FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The ViruLite Cold Sore Machine is indicated for shortening the time to healing of herpes simplex labialis lesions on or around the lips with time to healing defined as the time to patient described re-epithelialization.

Device Description

The ViruLite is a solid state opto-electronic device that emits a controlled quantity of 1072nm +/- 12nm peak wavelength near infrared light for a period of approximately 3 minutes. The maximum peak light intensity across the treatment surface is 20mW/cm². The light output and duration are monitored by a microprocessor. The power source is a standard alkaline 9V battery. which is replaceable. The tip of the device that contacts the patient is made out of Acrylonitiile Butadiene Stvrene (ABS).

AI/ML Overview

Here's an analysis of the provided text to extract the acceptance criteria and study details for the ViruLite Cold Sore Machine:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the ViruLite Cold Sore Machine are primarily focused on demonstrating clinical benefit (shortening time to healing for herpes simplex labialis lesions) and safety. The clinical performance data provided supports these criteria.

Acceptance Criteria Category	Specific Acceptance Criteria	Reported Device Performance (as demonstrated in studies)
Clinical Effectiveness	Adequate reduction in time to healing for herpes simplex labialis lesions on or around the lips, with time to healing defined as patient-described re-epithelialization. This is the primary endpoint for all studies.	The ViruLite demonstrated a reduction in healing time compared to placebo in all four supporting datasets.

The requester's own randomized clinical trial also indicated a trend towards effectiveness, though it had data collection and consistency concerns that prevented it from being standalone proof of effectiveness. |
| Clinical Safety | Assess risks of redness, discomfort, burns, and blisters. | Low risk profile demonstrated. The requester's randomized clinical trial reported no major long-lasting complications, only "mild blistering, burning or redness in some patients." This was consistent with what was observed in the four additional submitted datasets and with other light-based technologies. The overall risk was determined to be low. |
| Usability/Label Comprehension |

Device can be used by the intended patient population without assistance.
Labeling comprehension for OTC use.
Appropriate for ages 16 and older. | Demonstrated through two usability studies.
Combined, 47 out of 49 subjects correctly answered questions about appropriate actions in hypothetical scenarios, indicating good labeling comprehension and usability.
The studies were conducted on subjects 16 years of age or older, and it was determined that 16-year-olds could comprehend and follow instructions, and there was little physiological difference between 16-19 and 20+ year-olds. |
| Biocompatibility | Device must be demonstrated to be biocompatible. | Acceptable. The ABS material used for patient contact was evaluated per ISO 10993-1:2003 for cytotoxicity, irritation, and sensitization and found acceptable, as it's a widely used medical material. |
| Cleaning & Disinfection | Cleaning and disinfection instructions for the device must be validated. | Validation Required pre-market. The text states that "Cleaning and disinfection validation data to verify the effectiveness of the cleaning and disinfection instructions are required prior to marketing the ViruLite, otherwise the device is considered to be misbranded and adulterated." This implies it was an outstanding requirement for full market acceptance, not necessarily a completed study at the time of this document, but critical for final acceptance. Labeling includes instructions. |
| Ocular Safety | Performance testing must validate ocular safety. | Acceptable. ViruLite was tested according to IEC 64721:2008 (despite not being an FDA-recognized standard, accepted due to similar prior devices) operating at worst-case continuous LED operation for 8 hours. The measured exposure limit was below the standard's acceptable limit. |
| Electrical Safety | Performance testing must validate electrical safety. | Accepted. The device was subjected to electrical safety testing performed in accordance with EN60601-1:1993. |
| Electromagnetic Compatibility (EMC) | Performance testing must validate EMC. | Accepted. The device was subjected to EMC testing performed in accordance with EN60601-1-2:1993. |
| Software | Software performs as intended and all software-related risks have been adequately mitigated. | Acceptable. The software was deemed to have a minor level of concern. The requester provided comprehensive documentation (requirements, design, traceability, V&V tests, risk analysis) that provided reasonable assurance the software performs as intended. |
| Technical Parameters | The technical parameters of the device, including wavelength, treatment time, treatment area, energy density, spot size, and power, must be characterized. | Characterized. The document describes: 1072nm +/- 12nm peak wavelength, ~3-minute treatment duration, 20mW/cm² maximum peak light intensity, ~7cm² treatment area, 2 LEDs. |
| Labeling |
Complies with 21 CFR 801 and FDA's Guidance on Medical Device Patient Labeling (2001).
Direct users to contact manufacturer and MedWatch for adverse events.
Includes specific information pertinent to use by intended patient population and treatment regimen. | Complies. The document explicitly states compliance with 21 CFR 801 and the guidance. The MedWatch adverse event reporting statement is directly quoted in the text. The various warnings, precautions, contraindications, and instructions for use (e.g., "Do not use except for cold sores...", "not to prevent cold sores...", "not studied in immunocompromised...") demonstrate specific patient information. |

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

The "test set" for clinical effectiveness and safety primarily refers to the patient data used in the clinical studies.

Requester's Randomized Clinical Trial:
- Sample Size: Total of 95 subjects (ages 20 years and above).
  - 48 subjects in the active (treatment) arm.
  - 47 subjects in the control (placebo) arm.
- Data Provenance: Not explicitly stated but implied to be a prospective, double-blind, placebo-controlled, randomized clinical trial conducted by the requester. Location is not given, but likely the country where the company is based or a region allowing such trials.
Four Additional Data Sets (Supporting Effectiveness):
- Dougal and Kelly 2001: 56 subjects
- Dougal and Haslam 2004: 54 subjects
- Hargate 2006: 32 subjects
- Lee, Hargate and Dougal 2004: 87 subjects
- Data Provenance: These are listed as studies from 2001, 2004, and 2006. The exact country of origin is not explicitly mentioned but the authors' names (Dougal, Kelly, Haslam, Hargate, Lee) suggest a Western context (e.g., UK, USA, Australia). They are retrospective in the sense that they were submitted to support the De Novo request but were conducted prior to this specific submission. They are described as double-blind, placebo studies.
Usability Studies:
- Sample Size:
  - First study: 9 subjects.
  - Second study: 40 additional subjects (totaling 49, with 2 withdrawals).
  - Combined: 47 subjects (passed) out of 49.
- Data Provenance: Not specified, but likely conducted by the requester in a relevant country for OTC use within the target population. Prospective.

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

The ground truth for the clinical effectiveness (time to healing) was primarily established by patient self-assessment. The primary endpoint was "time to healing" defined as "patient described re-epithelialization". Therefore, no external experts were explicitly mentioned for establishing this specific clinical ground truth.

4. Adjudication Method for the Test Set

Given that the primary endpoint was "patient described re-epithelialization," there was no formal external expert adjudication method (like 2+1 or 3+1 consensus) explicitly described for the clinical effectiveness data. The patients themselves provided the "ground truth" for healing time.

For internal study consistency and data integrity, there would have been study coordinators or investigators involved, but the ultimate "truth" for the primary endpoint came directly from the patient's report.

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

No obvious MRMC comparative effectiveness study was described. The studies compared the device to a placebo (or acyclovir in one instance for a specific arm), and the endpoint was patient-reported healing time, not an assessment by human readers. The concept of "human readers improving with/without AI assistance" does not apply here as it's a device for direct physical treatment, not an imaging or diagnostic AI tool.

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

Yes, the primary clinical effectiveness studies are essentially "standalone" evaluations of the device. The ViruLite device is a physical light therapy device, not an algorithm. Its performance is measured directly by its effect on the patient (reduced healing time) without human intervention in its outcome assessment process beyond the patient's own reporting. The intervention itself (device use) is by the human (patient).

7. The Type of Ground Truth Used

Clinical Effectiveness (Healing Time): Patient-described re-epithelialization. (Outcomes data - specifically patient-reported outcome).
Clinical Safety: Patient self-reports of adverse events (redness, discomfort, blistering, burning), and overall absence of "major long-lasting complications."
Usability: Subject responses to questions regarding labeling comprehension and appropriate actions in hypothetical scenarios.

8. The Sample Size for the Training Set

The provided document does not discuss a "training set" in the context of an AI/machine learning model. The ViruLite is a hardware device with "software" to monitor button presses, control LEDs, and manage the 3-minute treatment cycle. This software is not a machine learning algorithm that learns from data. Therefore, the concept of a training set as typically understood for AI models does not apply here. The software review was about demonstrating it performs as intended, not about training an AI.

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

As explained in point 8, there is no "training set" for an AI model. The software's "ground truth" in this context would be defined by the functional requirements in its software requirements specification (e.g., "ON button press correctly initiates treatment cycle," "LEDs activate at specified wavelength," "treatment duration is 3 minutes +/- tolerance"). These were established by the device's design specifications and verified through standard software and hardware testing (verification/validation tests), not through empirical data training.

Summary

Regulation Number and Section

§ 878.4860 Light based energy source device for topical application.

(a)
Identification. The device emits light energy at near infrared spectrum and is applied externally to the surface of herpes simplex labialis lesions on or around the lips.(b)
Classification. Class II (special controls). The special controls for this device are:(1) The technical parameters of the device, including wavelength, treatment time, treatment area, energy density, spot size, and power, must be characterized.
(2) The cleaning and disinfection instructions for the device must be validated.
(3) The device must be demonstrated to be biocompatible.
(4) Performance testing must validate electromagnetic compatibility (EMC), ocular safety, and electrical safety of the device.
(5) Labeling must direct end-users to contact the device manufacturer and MedWatch if they experience any adverse events when using this device.
(6) Labeling must include specific information pertinent to use of the device by the intended patient population and the treatment regimen.
(7) Simulated use testing must include information from a usability, label comprehension and self-selection study to demonstrate that the device can be used by the intended patient population without any assistance.
(8) Clinical data must show adequate reduction in time to healing and assess risks of redness, discomfort, burns, and blisters.