wrinkle Severity Scale.
Safety Adjudication: Investigator observation and patient diaries for adverse events.
Self-Selection/Usability Studies: Expert opinion (interviewer + blinded outside expert) on the correctness of user actions and self-selection decisions.

8. The Sample Size for the Training Set

Not Applicable (for the device's primary function). The NEWATM device is an electrosurgical device, not a machine learning algorithm in need of a "training set" in the conventional AI/ML sense for its core functionality. Its software controls basic operational and safety functions, which are validated through traditional software V&V processes and bench testing, not through a large-scale data-driven training set.

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

Not Applicable. As noted above, a "training set" for an AI/ML algorithm is not described as being part of the device's development or validation for its primary function. Software validation relies on defined specifications and formal verification and validation protocols rather than a data-driven training approach.

Ask a Question

Ask a specific question about this device

K Number

K130793

Device Name

NEWA SKIN THERAPY SYSTEM

Manufacturer

ENDYMION MEDICAL LTD

Date Cleared

2013-08-16

(147 days)

Product Code

GEI

Regulation Number

878.4400

Type

Traditional

Panel

General & Plastic Surgery

Reference & Predicate Devices

K083461,K090525

Predicate For

DEN150005

Intended Use

The EndyMed Newa is a prescription home use device intended for non-invasive treatment of mild to moderate facial wrinkles and rhytides

Device Description

The Newa™ is a noninvasive, non-ablative, prescription home use hand held device consisting of:

User interface .
Programmable Logic controller (PLC) ●
RF power module ●
Power Supply .
RF Electrodes ●
The interface allows the selection of heating level by using the Power Level Switch as follows:
"0" mode = the device is "OFF". .
. "1" mode = low heating level.
. "2" mode = high heating level.
The PLC is a specially configured computer that provides the operational and safety function of the system.
The RF power module provides RF energy to the active tip, producing a sinusoidal signal at a 1MHz frequency.
Based on 3DEEP® technology, the Newa™ is comprised of 3 pairs of bipolar RF electrodes. The RF is emitted into the skin creating enough thermal effect to induce collagen remodeling with no ablative thermal damage in the epidermis, dermis or hypodermis.

AI/ML Overview

Acceptance Criteria and Device Performance for EndyMed Newa™

The EndyMed Newa™ device is intended for non-invasive treatment of mild to moderate facial wrinkles and rhytides as a prescription home-use device.

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria	Reported Device Performance
Decrease of at least 1 in the Fitzpatrick Wrinkle Severity Score at 3 months post the last treatment, as agreed upon by 2 of 3 blinded evaluators.	85% of subjects who completed the 3-month follow-up met this success criterion.

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

Sample Size: 69 subjects were enrolled in the study. 62 of these subjects completed the required follow-up at 3 months after the last treatment.
Data Provenance: The document does not explicitly state the country of origin of the data or whether the study was retrospective or prospective. However, the nature of the study, involving subjects performing task scenarios and follow-up, suggests it was a prospective clinical study.

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

Number of Experts: 3 blinded evaluators.
Qualifications of Experts: The document does not specify the qualifications of these evaluators (e.g., radiologist with X years of experience). It only states they were "blinded evaluators."

4. Adjudication Method for the Test Set

Adjudication Method: A 2 out of 3 consensus method was used. Specifically, "based on 2 of the 3 blinded evaluators agreeing that they observed a decrease of at least 1 in the Fitzpatrick Wrinkle Severity Score."

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not done. This study evaluated the standalone performance of the device when used by subjects in a home-use simulation.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, this study essentially represents a standalone performance evaluation of the device's effectiveness when operated by users in a simulated home-use environment. The success criteria were based on objective assessments by expert evaluators using the Fitzpatrick Wrinkle Severity Score, rather than the subjects' self-reported satisfaction or an AI's autonomous assessment. The study focused on the device's ability to induce a measurable clinical outcome.

7. The Type of Ground Truth Used

The ground truth used was expert consensus on clinical assessment. Specifically, it was the agreement of 2 out of 3 blinded evaluators on a change in the Fitzpatrick Wrinkle Severity Score, which is a standardized clinical grading scale.

8. The Sample Size for the Training Set

The document does not provide information regarding a "training set" or its sample size. This study appears to be a clinical performance study for device clearance, not a study involving the training of an AI algorithm. The Newa™ device itself is a radiofrequency energy device, not an AI-powered diagnostic or therapeutic algorithm.

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

As the device is not an AI algorithm and no "training set" is mentioned, this information is not applicable to the provided document.

Ask a Question

Ask a specific question about this device

Page 1 of 1