(276 days)
The Mitsar-EEG is intended to acquire, display and store the electrical activity of a patient's brain obtained by placing two or more electrodes on the head to aid in diagnosis.
The device Mitsar-EEG is intended to acquire, display and store the electrical activity of a patient's brain obtained by placing two or more electrodes on the head to aid in diagnosis.
The medical device "Mitsar EEG" consists of biosignal amplifier, USB cable, USB dongle and software.
The USB cable is part of the device. It is a standard USB-cable, substantially equivalent to the legally marketed predicates.
The USB dongle is also part of the device. It is a standard security token to authenticate software.
The software is supplied by means of information media and intended for device functioning.
The medical system includes "Mitsar EEG" device and computer (stationary PC with uninterruptible power supply (UPS) or laptop with internal battery). The system may include a medical cart and isolation transformer.
The device does not come in direct contact with patients. Accessories that contact patients, such as electrodes and cap-type electrodes, are the same as used with the legally marketed devices or are comprised of the same components materials as legally marketed accessories. Electrodes and cap-type electrodes are not supplied together with the Mitsar-EEG.
The device is intended for use in functional diagnostics wards and departments at out-patient clinics, hospitals, health research institutes, health centers and other medical institutions. Also, investigations can be performed outside of healthcare facilities, as long as they are led by qualified medical personnel.
The device does not draw any diagnostic conclusion. Recorded data is intended for use as an aid to diagnosis only. No medication or treatment is applied based on this data only. The results have to be considered only in conjunction with other clinical findings.
The device is not sterile. The device is intended for use by qualified medical personnel only and qualifies for exemption per 21 CFR 801 Subpart D «Prescription devices».
Required Components
- EEG amplifier
- USB-cable
- USB dongle
- EEG Studio software
- User manuals
The provided text details a 510(k) summary for the Mitsar-EEG device. However, it does not contain information about acceptance criteria for device performance studies, nor does it describe a study proving the device meets such criteria in the way typically found for AI/radiology devices.
Instead, this document focuses on demonstrating substantial equivalence to predicate devices through comparisons of technological characteristics, electrical safety, EMC, and software validation. It explicitly states that clinical studies were not required.
Therefore, I cannot fulfill your request for detailed information about acceptance criteria, reported performance, sample sizes, expert qualifications, or adjudication methods related to a clinical performance study using an AI device. The document does not describe such a study.
Here's what I can extract from the provided text regarding device validation:
-
1. A table of acceptance criteria and the reported device performance:
- Acceptance Criteria: Not explicitly stated in terms of performance metrics like sensitivity, specificity, accuracy, or F1 score against a defined ground truth for a diagnostic task. The criteria are implicitly tied to demonstrating equivalence to predicate devices and meeting safety standards.
- Reported Device Performance: The performance is discussed in terms of technical specifications and safety compliance, rather than clinical efficacy metrics.
- Channels: Fewer EEG-channels than predicate devices, but deemed sufficient as it meets the American Clinical Neurophysiology Society (ACNS) Guideline 1 for 10-20 System electrode placement (21 electrodes).
- Frequency Band: 0.16 - 70 Hz. This is same as Cadwell Easy II and sufficient for EEG registration, though narrower than NicoletOne System V32 (0.053 - 500 Hz).
- Input Impedance: Greater than predicate devices, indicating less distortion in measured signal.
- Noise: Lower than predicate devices, suggesting better recording quality.
- Offset Tolerance: Greater than predicates, allowing use at high electrode polarization.
- Safety Class: Class II, equal to primary predicate.
- Sterility, Calibration Signal, LED Impedance Indicators, Touch Proof Connectors: Same as predicate devices.
-
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
- N/A. No clinical test set or data provenance is mentioned as clinical studies were not required.
-
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):
- N/A. No ground truth establishment by experts for a test set is mentioned.
-
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- N/A. No adjudication method for a test set is mentioned.
-
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. No MRMC study was done, nor any study involving human readers or AI assistance in diagnostic interpretation. The device is an electroencephalograph, a data acquisition and display tool, not an AI for interpretation.
-
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The device itself is a standalone EEG acquisition system. Its performance evaluation focuses on its technical specifications and compliance with electrical safety and EMC standards, not on an algorithm's diagnostic performance. "Software Verification and Validation Testing" was conducted following FDA guidance, but this pertains to the software's functionality and reliability, not its diagnostic accuracy in a clinical context.
-
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- N/A. No ground truth for clinical diagnostic accuracy was established or used, as clinical studies were not required. The "truth" in this context revolves around meeting engineering specifications and safety standards.
-
8. The sample size for the training set:
- N/A. Not applicable, as this is for an EEG acquisition device, not an AI algorithm requiring a training set for diagnostic tasks.
-
9. How the ground truth for the training set was established:
- N/A. Not applicable.
In summary, the provided document explicitly states that clinical studies were not required to demonstrate the substantial equivalence of the Mitsar-EEG device. The "performance data" refers to technical specifications, electrical safety, electromagnetic compatibility, and software verification/validation, all aimed at showing the device is safe and effective as an EEG acquisition system and comparable to legally marketed predicate devices.
§ 882.1400 Electroencephalograph.
(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).