Search Results

Photopic stimuli are presented to the patient on an VGA-screen at a various number of elements in separately stimulated fields. Various modes are available for preferential stimulation of different retinal mechanism and isolation of signal from different retinal layers. Data are required by up to 8 recording channels using conventional EEGelectrodes. During the period of time that the system is aquiring data (1-20 minutes), there is a real time display of the raw and processed data presented to the user. Once the resulting individual waveforms are aquired, the signals are analyzed by software using algorithms for spatial filtering and artifact rejection. Data may be presented in a number of forms, including waves recorded at each of the points tested, color plots, or 3D topographical representation.

AI/ML Overview

The provided 510(k) summary for the RETIscan/RETIport device does not contain a detailed study design with specific acceptance criteria and performance metrics for the device's diagnostic accuracy or effectiveness in the way one might expect for a modern AI/ML device.

Instead, the submission focuses on substantial equivalence to predicate devices through comparisons of intended use, users, indications, population, environment, physiological data collected, and compliance with recognized standards.

Here's an attempt to structure the available information per your requested categories, acknowledging that much of it will be "Not Applicable" or inferential based on the type of submission:

1. Table of Acceptance Criteria and Reported Device Performance

Given the nature of a 510(k) for an existing technology (electrodiagnostic device), the "acceptance criteria" primarily revolve around demonstrating equivalence to predicate devices and meeting safety standards, rather than proving a specific diagnostic accuracy metric.

Acceptance Criteria Category	Specific Criteria/Standard	Reported Device Performance (RETIscan/RETIport)
Intended Use	Generate photic signals & measure/display electrical response from retina/visual nervous system	Yes (Substantially equivalent to predicates)
Intended Users	Ophthalmologists, trained medical technicians & professionals	Yes (Substantially equivalent to predicates)
Indications for Use	Electrophysiological Test Unit for quantifying retinal response, measuring VEP related to retinal response	Yes (Substantially equivalent to predicates)
Intended Population	Patients with ophthalmic conditions	Yes (Substantially equivalent to predicates)
Intended Use Environment	Hospitals, clinics, physician offices	Yes (Substantially equivalent to predicates)
Physiological Data	ERG waveforms, VEP	Yes (Substantially equivalent to predicates)
Electrical Safety	EN60601-1 Standards (IEC601-1-2 for stimulator)	Certificate of compliance received
Stimulator Equivalence	Equivalent stimulation for evoked potential recording (luminance, chromaticity, stimulated visual field size)	All stimulators provide equivalent stimulation for ERG, VEP recording
Patient Safety (Radiation)	Normal visual light radiation, no risk to patient	Level of exposure measured, declared safe
Electromagnetic Compatibility (EMC)	EN 55011: 03.1991	Yes (Substantially equivalent to predicates)

Study Details:

Based on the provided document, the "study" is primarily focused on demonstrating substantial equivalence through a comparison with legally marketed predicate devices and compliance with relevant safety standards. There isn't a "diagnostic performance" study in the sense of accuracy metrics (sensitivity, specificity, AUC) for the device itself.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

Sample Size: Not applicable. The submission does not describe a clinical performance study with a test set of patient data to assess diagnostic accuracy. The "Effectiveness" section refers to the equivalence of the stimulators themselves, not a study involving patient outcomes or diagnoses.
Data Provenance: Not applicable.

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)

Not applicable. As no clinical performance study involving patient data was described for determining diagnostic accuracy, expert-established ground truth for a test set is not mentioned.

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

Not applicable. No clinical performance study requiring adjudication is described.

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 not an AI/ML device, nor is an MRMC study described. The device is an electrodiagnostic tool that provides raw and processed data for interpretation by medical professionals.

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

Not applicable. This device is an electrodiagnostic hardware and software system, not solely an algorithm. Its output (ERG/VEP signals, maps) is specifically noted as being "controlled and interpreted by trained medical professionals."

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

Not applicable in the context of a diagnostic performance study. The "ground truth" implicitly assumed for electrodiagnostic devices is the accurate capture and display of bioelectrical signals, which is indirectly addressed by demonstrating the stimulator's equivalence and compliance with established standards for such devices.

8. The sample size for the training set

Not applicable. There is no mention of a machine learning model requiring a training set in this 510(k) submission.

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

Not applicable. No training set is mentioned.

Ask a Question

Ask a specific question about this device

Page 1 of 1