(221 days)
VRNT is a prescription-use immersive virtual reality system intended to provide adjunctive treatment based on cognitive behavioral therapy skills and other evidence-based behavioral methods for patients (age 18 and older) with a diagnosis of chronic lower back-pain (defined as moderate to severe pain lasting longer than three months). The device is intended for in-home use for the reduction of pain and pain interference associated with chronic lower back pain.
VRNT is an immersive virtual reality (VR) system which delivers behavioral therapy content for the treatment of chronic pain via virtual reality hardware. VRNT is a prescription-use device containing pre-loaded, proprietary content on commercially available VR hardware shown in the figure below. The behavioral content incorporates cognitive behavioral therapy (CBT) skills and other evidence-based behavioral methods.
VRNT uses a virtual reality system called GearVR, consisting of a virtual reality head-mounted display, a hand controller and a smartphone
VRNT is designed to be used in an 8-week treatment program which delivers a multifaceted combination of pain management skills training through a sequence of daily sessions (5 days a week) ranging from 7-27 minutes in length (average of 20 minutes). Similar to multisession behavioral treatment program begins with basic skills and progresses to more advanced skills over the 8 weeks. Initial themes in VRNT are focused on understanding the basic science behind chronic pain and developing rudimentary breathing, bodily awareness and mindfulness, relaxation and interoception skills. Later themes build on these skills; they expand on interoception, add passive distraction and refocusing attention, thought appraisal skills for managing emotion triggers. Finally, the program provides opportunities to practice applying the education and self-regulation skills when faced with actual pain triggers. The treatment content, thus, allows the patient over time to build upon education, skills training and their own experiential learning in a manner that increasingly mimics real-world situations.
Here's a breakdown of the acceptance criteria and study information for the VRNT device based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document details the clinical study results as evidence of effectiveness but does not explicitly state pre-defined acceptance criteria in a quantitative table format. Instead, it describes the statistical significance and effect sizes achieved.
| Acceptance Criteria (Implied - based on study objectives) | Reported Device Performance |
|---|---|
| Reduction in Pain Intensity | - Significantly greater reduction in pain intensity at post-treatment than controls (group by time interaction, p = 0.014, g = 0.63; medium to large effect). |
- 60% of VRNT participants, compared to 30% of controls, achieved clinically meaningful reductions (at least 30%) in pain intensity.
- 47% of VRNT participants compared to 13% of controls achieved ≥50% pain reduction. |
| Reduction in Pain Interference | - Significantly greater reduction in pain interference at post-treatment than controls (group by time interaction, p = 0.002, g = 0.84; large effect). - 77% of VRNT participants compared to 53% of controls achieved at least 30% reduction in interference.
- 60% of VRNT participants compared to 30% of controls achieved ≥50% pain interference reduction. |
| Reduction in Pain Interference (Individual Items) | - Significantly greater improvement in interference with general activity, mood, and sleep (p values: 0.03, 0.0006, 0.001, respectively). - General Activity: 80% VRNT and 53% control achieved ≥30% reduction; 67% VRNT and 37% control achieved ≥50% reduction.
- Mood: 77% VRNT and 37% control achieved ≥30% reduction; 63% VRNT achieved ≥50% reduction.
- Sleep: 73% VRNT and 30% control achieved ≥30% reduction; 53% VRNT achieved ≥50% reduction. |
| Safety | - 3% (1/31) of VRNT condition participants reported any adverse events (temporary cybersickness). |
2. Sample Size Used for the Test Set and Data Provenance
The "test set" in this context refers to the clinical trial participants.
- Sample Size: 61 adults.
- Data Provenance: Prospective, randomized clinical trial conducted by the device developer. The country of origin for the data is not explicitly stated.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
This device is a therapeutic virtual reality system, not a diagnostic or AI-driven image analysis device that requires expert ground truthing of cases. The "ground truth" for its effectiveness is based on patient-reported outcomes (pain intensity and pain interference) as assessed by the Short-Form Brief Pain Inventory (BPI-SF). The validation of these measures is established in the medical community through psychometric studies, not by expert consensus on individual cases for a test set in the way a diagnostic algorithm might be evaluated.
4. Adjudication Method for the Test Set
Not applicable. As this is a therapeutic device evaluated by patient-reported outcomes in a randomized controlled trial, there is no "adjudication method" in the context of expert review of cases (like 2+1 radiology review). The primary outcomes were assessed using a standardized, validated questionnaire (BPI-SF).
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, an MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic imaging AI, where multiple readers evaluate cases with and without AI assistance. The VRNT device is a therapeutic tool, and its effectiveness was evaluated via a randomized controlled clinical trial comparing the device to a control group.
6. If a Standalone Performance Study (i.e., algorithm only without human-in-the-loop performance) Was Done
The clinical trial is essentially a standalone performance study of the device (which includes the algorithm/software as its core therapeutic component). The "human-in-the-loop" here is the patient using the VR system, not a clinician interacting with an AI output for diagnosis or interpretation. The study evaluates the effectiveness of the VRNT program as a whole, including the software and the patient's interaction with it, without direct real-time human expert intervention to modify its output or efficacy during the treatment sessions.
7. The Type of Ground Truth Used
The ground truth for the clinical effectiveness study was based on patient-reported outcomes (PROs) of pain intensity and pain interference, measured using the Short-Form Brief Pain Inventory (BPI-SF). These are standardized, validated instruments in clinical research for chronic pain. The "ground truth" for an individual patient's pain experience is inherently subjective and best captured directly from the patient using such tools.
8. The Sample Size for the Training Set
The document does not provide information about a "training set" in the context of machine learning model development. The VRNT device delivers "behavioral therapy content" based on "cognitive behavioral therapy (CBT) skills and other evidence-based behavioral methods." This suggests that the content and therapeutic approach are designed based on established psychological and medical principles, rather than being developed through a machine learning training process on a specific dataset.
If there were any underlying AI components that were "trained," the details are not provided in this regulatory summary. The focus is on the clinical validation of the therapeutic program as a whole.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as no training set for a machine learning model is described in this document. The "ground truth" for the therapeutic approach is established through decades of research in CBT and other evidence-based behavioral methods for pain management. The content of the VRNT program is derived from these established principles.
§ 890.5800 Virtual reality behavioral therapy device for pain relief.
(a)
Identification. A virtual reality behavioral therapy device for pain relief is a device intended to provide behavioral therapy for patients with pain. Therapy is administered via a virtual reality display that utilizes a software program containing the behavioral therapy content.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance testing under the labeled conditions for use must validate the model of behavioral therapy as implemented by the device and evaluate all adverse events.
(2) The patient-contacting components of the device must be demonstrated to be biocompatible.
(3) Software verification, validation, and hazard analysis must be performed.
(4) Electromagnetic compatibility and electrical, mechanical, and thermal safety testing must be performed.
(5) Labeling must include the following:
(i) A warning regarding the risk of nausea and motion sickness;
(ii) A warning regarding the risk of discomfort from the device; and
(iii) A summary of the clinical testing with the device.