Search Results

The handLITE is intended to emit energy in the red and near infrared region of the light spectrum, is generally indicated to treat dermatological conditions and specifically indicated to treat contact dermatitis of the hand and wrist.

The handLITE device consists of:

1. Flexible silicone glove with integrated controller (contains rechargeable lithium-ion polymer battery)
2. Power supply and country specific adaptors

handLITE is a home use wearable light emitting diode (LED) phototherapy device.

The device consists of a flexible silicone glove that contains red (630nm) and near infrared (830nm) light emitting diodes (LEDs) and an integrated controller. The LEDs generate the light at an intensity of 30mW/cm², delivering 18J/cm² per treatment.

The power supply is used to charge the integrated Lithium battery in the handLITE.

The provided document contains information on the handLITE (TN19S) device, but it does not contain acceptance criteria or a study that specifically proves the device meets predefined acceptance criteria for a new and complex AI/ML device.

The document describes a 510(k) clearance, which largely focuses on demonstrating substantial equivalence to a predicate device. While a clinical study was performed to support safety and effectiveness, it's not structured as a typical AI/ML validation study with pre-defined performance metrics and acceptance thresholds.

Therefore, many of the requested fields cannot be directly extracted from the provided text. I will fill in what can be inferred or directly stated, and clearly mark what information is not present.

Acceptance Criteria and Device Performance (Not Applicable in the traditional AI/ML sense)

The FDA 510(k) clearance process for this device, a light-emitting device for dermatological conditions, focuses on demonstrating substantial equivalence to predicate devices. There are no explicitly stated numerical "acceptance criteria" for the device's performance in the way one might define them for an AI/ML diagnostic algorithm (e.g., "sensitivity must be >X% AND specificity >Y%").

Instead, the clinical performance testing aims to show the device is safe and effective for its intended use, analogous to how a new drug might demonstrate efficacy and safety in trials. The "performance" is articulated as an improvement in contact dermatitis symptoms.

Table of Performance (Based on Clinical Study Results):

Study Details

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

   • Clinical Study (Effectiveness & Safety):

     • Enrollment: 25 subjects
     • Completed Full Treatment: 23 subjects
     • Data Included in Evaluation: All available data from 25 subjects (including the 2 who did not complete the full course).
     • Data Provenance: Not explicitly stated, but the submission is from a UK company ("iSMART Developments LTD, Birmingham, B73 5LT United Kingdom"). The clinical study likely took place in the UK or a region where the sponsor operates, but this is an inference, not directly stated.
     • Retrospective/Prospective: Prospective (clinical study undertaken to support safety and effectiveness).

   • Usability/Human Factors Study:

     • Sample Size: 19 subjects
     • Data Provenance: Not explicitly stated.
     • Retrospective/Prospective: Prospective (study conducted to assess label comprehension).

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

   • This is not an AI/ML device requiring expert consensus for ground truth on images or other diagnostic data.
   • The "ground truth" for the clinical effectiveness study was objective measurement of dermatitis signs and symptoms using the SCORAD index, likely performed by clinical investigators. The qualifications of these investigators are not detailed in this summary.

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

   • Not applicable as this is not a diagnostic AI/ML device that requires adjudication of interpretations. The SCORAD index is a standardized scoring system.

4. 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 study was performed. This is not an AI/ML diagnostic or assistive device for human readers. It is a light therapy device.

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

   • Not applicable. This device is a treatment device, not a standalone diagnostic algorithm. Its performance is measured directly by its effect on the patient's condition.

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

   • For the effectiveness study: Clinical Assessment (SCORAD index) of the signs and symptoms of contact dermatitis. This is a standardized, objective scoring system. Patient-reported outcomes were also collected.

7. The sample size for the training set:

   • Not applicable. This is not an AI/ML device that requires a training set in the conventional sense. Its "training" would be device design and engineering.

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

   • Not applicable as no AI/ML training set is mentioned or implied for this device.

Ask a specific question about this device

The décoLITE LED device is an over-the-counter device that is intended for the use in the treatment of wrinkles in the decolletage area.

The décoLITE device consists of:

• 1. Flexible silicone panel
• 2. Controller
• 3. Power supply and country specific adaptors
• 4. Adjustable straps (2)
     décoLITE is a home use wearable light emitting diode (LED) phototherapy device.
     The device consists of a flexible silicone panel (1) that contains red (630nm) and near infrared (830nm) light emitting diodes (LEDs), a controller (2) that contains a rechargeable lithium polymer batter, a power supply (3) for charging the battery, and two adjustable straps (4) that hold the panel in place during treatment.
     The LEDs produce red and near infrared (NIR) light in the visible spectrum (Red: 630nm ± 10nm, NIR: 830nm ± 10nm). The device works through a non-thermal mechanism called photobiomodulation. The LEDs produce light at an intensity of 30mW/cm² delivering 18J/cm² per treatment.
     The power supply is used to charge the lithium polymer battery in the décoLITE controller

Here's a breakdown of the acceptance criteria and study details for the décoLITE LED device, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details:

1. Sample size used for the test set and the data provenance:

   • Clinical Performance Test Set Sample Size: 25 subjects were enrolled, 19 completed the full study treatment course. One subject's results were excluded due to unprotected sun exposure, resulting in 18 subjects effectively analyzed for efficacy.
   • Usability/Human Factors Test Set Sample Size: 17 subjects.
   • Data Provenance: The study appears to be prospective as it involved enrolling subjects, administering treatment, and then evaluating outcomes. The location of the study is not explicitly stated but implies a clinical setting.

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

   • The document primarily describes a patient-reported outcome (subjects "felt their wrinkles had improved" and "felt the overall appearance of their chest had improved") and an objective assessment using a validated scale ("Landau et al. (2016)"). It does not explicitly state the number or qualifications of experts used for establishing the ground truth for the clinical effectiveness endpoints. The "mean baseline wrinkle severity was 2.5 and the mean improvement after treatment was 0.9 points" suggests an objective assessment, likely by a trained clinician or rater using the Landau scale. However, the exact number and qualifications of these raters are not provided.

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

   • The document does not describe an adjudication method for the clinical effectiveness endpoints. The assessment using the Landau et al. scale likely involved a single or multiple trained raters, but whether consensus or adjudication was used is not specified.

4. 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, an MRMC comparative effectiveness study was not done. This device is a light-emitting diode (LED) device for wrinkle treatment, not an AI-powered diagnostic or assistive tool.

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

   • Yes, the clinical performance testing assesses the device's standalone effectiveness in reducing wrinkles when used by subjects at home. There is no human-in-the-loop component beyond the subject using the device as instructed.

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

   • For the clinical performance study, the primary effectiveness endpoint was measured using a validated scale developed by Landau et al. (2016), which represents an objective clinical assessment tool. Additionally, patient-reported outcomes (subjects feeling improvement) were used. Safety was assessed by reporting adverse events.

7. The sample size for the training set:

   • The document does not describe a separate "training set" in the context of an algorithm or machine learning model. The clinical study described is a performance study for the device itself, not for training a model.

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

   • As there is no mention of a "training set" for an algorithm, this question is not applicable based on the provided text.

Ask a specific question about this device

The LUMA LED light patches are over-the-counter devices intended to emit energy in the visible and near infra-red light spectrum.

LUMA Blemish is an over-the-counter device intended to emit energy in the red and blue region of the light spectrum, specifically indicated to treat mild to moderate acne vulgaris of the face.

LUMA Revive is an over-the-counter device intended to emit energy in the red and Near infra-red spectrum and is intended for the use in the treatment of facial wrinkles.

The LUMA Patches (Blemish and Revive) are battery operated, cordless wearable Light emitting diode (LED) devices intended to emit an even, cool, narrow band of light in the blue (415nm), red (630nm) and near infra-red (830nm) spectrum for the treatment of mild to moderate acne vulgaris and facial wrinkles. The devices work through non-thermal mechanisms called photobiomodulation (wrinkles) and endogenous Photodynamic therapy (acne vulgaris).

LUMA Blemish and LUMA Revive consists of the following key components.

• 1. Silicone flexible patches
• 2. Adhesive hydrocolloid patches x14
• 3. Magnetic 2 pin, 4mm to USB A connector
• User manual 4.

The LUMA patches are home use wearable LED phototherapy devices composed of flexible patches containing Light emitting diodes (LEDs). The LEDs generate the light.

The LUMA patches are comprised of an endo skeleton made of silicone containing an upper surface made of Polyurethane (PU) that houses the ON/OFF button magnetic charging pins and a battery charging indicator and a lower surface manufactured from Polyethylene terephthalate (PET).

The LEDs produce blue, red and near infra-red (NIR) light in the visible spectrum.

LUMA Blemish (Blue: 415nm +/- 10nm and Red: 630nm +/- 10nm)

LUMA Revive (Red: 630nm +/- 10nm and NIR 830nm +/-10nm.).

The LEDs are driven by an integrated 3.7V, 37mAh Lithium Polymer battery.

The battery is charged via a magnetic 2 pin, 4mm to USB A connector that plugs into a standard 5v USB A power adaptor. The device cannot be operated while in charging mode. The device contains a charging watchdog that prevents overcharge. The battery status of the devices is relayed to the user by a single indicator LED on the upper surface of the LUMA patches (during charging) and by the treatment LEDs on the lower or inner surface (during treatment).

The LUMA patches contain a simple ON/OFF button on the upper surface of the patch that switches the LEDs ON. The treatment time is 10 minutes. The devices automatically turn OFF after 600 seconds (10 minutes). The user may stop the treatment program during the 10 minutes by pressing the ON/OFF button.

The LUMA patches are worn on the face and are held in place by an adhesive hydrocolloid patch.

The provided document is a 510(k) Summary for the LUMA LED patches (LUMA Blemish and LUMA Revive). It describes the device, its intended use, and its substantial equivalence to predicate devices, but does not contain acceptance criteria or a study proving the device meets acceptance criteria related to its clinical effectiveness.

Here's a breakdown of why the requested information cannot be fully provided from this document:

• Clinical Performance Not Required: The document explicitly states in Section 5.6, "Since the LUMA patches are substantially equivalent to the predicate devices and raise no new questions in terms of safety and efficacy, clinical data is not required." This means a clinical study to establish performance against specific acceptance criteria for treatment efficacy was not performed or submitted for this 510(k) clearance.
• Focus on Substantial Equivalence: The primary goal of a 510(k) is to demonstrate substantial equivalence to a legally marketed predicate device, not necessarily to prove absolute effectiveness against predefined clinical acceptance criteria through new clinical trials.
• Non-Clinical Performance Testing: While non-clinical performance testing (electrical safety, EMC, biocompatibility, photobiological safety, software life cycle) was conducted, these tests focus on safety and device functionality rather than clinical efficacy.

Therefore, the requested details regarding acceptance criteria and a study proving the device meets them cannot be extracted for clinical efficacy from this document. However, I can extract information related to the non-clinical performance testing.

Here's what can be extracted based on the provided text, with clarifications where the information isn't present:

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

Regarding Clinical Effectiveness Acceptance Criteria: The document explicitly states "clinical data is not required" due to substantial equivalence. Therefore, there are no reported clinical acceptance criteria or performance data for clinical efficacy in this submission.

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

• For Non-Clinical Performance Testing (e.g., electrical safety, EMC, biocompatibility): The document does not specify general "sample sizes" for these types of tests, as they typically involve specific units of the device under defined testing conditions according to the standards. The provenance of this data is from the testing conducted to meet the relevant standards.
• For Label Comprehension Testing:
  • Sample Size: 26 subjects (12 M: 14 F)
  • Data Provenance: Not explicitly stated, but implied to be a prospective study conducted for the purpose of this submission ("A study was conducted demonstrating comprehension of the LUMA patch labelling"). Country of origin is not specified.

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)

• For Non-Clinical Performance Testing: Ground truth is established by the requirements and methodologies outlined in the referenced international standards. The "experts" would be the certified testing laboratories and their personnel carrying out the tests, but no specific number or qualifications are provided in this summary.
• For Label Comprehension Testing: "Ground truth" here relates to user comprehension of the labeling. The study assessed the users' understanding directly. There were no external experts used to establish a "ground truth" for the test set, but rather the study measured the users' ability to comprehend the instructions effectively.

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

• For Non-Clinical Performance Testing: Adjudication methods are typically defined by the specific testing standards. This document does not detail specific adjudication methods beyond stating conformity to the standards.
• For Label Comprehension Testing: The document does not describe an adjudication method for labeling comprehension. It evaluated comprehension outcomes directly from the subjects.

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 light therapy patch, not an AI-assisted diagnostic or therapeutic device that would involve human "readers" or AI assistance in decision-making. No MRMC comparative effectiveness study was done.

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

• Not Applicable: This is an LED light therapy device, not an algorithm. The device functions independently once activated by a user, but it's not an "algorithm only" system in the sense typically understood for standalone performance in AI/software.

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

• For Non-Clinical Performance Testing: The "ground truth" for these tests is the defined requirements and acceptable limits specified in each international standard (e.g., maximum permissible current leakage, specific EMC emission levels, defined biocompatibility responses).
• For Label Comprehension Testing: The "ground truth" was the accurate understanding of the device's labeling and instructions by the study participants, assessed through direct responses to comprehension questions.

8. The sample size for the training set

• Not Applicable: As this is primarily an LED light therapy device evaluated for substantial equivalence based on physical and technical characteristics and non-clinical safety, there is no "training set" in the context of an algorithm or AI system.

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

• Not Applicable: See point 8.

Ask a specific question about this device