Search Results

Nerivio is indicated for acute and/or preventive treatment of migraine with or without aura in patients 8 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

Nerivio Infinity is indicated for acute and/or preventive treatment of migraine with or without aura in patients 8 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

The Nerivio and Nerivio Infinity are wearable, battery-powered, Remote Electrical Neuromodulation (REN) devices that are controlled by a mobile application. The systems deliver low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically.

The devices are composed of:

• A pair of UltraStim® electrodes (K130987) covered with hydrogel and removable protective film. In NerivioInfinity, the electrodes are embedded in a disposable, replaceable pad. In Nerivio, the electrodes are not disposable or replaceable.
• An electronic circuitry that includes microcontroller with firmware, LED indicator, a power button for activating the device, and Bluetooth radio for wireless connection to Android and iOS mobile platforms. The circuitry also includes a battery, which is rechargeable in NerivioInfinity and not rechargeable in Nerivio.
• An armband that is wrapped over the device to secure the device position on the user's arm is also included.

The devices are operated and controlled via mobile application software that is installed and run on the user's personal mobile device, such as a mobile phone or tablet. The device's hardware communicates with the mobile application through Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0-40 mA), to start, pause or stop the stimulation program, and to view device status such as the device's connection state, stimulation duration, battery level (when connected to Nerivio Infinity), remaining number of treatments (when connected to Nerivio), and user notifications.

The user is instructed to adjust the intensity to the strongest stimulation level just below the perceived pain level. Treatments with Nerivio and Nerivio Infinity are intended to be self-administered by the user immediately after the onset of migraine headache or aura or every other day for migraine prevention.

The provided FDA 510(k) clearance letter and summary for Nerivio and Nerivio Infinity primarily focus on demonstrating substantial equivalence to a previously cleared predicate device (K241756). It discusses minor changes and states that extensive non-clinical and clinical testing was not needed for this specific 510(k) submission because of the close similarity to the predicate.

Therefore, the document does not contain detailed acceptance criteria and studies demonstrating device performance against those criteria in the way one might expect for an initial device clearance or a completely new technology. Instead, it refers to existing knowledge and prior clearances, and specifically addresses the basis for revising certain labeling precautions.

I will extract the information available, acknowledging the limitations inherent in this type of submission.

1. Table of Acceptance Criteria and Reported Device Performance

As this K250405 submission is for modifications to an already cleared device, it doesn't present new acceptance criteria or new primary performance study results in the typical format. Instead, it relies on the predicate device's established performance and justifies that the minor changes do not raise new questions of safety or effectiveness. The "reported device performance" here relates to the basis for modifying labeling precautions.

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

• For long-term use data:
  • Sample Size: Not explicitly stated in the 510(k) document, but the cited study (Synowiec A, et. al. Adv Ther. 2024 Jan;41(1):170-18) would contain this information. The description mentions "real-world data on use of Nerivio collected from US patients."
  • Data Provenance: United States patients, retrospective (post-market studies).
• For pregnancy data:
  • Sample Size: Not explicitly stated in the 510(k) document, but the cited study (Peretz A, et. al. Headache. 2023;63(7):968-970) would contain this information.
  • Data Provenance: Not explicitly stated regarding country, but described as a "retrospective survey-study."

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

This information is not provided in the 510(k) document. The cited studies are "post-market studies of real-world data" and a "retrospective survey-study," which typically rely on patient-reported outcomes or clinical records rather than expert adjudication for ground truth directly related to device performance in the same way, for example, a diagnostic imaging AI would.

4. Adjudication Method for the Test Set

This information is not provided in the 510(k) document. Given the nature of the evidence (real-world data, survey), formal adjudication by a panel of experts for a test set is unlikely to have been the primary method for establishing "ground truth."

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, an MRMC comparative effectiveness study was not done and is not applicable to this device or its clearance. Nerivio/Nerivio Infinity is a direct therapeutic device, not an AI-assisted diagnostic tool that involves human "readers."

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

N/A. This device is a transcutaneous electrical nerve stimulator for migraine treatment, not an algorithm that performs a standalone task for evaluation. It is a user-controlled device with specific treatment parameters. The "algorithm" in this context refers to the device's firmware controlling the stimulation, which is part of the integrated device used by the patient. Its performance is evaluated through patient response to the therapy, not an "algorithm-only" performance in isolation.

7. The Type of Ground Truth Used

• For long-term use data: Patient-reported outcomes and potentially clinical records from "real-world data on use of Nerivio."
• For pregnancy data: Patient responses from a "retrospective survey-study."
• The fundamental "ground truth" for therapeutic neurological devices like this is reduction in migraine symptoms, frequency, and severity, typically assessed through patient diaries and validated questionnaires. This specific 510(k) focuses on validating the safety aspects of long-term and pregnancy use, drawing from real-world data.

8. The Sample Size for the Training Set

The document does not contain information about a "training set" in the context of machine learning, as this is a neuromodulation device, not an AI/ML diagnostic or predictive algorithm being trained. The development of the device's therapeutic parameters would have been established through prior clinical trials (likely supporting the predicate device's initial clearance) and engineering design, not an ML training process.

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

N/A, as there is no "training set" in the context of machine learning described in this 510(k) submission. The efficacy and safety data upon which the device's design and indications are based would have come from the clinical trials that established the predicate device's clearance.

Ask a specific question about this device

The Nerivio is indicated for acute and/or preventive treatment of migraine with or without aura in patients 8 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

The Neriviolnfinity is indicated for acute and/or preventive treatment of migraine with or without aura in patients 8 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

The Nerivio and NerivioInfinity are wearable, battery-powered, Remote Electrical Neuromodulation (REN) devices that are controlled by a mobile application. The systems deliver low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically.

The devices are composed of:

• A pair of UltraStim® electrodes (K130987) covered with hydrogel and removable protective . film. In NerivioInfinity, the electrodes are embedded in a disposable, replaceable pad. In Nerivio, the electrodes are not disposable or replaceable,
• An electronic circuitry that includes microcontroller with firmware, LED indicator, a power button for activating the device, and Bluetooth radio for wireless connection to Android and iOS mobile platforms. The circuitry also includes a battery, which is rechargeable in NerivioInfinity and not rechargeable in Nerivio.
• An armband that is wrapped over the device to secure the device position on the user's arm is also included.

The devices are operated and controlled via mobile application software that is installed and run on the user's personal mobile device, such as a mobile phone or tablet. The device's hardware communicates with the mobile application through Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0-40mA), to start, pause or stop the stimulation program, and to view device status such as the device's connection state, stimulation, battery level (when connected to NerivioInfinity), remaining number of treatments (when connected to Nerivio), and user notifications.

The user is instructed to adjust the intensity to the strongest stimulation level just below the perceived pain level. Treatments with Nerivio and NerivioInfinity are intended to be self-administered by the user immediately after the onset of migraine headache or aura or every other day for migraine prevention.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary:

The core of this submission is to expand the indicated age range of the Nerivio and NerivioInfinity devices to include children aged 8-11. Therefore, the acceptance criteria and study focus on demonstrating the safety and effectiveness of the device in this younger population, showing it is comparable to its performance in the previously cleared adolescent and adult populations.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is an age range expansion for an already cleared device, the "acceptance criteria" are implicitly demonstrating comparable safety and effectiveness in the new age group (8-11 years old) to the previously cleared age group (12 years and older). The performance metrics align with what would be expected for a migraine treatment device.

Implicit Acceptance Criteria (for the 8-11 age group) and Reported Device Performance:

*Note: The study population included patients aged 6-11 years old. The device indication sought and granted in the 510(k) is for 8 years of age or older. The use of data from 6-7 year olds in the study would further support the safety and effectiveness for 8-11 year olds, as younger children might present more challenges in terms of compliance or adverse events.

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

• Sample Size: The clinical investigation included n=293 patients aged 6-11 at their first use of Nerivio (for safety and overall usage patterns in the real world). For effectiveness endpoints (acute treatment), analyses were performed on a subset of patients who completed voluntary pre- and post-treatment surveys, with the number of patients varying for each specific outcome (e.g., 18 for headache relief, 25 for headache freedom, 18 for functional disability, 10 for nausea/vomiting, 8 for phonophobia, 9 for photophobia).
• Data Provenance: The study consisted of a retrospective analysis of prospectively-collected real-world data for children in the United States. The data was collected between May 2020 to October 2023.

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

This type of study does not involve expert readers establishing ground truth in the traditional sense (e.g., for image interpretation). The "ground truth" for effectiveness is patient-reported outcomes of migraine symptoms, consistent with how efficacy trials for migraine treatments are typically conducted. Safety data is collected via customer service reports, which are also patient-reported or initiated.

4. Adjudication Method for the Test Set

Not applicable in this context. Adjudication methods (e.g., 2+1, 3+1) are typically used in studies where multiple expert readers interpret subjective data (like medical images) and their disagreements need to be resolved to establish ground truth. This study relies on patient-reported outcomes for effectiveness and adverse event reporting for safety.

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 a standalone therapeutic device for migraine treatment, not an AI-assisted diagnostic tool that would involve human "readers" interpreting cases.

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

This is a device that directly treats a condition; it's not an AI algorithm that provides a diagnosis or analysis. Therefore, a "standalone algorithm performance" evaluation is not relevant in the same way it would be for an AI diagnostic device. The device's performance is its direct therapeutic effect, not its output as an algorithm.

7. The Type of Ground Truth Used

The ground truth for effectiveness was patient-reported outcomes (PROs) on migraine symptoms (headache pain, functional disability, nausea/vomiting, phonophobia, photophobia) via voluntary pre- and post-treatment surveys. For safety, the ground truth was based on reported adverse events through customer service complaints and other product issue reports.

8. The Sample Size for the Training Set

Not applicable. This is not a study validating an AI model that requires a distinct training set. The clinical investigation is a real-world study assessing the device's performance in a new age group. The "knowledge" or "training" for the device itself comes from its prior development and existing clinical data which supported its previous clearances for older populations.

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

Not applicable, as there is no "training set" in the context of an AI/ML model for this specific submission. The established efficacy and safety data from prior clinical trials in adolescents and adults (e.g., K223169 and K232152) serve as the benchmark against which the performance in the 8-11 age group is compared for equivalence.

Ask a specific question about this device

The Neriviolnfinity is indicated for acute and/or preventive treatment of migraine with or without aura in patients 12 years of age or older. It is a prescription use, self-administered device for use in the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

The Neriviolnfinity is a wearable, battery-powered device that is controlled by a mobile application. The system delivers low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically. The device is composed of: A pair of UltraStim® electrodes (K130987) covered with hydrogel and removable protective film, embedded in an electrodes pad set. The electrodes pad is disposable and replaceable. An electronic circuitry that includes microcontroller with firmware and for wireless connection to Android and iOS mobile platforms, LED indicator, a USB-C charging port, a power button for activating the device and a battery contained in a plastic enclosure. An armband that is wrapped over the device to secure the NerivioInfinity position on the user's arm is included. The device is operated and controlled via mobile application software that is installed and run on the user's personal mobile device, such as a mobile phone or tablet. The device's hardware communicates with the mobile application through Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0-40mA), to start, pause or stop the stimulation program, and to view device status such as the device's connection state, stimulation duration, battery level, and user notifications.

The provided text is a 510(k) summary for the NerivioInfinity device. It details the device, its intended use, and a comparison to a predicate device (Nerivio). However, it does not contain the information requested regarding acceptance criteria, specific performance data (beyond "functioned as expected"), sample sizes for testing, ground truth establishment, or multi-reader multi-case studies.

The summary explicitly states: "No clinical trials were performed with the subject device, given that the therapeutic elements (electrodes, electrical waveform, location on the body, treatment instructions, treatment duration, etc.) are the same as in the predicate device." This means that the device's performance was not evaluated through a new clinical study. Instead, substantial equivalence was claimed based on its similarity to the predicate device, which presumably underwent clinical testing for its original clearance.

Therefore, I cannot provide a table of acceptance criteria and reported device performance from this document for the NerivioInfinity, nor details about its test set, ground truth establishment, or clinical study design, as these were not conducted for this specific device clearance.

The "Performance Data" section solely describes non-clinical bench tests and usability tests.

Here's what can be extracted based on the provided text, while also noting what cannot be provided:

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

• Cannot be provided for the NerivioInfinity from this document. The document states that "No clinical trials were performed with the subject device." The "Performance Data" section refers to non-clinical bench tests and usability tests, stating that "In all instances, the NerivioInfinity functioned and expected." No specific quantitative acceptance criteria or performance metrics (e.g., sensitivity, specificity, accuracy, or clinical efficacy outcomes like pain reduction percentages) are detailed for the non-clinical tests.

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

• A "test set" in the context of clinical performance or AI evaluation (as implied by the question) was not used for this device's clearance according to the document.
• For non-clinical bench tests and usability tests: The specific sample sizes are not provided. The document mentions "internal bench tests and external lab testing" and "Human factor (Usability) tests were performed to validate that all critical tasks related to use-errors and knowledge errors were successfully performed by representative intended users." No details on the number of "representative intended users" or the number of units tested are given.
• Data provenance: N/A for clinical data directly from this device's testing. For the non-clinical tests, the provenance is "internal bench tests" and "external lab testing" without further geographical details. The company is based in Netanya, Israel.

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

• N/A. As no clinical "test set" for performance evaluation (in the sense of the original prompt's context, i.e., diagnostic accuracy or clinical efficacy) was used for this device's clearance, there was no need for experts to establish ground truth in that context. Usability tests involved "representative intended users" but not "experts" establishing "ground truth" on medical outcomes.

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

• N/A. No clinical test set.

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:

• N/A. This device is a direct neuromodulation device, not an AI-assisted diagnostic or therapeutic device that would typically involve human "readers" or an MRMC study.

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

• N/A. This device is a standalone therapeutic device, not an algorithm. Its performance is evaluated through its physical and electrical characteristics and clinical outcomes (established by the predicate device's studies).

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

• N/A for the NerivioInfinity's clearance under this 510(k). The basis for clearance is "substantial equivalence" to the predicate device, meaning its safety and effectiveness are inferred from the predicate's established performance. For the predicate device, it would have been clinical outcomes data (e.g., migraine reduction, pain relief).

8. The sample size for the training set:

• N/A. This device does not have a "training set" in the context of machine learning or AI.

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

• N/A. This device does not have a "training set."

Summary of Device Performance (from the document but not necessarily "acceptance criteria"):

Ask a specific question about this device

The Nerivio is indicated for acute and/or preventive treatment of migraine with or without aura in patients 12 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

The Nerivio is a wearable, battery-powered device that is controlled by a mobile application. The system delivers low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically. The device is composed of a pair of UltraStim® electrodes (K130987) covered with hydrogel and removable protective film, an electronic circuitry that includes firmware, LED indicator and a power button for activating the device and for wireless connection with Android and iOS mobile platforms and a battery contained in a plastic case situated within thermoplastic elastomers ("TPE") shell. In addition, an armband that is wrapped over the device to secure the Nerivio position on the user's arm is included. The device is operated and controlled via software that is installed and run on a user's personal mobile device such as a mobile phone or tablet. The device hardware communicates with the mobile application through a Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0-40mA), to start or stop the stimulation program, and to view device status such as the device's connection state, stimulation duration, remaining number of treatments, and user notifications. The user is instructed to adjust the intensity to the strongest stimulation level just below the perceived pain level. Treatments with Nerivio are intended to be self-administered by the user immediately after the onset of migraine headache or aura.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Device Name: Nerivio
Indications for Use (New/Expanded): Acute and/or preventive treatment of migraine with or without aura in patients 12 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura for acute treatment, or every other day for preventive treatment.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes a clinical study for the preventive indication for Nerivio, comparing it against a sham device. The "acceptance criteria" are implied by the primary and secondary efficacy endpoints of the clinical trial designed to demonstrate superiority over sham for migraine prevention.

2. Sample Size and Data Provenance

• Test Set Sample Size: 248 participants randomized (Active: 128, Sham: 120) for the Intent-to-Treat (ITT) dataset. Analysis for the primary endpoint was also performed on a modified ITT (mITT) dataset of 95 active and 84 sham participants (total 179) who completed at least 12 treatments.
• Data Provenance: The randomized, controlled trial was prospective and multicenter. While the specific countries are not mentioned, the context of FDA submission suggests it was likely conducted, at least primarily, within the United States. It was a prospective study.
• For the adolescent real-world data: 61 patients. Data collected prospectively through the Nerivio App between January 2, 2021, and November 26, 2022, from US patients.

3. Number of Experts and Qualifications for Ground Truth (Clinical Trial)

• The document does not explicitly state the number or qualifications of experts used to establish the ground truth for the clinical trial. However, the ground truth was based on participants' self-reported data using an electronic daily migraine diary application installed on their smartphones, following the International Classification of Headache Disorders (ICHD-3) criteria for migraine. This suggests that the diagnostic criteria were applied by healthcare professionals at the 15 study sites, who would be qualified to diagnose migraine. The assessment of efficacy endpoints (migraine days, headache days, medication usage) relied on the self-reported diary data.

4. Adjudication Method for the Test Set

• The document does not mention an adjudication method for the test set data (e.g., 2+1, 3+1 for imaging reads). The data collection for efficacy endpoints was through self-reported daily diaries.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No, an MRMC comparative effectiveness study was not performed. This study was a Randomized Controlled Trial (RCT) comparing the device directly against a sham control for migraine prevention, not a study evaluating human reader performance with or without AI assistance.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop)

• This device is a physical neuromodulation device, not an AI algorithm for diagnosis or image interpretation. Therefore, the concept of "standalone performance" for an algorithm without human-in-the-loop does not directly apply in the typical sense of AI/imaging devices. The "performance data" presented is clinical efficacy and safety data from a human-device interaction (patients using the device).

7. Type of Ground Truth Used

• For the main clinical trial: The ground truth for headache/migraine days and medication usage was established through patient self-reported daily migraine diaries collected prospectively via an electronic application on smartphones. Migraine diagnosis itself was based on ICHD-3 criteria.
• For the adolescent real-world data: Similar to the clinical trial, the ground truth for migraine headache days was collected through the Nerivio App from self-reported data.

8. Sample Size for the Training Set

• This device is not an AI/ML algorithm that requires a "training set" in the conventional sense of supervised learning. The device's mechanism of action is electrical neuromodulation, not a learned algorithm.
• The clinical trial mentioned (K223169) is a validation study for the new preventive indication, building upon prior studies (like K203181) for acute treatment. The "training data" for the device's design would effectively be the pre-clinical research and prior clinical studies that informed its development and established its mechanism of action (conditioned pain modulation).

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

• As a hardware medical device with a well-defined physical mechanism, there's no "training set" ground truth in the AI sense. The "ground truth" for the device's development and prior understanding of its mechanism (e.g., conditioned pain modulation) would be based on previous basic science, preclinical studies, and prior clinical trials (such as K203181 which established its acute treatment efficacy). The current submission leverages this existing knowledge and demonstrates expanded efficacy for prevention using a randomized controlled trial. For the extrapolation to adolescents, the "ground truth" relies on the established mechanism of action (CPM) being the same across age groups, supported by real-world evidence collected via the device's app.

Ask a specific question about this device

The Nerivio is indicated for acute treatment of migraine with or without aura in patients 12 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura.

The Nerivio is a wearable, battery-powered device that is controlled by a mobile application. The system delivers low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically. The Nerivio is identical to the previously cleared Nerivio device with a modification to the indications for use to allow treatment in patients aged 12 years and older.

The device is composed of a pair of UltraStim® electrodes (K130987) covered with hydrogel and removable protective film, an electronic circuitry that includes firmware, LED indicator and a power button for activating the device and for wireless connection with Android and iOS mobile platforms and a battery contained in a plastic case situated within thermoplastic elastomers ("TPE") shell. In addition, an armband that is wrapped over the device to secure the Nerivio position on the user's arm is included.

The device is operated and controlled via software that is installed and run on a user's personal mobile device such as a mobile phone or tablet. The device hardware communicates with the mobile application through a Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0- 40mA), to start or stop the stimulation program, and to view device status such as the device's connection state, stimulation duration, remaining number of treatments, and user notifications.

The patient is instructed to adjust the intensity to the strongest stimulation level just below the perceived pain level. Treatments with Nerivio are intended to be self-administered by the user immediately after the onset of migraine headache or aura.

The provided text describes a clinical study for the Nerivio device, indicated for acute treatment of migraine. However, it does not detail acceptance criteria in the typical format of a table with specific metrics and thresholds for a device's performance. Instead, it presents results of clinical endpoints related to safety and efficacy.

Based on the provided text, here's an attempt to structure the information according to your request, inferring acceptance criteria from the reported efficacy outcomes:

1. Table of "Acceptance Criteria" (Inferred from Efficacy Endpoints) and Reported Device Performance

Note: The document does not explicitly state numerical acceptance thresholds. The "acceptance criteria" listed above are derived directly from the endpoints measured in the clinical study, implying that meeting these outcomes was considered sufficient for demonstrating safety and effectiveness for the expanded indication.

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

• Sample Size for Final Analysis Set (Test Set): 39 participants (adolescents aged 12-17 years old) for efficacy endpoints. A total of 45 participants entered the treatment phase, and safety analyses were performed on all 45.
• Number of treated migraine headaches: 159 qualifying migraine headaches.
• Data Provenance: Prospective, open-label, single-arm, multicenter study conducted at 12 sites in the USA.

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

The study involved self-reported pain scores, absence/presence of migraine-associated symptoms, and functional disability recorded by participants using an electronic diary application. The ground truth for headache diagnosis (ICHD-3 criteria for migraine) would have been established by healthcare professionals at the study sites; however, the number and specific qualifications of these professionals are not detailed in the provided text. No independent expert panel was used for establishing individual case ground truth during the treatment phase as data was self-reported.

4. Adjudication Method for the Test Set

No explicit adjudication method (like 2+1 or 3+1 consensus by experts) is described for the patient-reported outcomes that formed the test set. The data was collected directly from participants via electronic diaries. For "missing data" for the primary efficacy endpoint, a worst-case scenario imputation was used, where all treatments with missing pain level data were considered failures.

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

No. This was a single-arm study evaluating the device's effect in adolescents, not a comparative effectiveness study involving human readers assisting AI or comparing human performance with and without AI assistance. The device functions as a direct treatment, not an AI diagnostic aid.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

This question is not applicable in the context of this device. Nerivio is a medical device that delivers electrical stimulation for migraine treatment, not an algorithm, so evaluation of "standalone (algorithm only)" performance is not relevant. The performance evaluated is that of the device in use by humans.

7. The Type of Ground Truth Used

The ground truth for the effectiveness of the device was established based on:

• Patient-reported outcomes: Self-reported pain scores (mild, moderate, severe, none), presence/absence of associated symptoms (nausea, photophobia, phonophobia), and functional disability (via electronic diary).
• Validated questionnaire: Pediatric Migraine Disability Assessment (PedMIDAS) questionnaire for migraine-related disability.
• Safety data: Incidence and characteristics of adverse events reported by participants.

8. The Sample Size for the Training Set

The text does not refer to a "training set" in the context of machine learning, as this is a medical device for treatment, not an AI model. The study described is a clinical investigation to evaluate the device's safety and efficacy in a specific patient population (adolescents), thus acting as a validation study for the expanded indications.

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

Not applicable, as there is no "training set" in the context of an AI model to which this question would apply. The "ground truth" for the device's intended use (migraine treatment) is established through clinical practice guidelines (ICHD-3 criteria for migraine diagnosis) and observed patient responses to treatment.

Ask a specific question about this device

The Nerivio is intended for acute treatment of migraine with or without aura in patients 18 years of age or older. It is a prescription use, self-administered device for use in the home environment at the onset of migraine headache or aura.

The Nerivio is a wearable, battery-powered device that is controlled by a mobile application. The system delivers low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically. The device hardware consists of an armband intended to be worn on a user's upper arm. The armband contains the electronic circuitry and the battery in a plastic storage case as well as two electrodes that are attached to the interior of the armband and placed against the user's skin. The device is operated and controlled via software that is installed and run on a user's personal mobile device such as a mobile phone or tablet. The device hardware communicates with the mobile application through a Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0- 40mA), to start or stop the stimulation program, and to view device status such as the device's connection state, a progress bar for stimulation duration, battery level, and user notifications. The patient is instructed to adjust the intensity to the strongest stimulation level below the perceived pain level. Treatments with Nerivio are intended to be self-administered by the user immediately after the onset of migraine headache or aura.

The provided document describes the Nerivio device and its substantial equivalence to a predicate device (Nerivio Migra), primarily based on clinical studies rather than an AI/ML algorithm's performance. Therefore, many standard AI/ML acceptance criteria and study elements (like training set size, ground truth for training, expert adjudication, MRMC studies, standalone performance with metrics like sensitivity/specificity, or specific effect sizes of AI with human readers) are not present in this document.

However, I can extract the acceptance criteria and performance data related to the clinical studies conducted for device efficacy and safety as described in the provided text. The "acceptance criteria" here refer to the primary efficacy endpoints defined for the clinical trials, which demonstrate the device's effectiveness.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document outlines clinical study endpoints as measures of device performance, which serve as "acceptance criteria" for demonstrating efficacy and safety. The primary endpoint for efficacy was "pain relief at 2 hours post-treatment."

2. Sample size used for the test set and the data provenance

The clinical studies acted as the primary "test set" for validating the device's performance.

• Study 1 Sample Size:
  • 42 patients recruited initially.
  • 38 participants completed at least one treatment in response to a migraine.
  • 296 qualifying migraine headaches treated.
• Study 2 Sample Size:
  • 97 participants completed at least one treatment.
  • 91 participants formed the final analysis set for test treatment.
  • 493 evaluable treatments of qualifying migraine headaches conducted.
• Data Provenance: The document states that Study 2 was conducted at 9 sites in the USA. Study 1 was conducted at 2 sites, but the country of origin is not explicitly stated, although it's within the context of FDA submission, suggesting US or international sites adhering to US standards. Both studies were prospective, open-label, single-arm, multicenter studies.

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

The concept of "experts" establishing ground truth in the traditional sense of medical image analysis (e.g., radiologists) is not applicable here. The ground truth for efficacy was self-reported by the patients using an electronic diary application:

• Pain scores: Self-reported by participants (e.g., severe or moderate pain to mild or none, or mild pain to none).
• Absence/presence of associated migraine symptoms: Self-reported.
• Functional disability: Self-reported.

The diagnostic criteria for chronic migraine (ICHD-3) were applied to select eligible participants, implying medical professionals (neurologists/headache specialists) were involved in patient selection. However, their role wasn't in establishing ground truth for individual treatments but in determining study eligibility.

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

No specific adjudication method (like 2+1 or 3+1 for expert review) is mentioned for the patient-reported outcomes. Given that the data collected was patient self-reported via an electronic diary, it implies direct measurement of patient experience, not subject to expert adjudication of the outcome itself, although clinical staff would have monitored data collection.

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

This is not an AI/ML device, and no MRMC comparative effectiveness study involving human readers or AI assistance was conducted or reported. This device is a direct treatment device, not a diagnostic imaging or AI-assisted diagnostic tool.

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

This is not an AI/ML algorithm. The device, Nerivio, operates as a standalone therapeutic device that patients self-administer. Its "performance" refers to its direct therapeutic effect on migraine symptoms.

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

The "ground truth" for the efficacy studies was primarily patient-reported outcomes data. This includes:

• Self-reported pain levels (e.g., severe, moderate, mild, none).
• Self-reported presence or absence of associated migraine symptoms (nausea, photophobia, phonophobia).
• Self-reported functional ability.

8. The sample size for the training set

The concept of a "training set" in the context of an AI/ML algorithm is not applicable here. The device does not employ an AI/ML model that requires training data. The "training treatment" mentioned in Study 2 (97 participants completed at least one training treatment) refers to an initial treatment session to familiarize participants with the device, not an AI model training phase.

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

Not applicable, as there is no AI/ML training set. The "training treatment" phrase refers to the initial use of the device by patients.

Ask a specific question about this device

The Nerivio Migra is indicated for acute treatment of migraine with or without aura in patients 18 years of age or older who do not have chronic migraine. It is a prescription use, selfadministered device for use in the home environment at the onset of migraine headache or aura.

The Nerivio Migra is a wearable, battery-powered device that is controlled by a mobile application. The system delivers low energy electrical pulses to the upper arm for 45 minutes per treatment, after which the device turns off automatically.

The device hardware consists of an armband intended to be worn on a user's upper arm. The armband contains the electronic circuitry and the battery in a plastic storage case as well as two electrodes that are attached to the interior of the armband and placed against the user's skin.

The device is operated and controlled via software that is installed and run on a user's personal mobile device such as a mobile phone or tablet. The device hardware communicates with the mobile application through a Bluetooth protocol. This mobile application software allows the user to control the stimulation intensity from 0 to 100% (representing intensity levels of 0-40mA), to start or stop the stimulation program, and to view device status such as the device's connection state, a progress bar for stimulation duration, battery level, and user notifications.

The patient is instructed to adjust the intensity to the strongest stimulation level below the perceived pain level. Treatments with Nerivio Migra are intended to be self-administered by the user immediately after the onset of migraine headache or aura.

The basic pulse structure is biphasic, with symmetrical interleaving phases and rectangular shape. The amplitude shift signal alternates between a nominal maximum and a nominal minimum of the amplitude signal. The maximal output current is 40mA. The assumed impedance is 1K ohm +/- 500 ohms.

The provided text describes the regulatory information, device description, non-clinical/bench studies, and clinical study details for the Nerivio Migra device. It does not contain information about a study that specifically proves the device meets acceptance criteria in the formal sense often used for AI/ML medical devices (e.g., target metrics for sensitivity, specificity, or similar performance measures).

Instead, the document details a clinical trial designed to demonstrate the safety and effectiveness of the Nerivio Migra device for its intended use compared to a sham device. The "acceptance criteria" here are implicitly tied to the statistical significance and clinical meaningfulness of the primary and secondary endpoints in this clinical trial, as well as satisfactory results from non-clinical testing.

Based on the provided text, here's a breakdown of the information that aligns with your request, interpreting "acceptance criteria" as the successful demonstration of safety and effectiveness through the described clinical study and non-clinical testing:

Acceptance Criteria and Device Performance (Interpreted from Clinical Trial Endpoints and Non-Clinical Testing)

Ask a specific question about this device