(343 days)
The TNM Device is intended to stimulate the vestibular system using tightly controlled thermal waveforms. The TNM Device is indicated for the prophylactic treatment of episodic migraine in adolescent and adult patients 12 years or older.
The TNM Device is a non-invasive, home-use, DC-powered medical device that consists of an over-the-ear Headset with earpieces that protrude into the external ear canals, a Control Unit with resistive touchscreen display, and a power cord. Optional accessories include a wedge pillow to support reclining during each treatment in place of a firm pillow, a stylus pen that can be used in place of a fingertip to interact with the display and prism spectacles that may be worn to enable reading and other visual relaxation activities during treatment.
The TNM device uses a set of controlled thermal waveforms delivered to the anodized aluminum earpieces. The fluctuations interact with the patient's vestibular system, causing changes which can be used to treat migraine headaches.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria (Primary Efficacy Endpoint) | Reported Device Performance (Active Treatment Group) | P-value (vs. Placebo) |
|---|---|---|
| During the third Month of the Treatment Period, their average total number of Monthly Migraine Headache Days will be lower than their comparable averages derived from the Pre-Treatment Baseline Period. | Average change in migraine days: -3.6 ± 0.7 (Per protocol) | |
| -3.3 ± 0.6 (Intention-to-treat) | 0.0142 (Per protocol) | |
| 0.0246 (Intention-to-treat) |
Secondary Efficacy Endpoints (Examples, not all listed as acceptance criteria but used to support effectiveness):
| Secondary Efficacy Endpoint (Example) | Reported Device Performance (Active Treatment Group) | P-value (vs. Placebo) |
|---|---|---|
| Percentage of responders (>50% reduction in monthly migraine days) | 57.1% (Per protocol) | |
| 52.9% (Intention-to-treat) | 0.1146 (Per protocol) | |
| 0.1772 (Intention-to-treat) | ||
| Percentage reduction in monthly migraine days (baseline vs. third month) | -46.1% ± 7.3% (Per protocol) | |
| -40.8% ± 7.6% (Intention-to-treat) | 0.0336 (Per protocol) | |
| 0.0677 (Intention-to-treat) | ||
| Average Total Monthly Headache Pain Scores were lower than baseline | Change in total pain: -21.3 ± 4.1 (Per protocol) | |
| -18.7 ± 3.8 (Intention-to-treat) | 0.0382 (Per protocol) | |
| 0.0966 (Intention-to-treat) | ||
| Average number of Treated Headaches (Acute anti-migraine prescription drug intake) was lower than baseline | Change in acute anti-migraine drugs: -3.7 ± 0.7 (Per protocol) | |
| -3.4 ± 0.6 (Intention-to-treat) | 0.0195 (Per protocol) | |
| 0.0464 (Intention-to-treat) |
Safety Endpoint (Acceptance Criteria):
| Acceptance Criteria (Safety Endpoint) | Reported Device Performance |
|---|---|
| Absence of material dizziness, with the associated risk of falls, as a consequence of using the active-treatment device. | No device-related serious adverse events observed. Berg Balance test used to assess changes, no adverse effects on balance reported. Transient nausea and minor dizziness experienced by some patients, as reported in diagnostic CVS literature. |
Study Details
-
Sample Size used for the test set and the data provenance:
- Randomized subjects (initial test set):
- Active: 50
- Placebo: 28
- Partially active placebo: 40
- Total: 118
- "Per protocol" analysis (subset of test set):
- Active: 30
- Placebo: 18
- Total: 48
- "Intention-to-treat" analysis (original; subset of test set):
- Active: 39
- Placebo: 19
- Total: 58
- "Intention-to-treat" analysis (carry-forward percentage; subset of test set):
- Active: 45
- Placebo: 21
- Total: 66
- Data Provenance: The study was a "multi-center" and "triple-blinded, placebo-controlled, randomized pivotal study." The text does not specify the country of origin, but generally, pivotal studies for FDA approval are often conducted in the US or in countries with comparable regulatory standards. It was a prospective study.
- Randomized subjects (initial test set):
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The study involved clinical diagnosis of migraine and assessment of symptoms. The text mentions that migraine diagnosis was "consistent with the International Classification of Headache Disorders-II (ICHD-II) guidelines" and that investigators reviewed medication usage and concerns about analgesic abuse based on ICHD-II guidelines. This implies medical professionals (physicians/investigators) were responsible for diagnosis and assessment, guided by established clinical criteria.
- The specific number and individual qualifications of these experts are not explicitly stated in the provided text. However, the study design (multi-center, pivotal study) suggests multiple qualified clinicians were involved at various sites.
-
Adjudication method for the test set:
- None explicitly stated for individual case adjudication.
- The study was "triple-blinded," meaning the patients, investigators (those administering treatment and assessing outcomes), and the data analysts were unaware of the treatment assignment. This blinding serves as a robust method to reduce bias in outcome assessment rather than an adjudication method for ground truth.
-
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 therapeutic neurostimulation device for migraines, not an AI-powered diagnostic or interpretive tool that would involve "human readers" or AI assistance in a diagnostic context. Therefore, the concept of "improving human readers with AI assistance" does not apply to this device.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, in essence, the primary efficacy endpoint measures standalone device performance. The study evaluated the device's ability to reduce migraine headache days (and other secondary outcomes) independently when used by patients, compared to a placebo. While the patient interacts with the device, the core therapeutic effect being measured is that of the device itself (the thermal waveforms) without real-time human intervention in modifying the treatment based on AI output. This is a therapeutic device, not an AI diagnostic.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth for effectiveness was primarily outcomes data reported by patients and assessed by investigators:
- Monthly Migraine Headache Days (primary endpoint)
- Monthly Headache Pain Scores
- Number of Treated Headaches (medication intake)
- Quality of Life and Cognition Assessment measures
- Initial diagnosis of episodic migraine was based on expert clinical diagnosis following ICHD-II guidelines.
- The ground truth for effectiveness was primarily outcomes data reported by patients and assessed by investigators:
-
The sample size for the training set:
- This was a clinical trial intended to evaluate the device's efficacy and safety. There is no separate training set in the context of machine learning model development. The study population described (e.g., 50 active, 28 placebo, 40 partially active placebo randomized subjects) is the dataset used to assess the device's performance.
-
How the ground truth for the training set was established:
- As there wasn't a "training set" in the machine learning sense, this question isn't directly applicable. However, the "ground truth" for the study's outcomes was established through patient diaries/reporting, clinical assessments, and self-reported measures of migraine frequency, pain, and medication use, all within the framework of a blinded clinical trial. The initial diagnosis was based on ICHD-II criteria by medical professionals.
§ 882.5893 Thermal vestibular stimulator for headache.
(a)
Identification. The thermal vestibular stimulator for headache is a prescription device used to stimulate the vestibular system by applying thermal waveforms through earpieces placed in a patient's ear canal for the treatment of headache.(b)
Classification. Class II (special controls). The special controls for this device are:(1) The patient-contacting components of the device must be demonstrated to be biocompatible.
(2) Performance testing must validate electromagnetic compatibility and electrical, mechanical, and thermal safety.
(3) The technical parameters of the device, including waveform outputs and temperature limits, must be identified.
(4) Cleaning validation of earpieces must be conducted.
(5) Software verification, validation, and hazard analysis must be performed.
(6) Labeling must include the following:
(i) Information on how the device operates and the typical sensations experienced during treatment;
(ii) A detailed summary of the device's technical parameters; and
(iii) Instructions for maintenance and cleaning of the device.