Search Results

The sensiLift 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.

The sensiLift 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, microcontroller) embedded in PCBA ●
• RF power module
• Power Supply ●
• RF electrodes ●

The provided document describes the SensiLift device, an over-the-counter home use device intended for non-invasive treatment of mild to moderate facial wrinkles. The document outlines the studies conducted to demonstrate its safety and effectiveness for FDA 510(k) clearance.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria for the SensiLift device are inferred from the safety and effectiveness endpoints of the clinical study, as well as the successful completion of various non-clinical bench tests and human factors studies.

Study Details

The document primarily describes a single-arm, prospective, interventional clinical study for effectiveness and safety, along with several non-clinical studies.

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

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

   • Clinical Study (Effectiveness & Safety):

     • Enrollment: 40 female participants (ages 40-64).
     • Completed Study: 35 participants (total of 87 treatment areas) completed 8 treatments and the 3-month follow-up.
     • Provenance: Not explicitly stated, but presumable from the location of the submitting company (Israel) or where a clinical trial would be conducted. The study is described as "prospective" and "interventional."

   • Human Factors Validation Testing:

     • Labeling Comprehension/Self-Selection Study: 43 participants (2 men, 41 women), ages 18-65 (45 ± 13 years old).
     • Usability/User Interface Study: Not explicitly stated but implies a subset of the 43 participants or a similar number based on "14 out of 20" and "7 out of 20" comments. Assuming it's at least 20 participants for this part.
     • Provenance: Not specified, but likely conducted in a simulated environment.

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

   • Clinical Study (Effectiveness): 3 independent physicians (apart from the PI - Principal Investigator).
   • Qualifications: "3 board certified dermatologists or plastic surgeons."

4. Adjudication method for the test set:

   • Clinical Study (Effectiveness): Wrinkles appearance was assessed independently by the 3 physicians. There is no explicit mention of an adjudication process (e.g., 2+1 or 3+1 consensus). The percentages of improvement are reported for each reviewer separately (e.g., "89%, 95% and 95% of the study participants (as assessed by 3 reviewers, respectively)"). This implies independent assessment rather than a combined adjudicated score for each participant.

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:

   • No MRMC comparative effectiveness study involving AI assistance for human readers was conducted or described. This device is a direct-to-consumer physical device for wrinkle treatment, not an AI diagnostic tool.

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

   • This question is not applicable. The device is a physical electrosurgical aesthetic device, not an algorithm. Bench tests and a clinical trial evaluated the device's standalone performance in a human-in-the-loop setting (users operating the device).

7. The type of ground truth used:

   • Clinical Study (Effectiveness): Expert assessment using the Fitzpatrick Wrinkles Severity Scale. Improvement was defined as a decrease of at least one score on this scale. This is a clinical outcome observed by qualified experts.
   • Clinical Study (Safety): Observation of adverse events.
   • Human Factors Study: Direct observation of task completion and user responses to questions.

8. The sample size for the training set:

   • The document implies that the clinical study was conducted for final validation and performance assessment. There's no separate mention of a distinct "training set" for an algorithm, as this is a physical device submission. If the device's software had any machine learning components, details about a training set would typically be provided under software V&V. The software concern level is "moderate," indicating potential harm from errors, but it's not described as an AI/ML algorithm.

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

   • Not applicable, as a discrete training set for an AI/ML algorithm is not described. The clinical study acts as the primary validation of the device's performance against ground truth established by expert consensus (dermatologists/plastic surgeons) using a recognized severity scale.

Ask a specific question about this device

The sensiLight Mini is an over the counter device intended for the removal of unwanted hair. The sensiLight Mini is also intended for permanent reduction in hair regrowth, defined as a long-term, stable reduction in the number of hairs re-growing when measured at 6, 9, and 12 months after the completion of treatment regimen.

The sensiLight Mini device is a pulsed light hair removal device. Light-based hair removal is based on the theory of selective photothermolysis in which optical energy is used to disable hair growth. The sensiLight Mini device is composed of a hand held applicator and an external power supply. The spot size (treatment area) in the sensiLight Mini device is 3 cm2.

The device contains a lamp, a skin proximity sensor and a skin pigmentation sensor to detect appropriate skin tones. If the sensiLight Mini is not properly applied (in full contact with the skin) or user skin tone is too dark/tanned, the sensiLight Mini will not trigger a pulse.

This document is a 510(k) premarket notification for the sensiLight Mini, which is a pulsed light hair removal device. The device described in this submission (K161089) is stated to be identical to a previously cleared device (K140527). Therefore, no new performance data, non-clinical data, or clinical data are reported in this specific submission. The substantiation relies on the data from the predicate devices.

However, based on the information provided, we can infer some details about the clinical performance for the original device that K161089 references (K140527), particularly regarding its "permanent reduction in hair regrowth" claim.

Here's an attempt to answer your questions based on the available information and reasonable inferences:

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

Since this submission explicitly states "No new clinical performance data is reported in this submission" and "The sensiLight Mini device is identical in all details to the sensiLight Mini device cleared under K140527," the acceptance criteria and performance would be associated with the original K140527 submission. The document defines "permanent reduction in hair regrowth" as:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not provided in the K161089 document as it refers back to a previous submission (K140527). To obtain these details, one would need to consult the K140527 submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided in the K161089 document. Clinical studies for hair removal devices often involve trained technicians or physicians for evaluation, but specifics are missing here.

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

This information is not provided in the K161089 document.

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

Hair removal devices like the sensiLight Mini are typically consumer-use devices and do not involve "readers" in the context of diagnostic imaging. Therefore, an MRMC study and AI assistance as described are not applicable to this type of device.

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

This device is a physical light-based hair removal device for consumer use, not an algorithm. Therefore, "standalone (algorithm only)" performance is not applicable. The device's performance is inherently tied to human use and application according to instructions.

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

For hair removal studies of this nature, the "ground truth" for efficacy (hair reduction) is typically established by outcomes data in the form of objective measurements of hair count or hair density in treated vs. untreated areas, often performed by trained personnel or experts following a standardized protocol. This would be observed at specified time points (6, 9, and 12 months as indicated by the definition).

8. The sample size for the training set

The device described is a physical medical device, not an AI/ML algorithm that requires a "training set" in the conventional sense of machine learning. Therefore, a "training set" as it applies to AI/ML is not applicable. Its development would involve engineering, safety, and clinical testing, not algorithmic training.

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

As explained in point 8, the concept of a "training set" with ground truth establishment for an AI/ML algorithm is not applicable to this device.

Ask a specific question about this device