Search Results

The Milieve is indicated for

• The acute treatment of migraine with or without aura in patients 18 years of age or older.
• The prophylactic treatment of episodic migraine in patients 18 years of age or older.

The Milieve device is a transcutaneous electrical nerve stimulator (TENS) developed for the acute treatment of migraine and the prophylactic treatment of episodic migraine. The device is placed on the patient's forehead to stimulate the upper branch of the trigeminal nerve. It is harmless to the human body. The Milieve device is indicated for OTC use.
There are two treatment programs: ACUTE and PREVENT. The ACUTE treatment program is intended for treatment during migraine attack at the onset of a migraine. The PREVENT treatment program is meant for daily preventative treatment.
The Mileve device comprises a plastic external casing and electrical components. It is operated by an internal rechargeable battery.

The provided text is a 510(k) summary for the Milieve (YPS-301BD) device, a transcutaneous electrical nerve stimulator for migraine treatment. The summary demonstrates substantial equivalence to a predicate device (Cefaly Dual).

The document does not describe a study involving an AI/algorithm where acceptance criteria are set for the performance of the AI model itself. Instead, it focuses on demonstrating the Milieve device's substantial equivalence to a predicate device through bench testing and comparison of technical specifications. The acceptance criteria and "device performance" in this context refer to the physical and electrical characteristics of the Milieve device and how they compare to those of the predicate device.

Therefore, many of the requested points from your prompt (e.g., sample size for test/training sets, number of experts for ground truth, MRMC studies, standalone AI performance) are not applicable to this type of submission, as the Milieve device is a hardware medical device, not an AI/algorithm-based diagnostic or therapeutic system.

However, I can extract and present the relevant information regarding the device's "performance" and how its "acceptance criteria" (understood as equivalency to the predicate) are met based on the provided text.

Acceptance Criteria and Device Performance (Demonstration of Substantial Equivalence)

The acceptance criteria for the Milieve device are implicitly based on demonstrating substantial equivalence to the predicate device, Cefaly Dual. This is achieved by showing that the technological characteristics and performance parameters are either identical or substantially equivalent, and that any differences do not raise new questions of safety and effectiveness.

1. Table of Acceptance Criteria and Reported Device Performance:

The provided table directly compares the Milieve device to the Cefaly Dual (Predicate Device). The "Comparison" column indicates whether the parameters are "Identical" or "Substantially Equivalent (SE)" with notes explaining the implications of the differences.

Notes on Substantial Equivalence:

• Note 1 (Ramp down Time): "The subject device has a slightly longer ramp down time. This longer ramp time helps with subject comfort. This difference will not raise new questions of efficacy as the therapeutic session times (20 min and 60 min) are identical."
• Note 2 (Dimensions): "The dimension of the subject device is slightly different from the predicate device. This minor difference will however not raise any new safety and effectiveness issues."
• Note 3 (Weight): "The weight of the subject device is slightly more than the predicate device. This minor weight increase has not impacted the ability to hold device and electrode reliably on the forehead in the in-house tests conducted and the human factors validation study. It is therefore expected to not raise any new safety and effectiveness issues."

Regarding the AI/Algorithm-specific questions (which are not applicable to this submission):

• 2. Sample size used for the test set and the data provenance: Not applicable. The study was bench testing of a hardware device.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth was established by direct measurement against engineering specifications and comparison to the predicate device.
• 4. Adjudication method for the test set: Not applicable. Performance was assessed via bench testing.
• 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 is a hardware medical device, not an AI-assisted diagnostic tool.
• 6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. The device is a TENS unit, not an algorithm, and its use is intended for direct patient application (OTC).
• 7. The type of ground truth used: For the technical specifications, the ground truth is the performance parameters of the predicate device and established engineering standards. For the human factors validation (mentioned for weight), the ground truth is likely defined by user feedback and ability to use the device as intended.
• 8. The sample size for the training set: Not applicable. No AI model was trained.
• 9. How the ground truth for the training set was established: Not applicable. No AI model was trained.

Summary of the Study Proving Acceptance Criteria:

The study involved bench testing to demonstrate that the Milieve device's performance parameters are "substantially equivalent" to those of the predicate device (Cefaly Dual). Additionally, software verification and validation and risk management were conducted to support this equivalence. A human factors validation study was also mentioned regarding the device's weight, indicating that the slightly increased weight did not negatively impact usability.

The overarching "acceptance criteria" here is the demonstration of substantial equivalence to a legally marketed predicate device, as per 510(k) requirements. The study successfully met these criteria by showing identical or non-concerning, explained differences in all critical parameters.

Ask a specific question about this device

MEGA-IOM system with Neuro-IOM.NET software is a medical device intended for intraoperative neurophysiologic monitoring: the device provides information to assess a patient's neurophysiological status.

The system allows to monitor the functional integrity and/or mapping of central and peripheral nervous system including motor and sensory pathways.

It is provided in three different configurations:

I. 32/B

II. 32/S

III. 16/S

The system ensures the following IOM modalities: free-run EMG (electromyography), direct nerve stimulation including pedicle screw test, SSEP (somatosensory evoked potential), MEP (motor evoked potential), EEG (electroencephalography), AEP (auditory evoked potential), VEP (visual evoked potentials), direct cortical stimulation. Also the train-of-four (TOF) stimulation is performed.

The system is not intended to measure vital signs. It records the data to be interpreted by the neuromonitoring specialist.

MEGA-IOM system is intended for use in adults age 18 years and older.

The MEGA-IOM system with Neuro-IOM.NET software is intended for intraoperative neurophysiological monitoring (IOM).

The system is intended for monitoring the functional integrity and/ or mapping of central and peripheral nervous system including motor and sensory pathways.

Soterix Medical is assuming manufacturing of the predicate product cleared in K190703. This 510(k) submission includes the same hardware cleared with the predicate device system (no changes) and an updated version of the software compared to the predicate device.

Below, a high-level summary of the changes from the predicate are provided:

Software: The primary changes in this 510(k) submission are related to the software. The changes are troubleshooting updates for greater usability such as user interfaces and bug fixes. Detailed descriptions of these software changes per version are provided below:

Version 1.1.52.7: Fixes related to the stimulation stop after a few hours, adding a stimuli limit for double train stimulation, allowing pulse duration (200 microseconds) entry, masking noise limitation per IEC 60601-2-40 (Particular requirements for the basic safety and essential performance of electromyographs and evoked response equipment), reporting correct status of multichannel operation, prevent skipping of traces, and check for incompatible stimulation parameter entry.

Version 1.1.52.8: Fixes related to facilitating quick turning off stimulation, real-time stimulus change control, scrolling in spectral setup window, constraining window within pattern printout to screen, ensuring modality window description is unchanged, incorrect Ch 17 display in emulation mode, video filters error during installation, ensuring all text is displayed within visibility area, incorrect auditory evoked potentials (EPs) average calculation in emulation mode.

Version 1.1.52.9: Fixes related to exam saved message, flexibility to change test template sequence, sleep mode prevention, rendering speed, interpulse interval display correction, allowing comments in the event window, automatic creation of user template, template list update, impedance measurement window rendering, parameter display correction in EMG trigger window and Group mode, ensuring non-disappearance of red line around patient's birth date, enabling stimulation via local menu in Scoliosis test template, frame switching error during video recording, displaying correct device status.

Version 1.1.53.7: Fixes related to addition of video clip creation button, accidental stimulation activation protection, display of preliminary train in double train mode, voltage and charge value display in stimulation panel, allowing repetitive stimulation in Double Train and Train+Pulse modes, option to view amplitude values up to 10 microA, option to select scales in X axis, option to delay auto saving if stimulation in progress, option to titrate stimulation amplitude using mouse wheel, option to select grid type, confirmation on layout uninstallation, addition of the Pause button in Stimulation programs, option to select motor response search interval and displaying the motor response search interval, addition of measured impedance visualization, offering first the windows already available when adding a new window, preventing closure of window if input row is active in derivation test, enable display of additional TOF parameters, option to playback trace fragments, addition of Take a screenshot command, parameter trend export, pulse duration interval display in TES train, option to enter multiple-line comments, option to re-name layout, option to hide command list, ability to save only responses beyond a certain level, stimulator list scrolling, RMS noise value display, test template cloning, motor response onset marker, previous recorded traces display, layouts during new test reset, stimulator reminder mod, video file duration based on frame rate, saving of the number of traces, test template rewriting, group trace visualization display, layout switching, stimulation resumption post coagulator off, video playback if another program is run.

Version 1.1.53.8: Fixes related to allowing multiple image view within the image window, allowing EEG artifact recording, showing baseline in the Overlay mode, option to disable program, option to save screen shots to a specific folder, stimulation program panel addition, correction of autoincrement window bug, correction of DSA rendering.

Version 1.1.53.9: Fixes related to custom scale adjustment in Freerun window, randomly changing pulse intervals in multichannel mode, event trace copy to report, layout panel updating post deletion, sound, threshold, and color parameter display during new site addition, EMG channels in template during long-term monitoring, site visibility during stimulation in presence of temporary markers, auto sweep resets, temporary markers display, trace export to EDF, layout non-save post video window opening, type conversion in trace window.

Version 1.53.10: Fixes related to video window copying over to report, trace scale reset, appearance of average trace display in case of no averages due to artifacts, site name display in TOF window, saving of initial study state in autosave mode, incomplete installation of video components, volume increment of auditory stimulator signal volume.

Version 1.1.53.11: Fixes related to active probe switch-off during monitoring, limiting maximum increment adjustment of electrical stimulation amplitude to 1 mA and 5V, stimulus duration set-up when stimulation amplitude is increased, stimulation disablement after power supply resume, stimulus sound notification, text visualization in dialogue box, non-active stimulator panel, maximum stimulus artifact width display, minimum and maximum MEP trace markers.

Version 1.1.53.12: Fixes related to pulse width change during stimulation in multichannel mode, MS Office word report, TeamViewer, logo, and translation corrections.

Version 1.1.53.13: Fixes related to removal of sites containing TOF and logo change.

Version 1.1.53.14: Fixes related to start monitoring during video camera switch off, video recording in some interface languages, sound disablement during impedance measurement, printing test template, USB driver-related Windows 10 OS bugs.

In summary, the aforementioned software changes are related to resolving software bugs and increasing user convenience, but the changes do not impact the intended use, indications for use statement, contraindications, or warnings. They also don't increase the likelihood that the device will be used by a broader or different group of users and do not raise any new risks.

Labeling: Modifications have been made to labeling and these changes are related to the new device trade name and change in manufacturer. Instances of "Neuro-IOM" were changed to "MEGA-IOM" in the user manual and on the device labels. Soterix Medical is named the manufacturer and point of contact in the labeling including for all complaints and service requests.

Waveforms: The MEGA-IOM system has the same waveforms as the predicate device. No change to the waveforms.

The provided text is a 510(k) Premarket Notification from the FDA for the "MEGA-IOM system with Neuro-IOM.NET software". This document primarily focuses on demonstrating substantial equivalence to a predicate device (K190703 Neuro-IOM system with Neuro-IOM.NET software) rather than detailing extensive clinical studies with acceptance criteria for new device performance.

The submission is for a device that has primarily undergone software updates and a change in manufacturer. Therefore, the "study that proves the device meets the acceptance criteria" is in the form of software verification and validation, and comparison to the predicate device's established performance.

Here's an analysis based on the provided text:

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

The document doesn't provide explicit "acceptance criteria" in the traditional sense of a clinical trial (e.g., target sensitivity/specificity for a diagnostic AI). Instead, the acceptance criteria are implicitly demonstrating that the updated software, in conjunction with the unchanged hardware, performs identically or equivalently to the predicate device. The performance is assessed by confirming that all functional and technical specifications remain the same.

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

The document states that the changes are primarily software-related (bug fixes, usability improvements) and do not impact the device's fundamental performance characteristic or intended use. Therefore, instead of a clinical "test set" with patient data in the typical sense for AI/diagnostic devices, the "testing" described is focused on software verification and validation.

• Sample size for test set: Not applicable in the sense of clinical cases or patient samples. The "test set" consists of software functionalities and user interface elements.
• Data provenance: Not directly applicable to patient data. The provenance relates to the software development process and testing environment. It is internal software validation data.
• Retrospective or prospective: Not applicable to patient data. Software verification and validation are typically performed prospectively during development and after changes.

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

This is not applicable as the "ground truth" for this submission is the established, cleared performance of the predicate device. The changes are bug fixes and usability enhancements, not a new diagnostic algorithm requiring expert-established ground truth. The "experts" would be the software developers and quality assurance personnel performing the verification and validation, ensuring the software performs as designed and intended, consistently with the predicate's established functions.

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

Not applicable. Software verification and validation follow structured testing protocols (e.g., unit testing, integration testing, system testing, regression testing) and risk management processes. There is no "adjudication" in the sense of reconciling clinical interpretations.

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. This submission is not for a new AI/CAD device requiring an MRMC study. It is for an established device platform with software updates. The device itself is an "Evoked Response Electrical Stimulator" and "Intraoperative Neurophysiologic System" that records data for interpretation by a neuromonitoring specialist; it does not explicitly feature AI assistance for interpretation that would necessitate an MRMC study.

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

Not applicable. This device is an instrumentation system for intraoperative neuromonitoring, where the data is recorded to be interpreted by the neuromonitoring specialist. It is inherently a human-in-the-loop system. The software updates are "troubleshooting updates for greater usability such as user interfaces and bug fixes."

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

The "ground truth" for this submission is the documented and previously cleared performance of the predicate device. The new device demonstrates substantial equivalence by showing that its software updates do not alter the fundamental safety or effectiveness of the system, which is achieved by confirming that hardware specifications remain identical, and software functions operate as expected (i.e., fixing bugs, improving usability) without introducing new risks or changing the device's core output.

8. The sample size for the training set:

Not applicable. This device is not an AI/machine learning device that requires a "training set" in the context of learned algorithms. The "software updates" are bug fixes and usability improvements to a traditional software application, not a learning algorithm.

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

Not applicable, as there is no "training set" in the context of machine learning. The "ground truth" for the software's correct operation is defined by its functional requirements and the established performance of the predicate device.

Ask a specific question about this device

Stimulation of peripheral nerves for diagnostic purposes.

The MEGA-TMS is intended for stimulation of peripheral nerves for diagnostic purposes. The device introduces electrical stimulation to tissue through magnetic induction generated from the coil. The obtained responses of stimulated structures is recorded with an EMG system for further diagnostic evaluation. The MEGA-TMS device is intended to be paired with a Focus EMG device cleared under FDA 510(k): K102610. Magnetic stimulation is used for peripheral nerve conduction studies and to evaluate peripheral nervous system.

The provided text is a 510(k) summary for the MEGA-TMS device, which is an evoked response electrical stimulator used for diagnostic purposes. It primarily focuses on demonstrating substantial equivalence to predicate devices and does not describe a study to establish acceptance criteria for an AI/CADe device's performance.

Therefore, I cannot extract the requested information regarding AI/CADe acceptance criteria or the study proving a device meets them. The document mentions performance testing, but this refers to safety, EMC, design verification, and risk management for the electrical stimulator, not an AI or CADe system.

The closest relevant information, though not directly applicable to an AI device's performance, is under "Electric and Magnetic Field Characteristics," where measurements and simulations were performed for electric and magnetic fields. However, this pertains to the physical and electrical characteristics of the stimulator itself, not the diagnostic performance of an AI.

To directly answer your request based on the provided text, the document does not contain the specific information you are looking for regarding acceptance criteria and a study proving an AI/CADe device meets those criteria.

Ask a specific question about this device

The Neural Navigator is a neuronavigation system indicated for accurate positioning of the treatment coil of the CloudTMS Therapy System with respect to target brain regions based on data obtained from MRI measurements. Specifically, the Neural Navigator is indicated for use with the following CloudTMS Therapy System coils manufactured by Neurosoft Ltd: AFEC-02-100 and AFEC-02-100-C.

The Neural Navigator combines MRI-based, 3-D localization of cortical motor areas of the brain with non-invasive TMS and simultaneous EMG measurement to locate areas of the brain that are capable of evoking muscle responses when stimulated, and to locate the target area for depression therapy. The Neural Navigator software is used to import a patient's MR image slices through standard DICOM communication protocols, and automatically generates an accurate 3-D model of the patient's head, and a custom automatic tissue segmentation routine to reveal anatomical structures of the brain surface in 3D.

The provided text describes the 510(k) premarket notification for the Neural Navigator device. While it asserts substantial equivalence based on performance testing, it does not explicitly define "acceptance criteria" in a quantitative table with specific thresholds as would be typical for a detailed study report. However, it implicitly presents performance metrics and their comparison to predicate devices, which serve as the basis for acceptance.

Here's an attempt to extract and rephrase the information to fit the requested format, acknowledging the limitations of the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present explicit acceptance criteria with defined pass/fail thresholds. Instead, it compares the Neural Navigator's performance to its predicate devices, implying that performance comparable to or better than the predicate is considered acceptable.

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

• Clinical Study for Coil Compatibility Validation and System Accuracy: 10 healthy volunteers.
• Data Provenance: The document does not specify the country of origin for the clinical study data or if it was retrospective or prospective. Given it is a 510(k) submission, it is likely prospective testing specifically for this submission.
• Monte Carlo Simulations: 10,000 runs for both mapping algorithm and ensuing navigation. The provenance for this is computational simulation.

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

The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth. The clinical study involved "MEP mapping," which typically involves expert neurophysiology interpretation. However, details on the adjudicators or their qualifications are not provided.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for the clinical test set. The ground truth seems to be implicitly derived from the MEP mapping procedure itself, which is a physiological measurement, rather than subjective interpretation requiring multiple readings.

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

No, an MRMC comparative effectiveness study with human readers assisting AI versus without AI assistance was not performed or reported. This device is a neuronavigation system for coil placement, not an AI-assisted diagnostic imaging tool where such a study would typically be conducted. The study is focused on the accuracy of the navigation system itself.

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

Yes, the document reports on elements of standalone performance:

• Tracking System Accuracy: Tested independently by NDI (the tracking system manufacturer).
• System Accuracy (simulations): 10,000 Monte Carlo simulations were run, representing an algorithm-only evaluation of accuracy under various noise conditions.
• Clinical Study: While it involves humans (volunteers), the focus is on the accuracy of the device's navigation in placing the TMS coil, which is a direct measure of the algorithm's performance in guiding coil placement, rather than human interpretation aided by the algorithm. The "human-in-the-loop" is the operator using the device, but the performance metric is the device's ability to accurately guide.

7. The Type of Ground Truth Used

• System Accuracy (Clinical Study): The ground truth for the clinical study measuring system accuracy via MEP mapping is based on a physiological response (Motor Evoked Potentials - MEPs). The assumption is that successful MEPs indicate accurate targeting of the motor cortex.
• Tracking System Accuracy: Ground truth is established by the independent testing of the tracking system by its manufacturer, likely using known spatial measurements.
• System Accuracy (Simulations): Ground truth is an ideal or expected outcome defined within the simulation model.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set size or methodology. This type of device, which is based on established physics and medical imaging principles (e.g., MRI-based 3D localization, tissue segmentation), may not involve a "training set" in the sense of a machine learning model where data is used to optimize algorithms. The algorithms are likely engineered based on physiological and anatomical models.

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

As no "training set" is mentioned for a machine learning context, the method for establishing its ground truth is not applicable or described in the provided text. The foundational principles and calibrations for the device's operations (e.g., MRI space to patient space registration, calibrated electric field maximum) are inherent to its design and validated through the performance tests mentioned above.

Ask a specific question about this device