K Number
K110376
Manufacturer
Date Cleared
2011-07-29

(170 days)

Product Code
Regulation Number
882.1400
Panel
NE
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

EEG- 1200A Series Neurofax is intended to record, measure and display cerebral and extracerebral activity for EEG and Sleep Studies. These data may be used by the clinician in Sleep Disorder, Epilepsies and other related disorders as an aid in diagnosis.

The PE-210AK Switch Box is an optional accessory for the EEG-1200A device. It is used with the EEG-1200A to switch between EEG recording and cortical stimulation using the same cortical electrode. The software is used for functional brain mapping to support diagnostic and surgical epilepsy procedures.

The device is intended for use within a hospital or medical facility under direct supervision of a medical professional

Device Description

The PE-210A Switch Box is an optional accessory for the EEG-1200A device cleared under 510k # K080546. The PE-210AK Hardware is made up of electronic switches inside a box enclosure and cable connections on the outside of the box enclosure. The PE210AK Hardware switch box does not have any controls or adjustment for the operator. All settings, controls, and adjustments are made using the PE-210AK software installed on the EEG's (off the shelf) PC. Utilizing the EEG's CPU. Data storage, keyboard, mouse, and display, the PE-210AK switch box software allows the user switch electrode stimulation sites between the EEG recording and the cortical stimulator. The PE-210AK software allows the user to query the data recorded on the EEG's PC and create a report of the stimulation sites, including duration and intensity settings.

AI/ML Overview

The Nihon Kohden PE-210AK Switch Box for EEG-. 1200A is an accessory that facilitates switching electrodes between an electroencephalograph (EEG) and a cortical stimulator, primarily for functional brain mapping in the context of diagnostic and surgical epilepsy procedures. The 510(k) submission K110376 does not explicitly detail acceptance criteria in a quantitative manner as would be expected for a diagnostic or AI-powered device. Instead, the "acceptance criteria" are implied by the demonstration of substantial equivalence to a predicate device, the Excel Tech EMU 128s Switch Matrix (K040360), and verified through design validation and various testing procedures.

The provided document describes the device's functional capabilities and compares them to the predicate device to establish substantial equivalence. The "study" proving the device meets these criteria is a design validation that confirmed the operation of the software and hardware according to design specifications, along with electromagnetic, environmental, safety, and performance testing. However, there is no information provided about a clinical study involving human subjects, diagnostic accuracy metrics (e.g., sensitivity, specificity, AUC), or a comparison against a defined ground truth for specific clinical outcomes.

Here's an attempt to structure the information based on your request, understanding that the given document focuses on functional equivalence rather than quantitative performance metrics for diagnostic accuracy.


Acceptance Criteria and Device Performance

Acceptance Criteria (Implied from Substantial Equivalence and Design Validation)Reported Device Performance
Functional Equivalence to Predicate Device:Met: The PE-210AK Switch Box performs the core functions of switching electrode output from a stimulation unit to EEG electrodes connected to the patient and EEG instrument, similar to the Excel Tech EMU 128s Switch Matrix.
- Software Capabilities (e.g., electrode arrangement, stimulation site selection, data display, report generation)- Met: The software allows electrodes to be arranged on a brain map, selection of STIM SITE (+) and STIM REF (-) electrodes, display of selected electrode names, and creation/saving/printing of functional mapping reports and stimulation event tables. Minor differences (e.g., zoom feature, display of current values) were noted as not impacting safety or effectiveness.
- Hardware Characteristics (e.g., electronic switch, trigger out)- Met: The device utilizes an electronic switch and provides trigger out for external stimulator, consistent with the predicate.
Operational Conformance to Design Specifications:Met: Design validation confirmed the operation of both software and hardware in accordance with design specifications.
Safety and Effectiveness:Met: Electromagnetic, environmental, safety, and performance testing procedures were conducted, and these tests "verified the proper operation of the device." The manufacturer asserts that features differing from the predicate (e.g., zoom feature, check-up program for switch/trigger signals) have "no impact on patient safety or effectiveness of device." The device is non-sterile and does not contact patients.
Intended Use Fulfillment:Met: The device is used with the EEG-1200A to switch between EEG recording and cortical stimulation using the same cortical electrode, and its software supports functional brain mapping for diagnostic and surgical epilepsy procedures, as intended.

Study Details Proving Acceptance Criteria

The provided 510(k) summary does not detail a clinical study with human subjects, diagnostic performance metrics, or specific quantitative acceptance criteria that would typically be associated with an AI or diagnostic device. Instead, the "study" is a collection of engineering tests and a comparison to a predicate device to establish substantial equivalence.

Here's an analysis based on the available information:

  1. Sample size used for the test set and the data provenance: This information is not provided. The document states "Design validation confirmed the operation of the software and hardware of the device is in accordance to the design specifications" and "The device was subjected to electromagnetic, environmental, safety and performance testing procedures. These test verified the proper operation of the device." These are internal engineering and verification tests, not typically clinical trials with defined test sets of patient data.

  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This information is not provided. As the "study" described is a design validation and technical testing, there's no mention of expert-established ground truth in the context of clinical accuracy or a diagnostic outcome.

  3. Adjudication method (e.g., 2+1, 3+1, none) for the test set: This information is not applicable/not provided. There is no indication of a clinical test set requiring adjudication of findings.

  4. 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 information is not applicable/not provided. The Nihon Kohden PE-210AK Switch Box is an accessory for switching electrodes and assisting with functional brain mapping, not an AI-powered diagnostic tool that directly interprets data or assists human readers in a diagnostic task in a way that would warrant an MRMC study comparing AI-assisted vs. non-assisted performance.

  5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: This information is not applicable/not provided. The device is an accessory controlled by software and is intended for use by medical professionals; it does not operate as a standalone algorithm without human interaction or supervision.

  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): This information is not provided/not explicitly defined in a clinical context. For the design validation, the "ground truth" would be the engineering and functional specifications that the device's hardware and software were designed to meet. The verification tests confirmed conformance to these specifications.

  7. The sample size for the training set: This information is not applicable/not provided. The device is not an AI/ML-based system that requires a "training set" of data in the conventional sense. Its software performs control and display functions based on predefined logic and parameters, rather than learning from data.

  8. How the ground truth for the training set was established: This information is not applicable/not provided for the same reasons as point 7.

§ 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).