Search Results

The Resolve Fundus Camera is an automatic eye-fundus camera intended for taking digital images of a human retina with or without the use of a mydriatic agent. It is intended for use as an aid to clinicians in the evaluation and diagnosis of ocular health.

The Resolve Fundus Camera is a fundus camera designed to perform fundus observation, automatic pupil tracking and focusing, automatic image capture, and image preservation. The Resolve Fundus Camera is used for non-mydriatic observation and capturing of retinal images. The fundus camera employes three internal imaging systems to operate: illumination system, imaging system and observation system. Auto-alignment and auto-focus algorithms are used to automatically find and capture desired images of the fundus.

The fundus camera features an internal, movable three-dimensional platform that allows for switching and precise positioning of the left and right eyes. The imaging process is done one eye at a time (left eye and then the right eye). The internal, moveable three-dimensional platform contains two types of cameras: a set of infrared cameras (one on each side) as well as one main camera.

The observation system is used to detect and track the patient's pupil. Next, the illumination system determines the precise location of the ocular fundus after the pupil is located by the observation system. The system precisely finds the relationship between the position of the ocular fundus at different diopters, and the lens of the main camera.

Once the location of the fundus is found, a charge-coupled device (CCD) automatically captures a still image of the fundus through the main camera. The autofocus system utilizes a beam splitter to split a beam of light into two fine beams, which then image the ocular fundus onto the CCD. When the focus is at its sharpest position, the split beams align horizontally. At this point, the LED white light illumination system, installed in the imaging module on the three-dimensional movable platform, emits uniform white light of appropriate intensity to illuminate the ocular fundus. The imaging system captures the fundus information onto the CCD, and the received signals are displayed in real-time on a liquid crystal display (LCD) through the control system. Doctors can visually assess the patient's ocular fundus on the LCD screen.

The provided FDA 510(k) clearance letter for the Optain Health Resolve Fundus Camera focuses primarily on establishing substantial equivalence to a predicate device (Next Sight Srl Nexy). For this type of device (an ophthalmic camera), the clearance process in this document does not necessitate a detailed clinical study for performance evaluation that would typically involve acceptance criteria for diagnostic accuracy (e.g., sensitivity, specificity) of an AI algorithm. Instead, the performance data presented is focused on demonstrating that the device meets safety and basic functional standards, similar to the predicate device.

Therefore, many of the requested points regarding AI algorithm performance (like specific acceptance criteria for diagnostic accuracy, sample sizes for test sets, expert adjudication methods, MRMC studies, standalone performance, and ground truth establishment for training/test sets) are not explicitly described or required for this particular regulatory submission type, given the device's classification and stated indications for use. The device's indication is for "taking digital images" and "aid to clinicians in the evaluation and diagnosis of ocular health," implying that the device primarily performs an imaging function, and any "diagnosis" is still ultimately made by the human clinician using the image.

Below is an attempt to answer the questions based only on the provided text. Where information is not available, it will be stated as such.

Device: Optain Health Resolve Fundus Camera

Indications for Use: The Resolve Fundus Camera is an automatic eye-fundus camera intended for taking digital images of a human retina with or without the use of a mydriatic agent. It is intended for use as an aid to clinicians in the evaluation and diagnosis of ocular health.

Acceptance Criteria and Reported Device Performance

The document describes the device's performance in terms of compliance with recognized consensus standards rather than diagnostic performance metrics (e.g., sensitivity, specificity, accuracy) for an AI algorithm. The acceptance criteria are implicit in meeting the requirements of these standards.

1. Table of Acceptance Criteria and Reported Device Performance:

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

• The document states "Non-clinical testing was performed," and "Performance testing" but does not specify a "test set" in the context of a dataset for evaluating an AI algorithm's diagnostic performance.
• The tests are primarily related to general device safety, function, and image quality standards compliance, not the diagnostic accuracy of an AI.
• Data Provenance: Not specified, but likely laboratory or engineering test data, not patient data from a specific country or retrospective/prospective study.

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

• Not applicable/Not specified in the provided document, as no specific diagnostic ground truth for an AI algorithm's performance is described. The device's function is to aid clinicians, not to output a diagnosis via AI.

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

• Not applicable/Not specified, for the same reasons as above.

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 MRMC study is described in this 510(k) summary. The device's clearance is based on substantial equivalence to a predicate ophthalmic camera, not on a claim of AI-assisted diagnostic improvement.

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

• No standalone AI performance study is described. The device is an "automatic eye-fundus camera" which "aids clinicians." There is no mention of an AI algorithm producing a diagnostic output independently of a human.

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

• Not applicable/Not specified, as the performance evaluation is focused on device functionality and safety standards, not diagnostic accuracy against a clinical ground truth.

8. The sample size for the training set:

• Not applicable/Not specified. The document does not describe a training set for an AI algorithm. If there are "auto-alignment and auto-focus algorithms," these might involve machine learning, but the document does not detail their training data or performance evaluation beyond general "software verification and validation."

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

• Not applicable/Not specified, for the same reasons as above.

Ask a specific question about this device