(188 days)
The Epoch 2000 is intended for use in the operating room and critical care areas for neurological monitoring and assessment. The instrument uses EEG, evoked potentials and EMG techniques to provide the health care professionals with information to help access a patient's neurological status during surgery or longterm monitoring in the ICU.
The Epoch 2000 is similar is concept and function to our original product, the Sentinel-4 EEG/EP Intraoperative Monitor (K900482A), a class II device. This instrument is also used to monitor brain function and neurological activity utilizing EEG and multiple modality evoked potential techniques. The additional features incorporated in this product are designed to meet the current and expanding demands of health care professionals for more effective ways to monitor the neurological status of their patients without compromising safety or effectiveness.
The provided documentation describes the Epoch 2000 Neurological Workstation, which is a medical device for neurological monitoring. However, it does not contain specific acceptance criteria, performance metrics, or a dedicated study design that proves the device meets those criteria, as one would expect for an AI-powered device. Instead, it focuses on demonstrating substantial equivalence to predicate devices and adherence to regulatory standards.
Therefore, many of the requested sections (2-9) cannot be filled with direct information from the provided text. I will explain what information is available and then address the rest by stating that the information is not present.
1. A table of acceptance criteria and the reported device performance
The document does not explicitly define quantitative acceptance criteria for device performance based on metrics like sensitivity, specificity, accuracy, or similar. Instead, it relies on demonstrating that the Epoch 2000 has the same intended use and capabilities as legally marketed predicate devices, and that it meets established industry and electrical safety standards.
| Acceptance Criteria Category | Specific Criteria (from document) | Reported Device Performance |
|---|---|---|
| Industry Standards | Meets or exceeds American Electroencephalograph Society Intraoperative Monitoring guidelines for EEG and evoked response devices. | Claimed: "We claim the device to be safe, effective and substantially equivalent to the predicate devices noted." (Implying adherence to guidelines) |
| Electrical Safety | UL544, IEC 601-1, C22.2 No. 125 | Claimed: Adheres to these standards. |
| Functional Equivalence | Performance of "Epoch 2000" equivalent to predicate devices for various monitoring types (listed below). | Claimed equivalent functionality for all types: Cerebral ischemia, changes in EEG due to neuroactive drugs, long term coma, seizure tracking, electrocorticography, somatosensory evoked potentials, motor evoked potentials, auditory evoked potentials, visual evoked potentials, EMG, Direct Nerve stimulation/EMG. |
| Patient Protection | "Touch proof" female safety electrode connectors, Insulated ABS plastic patient enclosures, Optical & transformer isolation, Line isolation transformer, Built-in software & hardware start-up diagnostics, Software & hardware shutdown protection, Zero average DC electrical stimulation, Hi, medium & low average stimulation intensity limited, Peak stimulation intensity limited, Hi level electrical stimulator disconnected on fault, Preamplifier DC fault limited to safe current (30uA). | Claimed to incorporate these features. |
Study to prove acceptance criteria:
The study proving the acceptance criteria is not a "study" in the traditional sense of a performance evaluation with statistical metrics. Instead, it is a declaration of substantial equivalence to existing predicate devices (Axon Systems Sentinel-4, Moberg Medical Neurotrac II, Nicolet Viking IV) and adherence to recognized standards. The "study" here is the review process by the FDA based on the submitted 510(k) notification.
The document claims:
- "Based upon the documentation stated above and the safety and effectiveness criteria of the design and development process, validated by testing and quality control procedures, we claim the device to be safe, effective and substantially equivalent to the predicate devices noted."
- "The Epoch 2000 is similar is concept and function to our original product, the Sentinel-4 EEG/EP Intraoperative Monitor (K900482A), a class II device."
- The FDA's decision states: "We have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to devices marketed in interstate commerce prior to May 28, 1976..."
This implies that the "proof" is based on comparing the features, intended use, and technological characteristics of the Epoch 2000 to the established predicate devices, and ensuring compliance with general controls and relevant standards for safety.
The following points refer to aspects of a performance study, which are not relevant or applicable to the provided document's content. The provided text focuses on substantial equivalence for regulatory clearance, not on a performance study of an AI algorithm.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Information not provided. This document does not describe a performance study with a test set of patient data.
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)
- Information not provided. This document does not describe a performance study that required expert-established ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Information not provided. This document does not describe a performance study with an adjudication method.
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
- Information not provided. This document describes a standalone neurological monitoring device, not an AI-assisted human reading system, and therefore no MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Information not provided in the context of an algorithm's performance. The device itself is a "standalone" monitoring system, but not in the "algorithm-only" sense typically implied by this question for AI products.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Information not provided. No ground truth definition is mentioned as there is no specific performance study outlined. The "ground truth" for regulatory clearance is that the device aligns with the functionality and safety of predicate devices.
8. The sample size for the training set
- Information not provided. This document does not describe an AI training process.
9. How the ground truth for the training set was established
- Information not provided. This document does not describe an AI training process.
§ 882.1870 Evoked response electrical stimulator.
(a)
Identification. An evoked response electrical stimulator is a device used to apply an electrical stimulus to a patient by means of skin electrodes for the purpose of measuring the evoked response.(b)
Classification. Class II (performance standards).