(204 days)
The Foresce Home is intended for use in the detection and characterization of central and paracentral metamorphopsia (visual distortion) in patients with age-related macular degeneration, as an aid in monitoring progression of disease factors causing metamorphopsia including but not limited to choroidal neovascularization (CNV). It is intended to be used at home for patients with stable fixation.
The Foresee Home system is an interactive software driven device that provides a series of linear images to the macular and peri-macular region of the eye. The changes in macular and near macular function can be quantified by the device thus enabling the reader to detect early changes in macular degeneration and associated diseases to allow earlier intervention.
The Foresee Home applies the concept of the static and automated perimeter in the detection of visual field defects. The technology, based on hyperacuity, is used for highly specific quantification of central and paracentral visual fields defects. Hyperacuity (also termed "Vernier acuity") is defined as the ability to perceive a difference in the relative spatial localization of two or more visual stimuli. Hyperacuity threshold may be as low as 3-6 sec of arc and the hyperacuity stimuli are highly resistant to retinal image degradation and thus suitable for assessing retinal function in patients with opaque media as well. Retinal pigment epithelium (RPE) elevation, such as that which occurs in AMD, causes a shift in the regular position of photoreceptors. It is hypothesized that such a shift causes an object to be perceived at a different location from its true location in space.
The analysis engine of the device tries to define areas in the visual field that are suspected as being related to CNV. Such areas are called CNV related zones. Although these zones are called 'CNV-related,' they simply indicate areas of greater metamorphopsia and can often occur in non-CNV lesions."
Note that the response on this indicator is only indicative of the presence or absence of significant metamorphopsia that may exist in conditions NOT associated with CNV (such as geographic atrophy or drusen).
The Foresee Home is intended to be used in a home environment following training given by a qualified healthcare professional. The user interface and interaction with the device is similar to office Preview PHP. The results of each testing session, the test reports, similar to these generated by the Preview PHP system, will be transmitted electronically directly to the healthcare professional. Test reports will not be displayed on the monitor in the patient's home, but rather will be used by the healthcare professional in the same fashion as it is currently employed with the in-office Preview PHP. Thus, the only difference between the Preview PHP system and the Foresee Home is that the Foresee Home unit is placed in the patient's home environment to facilitate testing and the test report is then transmitted to the healthcare professional.
It should be noted that the Foresee Home is not intended to provide automated interpretation, evaluation, treatment decisions, or to be used as a substitute for professional healthcare judgment.
Here's a breakdown of the acceptance criteria and study information for the Foresee Home™ device, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Minimal percent positive agreement > 80% with gold standard | 81.5% |
| Minimal percent negative agreement > 80% with gold standard | 87.7% |
| Capability of users to perform the test by themselves after clinic training | 98.5% |
| Correlation between unsupervised home simulated environment tests and supervised clinic tests | 93.85% |
Study Details
2. Sample Sizes and Data Provenance
The provided document refers to a clinical study submitted in K050350 for the Preview PHP (the predicate device) to validate the positive and negative agreement. However, the specific sample size for this test set is not explicitly stated in the provided text.
Regarding data provenance, the document does not specify the country of origin. The study for Preview PHP was likely retrospective or prospective, but this detail is not provided. The usability study for Foresee Home™ and the comparison between unsupervised and supervised tests were likely prospective, given their nature of evaluating user capability and test correlation, but this isn't explicitly stated.
3. Number of Experts and Qualifications for Ground Truth (Test Set)
The document states that the Preview PHP results were compared to "gold standards, i.e., color fundus photographs and fluorescein angiographics." It does not specify the number of experts used to establish the ground truth from these images, nor their specific qualifications (e.g., "radiologist with 10 years of experience").
4. Adjudication Method (Test Set)
The adjudication method used to establish the ground truth for the test set is not described in the provided text.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being done. The document does not discuss the effect size of how much human readers improve with AI vs. without AI assistance, as the device is primarily for home monitoring and subsequent review by a healthcare professional, not for direct AI-assisted reading in real-time by a human.
6. Standalone Performance Study
A standalone performance study (algorithm only without human-in-the-loop performance) was effectively done as part of the predicate device's (Preview PHP) validation. The document states: "The clinical study submitted in K050350 for the Preview PHP was designed to validate that that the minimal percent positive agreement and minimal percent negative agreement are greater than 80%." This implies an evaluation of the device's ability to detect and characterize metamorphopsia (as reflected in positive and negative agreement) independent of human interpretation during the actual test, with human interpretation occurring after the test data is generated.
7. Type of Ground Truth Used (Test Set)
The type of ground truth used for the clinical study of the predicate device (Preview PHP) was expert consensus based on clinical imaging: "gold standards, i.e., color fundus photographs and fluorescein angiographics."
8. Sample Size for the Training Set
The document does not provide any information regarding the sample size for a training set. The descriptions focus on the validation of the device's performance against clinical gold standards, without detailing any machine learning training processes or associated datasets.
9. How Ground Truth for the Training Set Was Established
As no training set is discussed or implied within the context of machine learning, there is no information on how ground truth for a training set was established. The device is described as applying "the concept of the static and automated perimeter in the detection of visual field defects" and using "hyperacuity" for quantification, suggesting a more rule-based or signal processing approach rather than a deep learning model requiring a large labeled training set.
§ 886.1605 Perimeter.
(a)
Identification. A perimeter is an AC-powered or manual device intended to determine the extent of the peripheral visual field of a patient. The device projects light on various points of a curved surface, and the patient indicates whether he or she sees the light.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter, subject to the limitations in § 886.9. The device is also exempt from the current good manufacturing practice requirements of the quality system regulation in part 820 of this chapter, with the exception of § 820.180, with respect to general requirements concerning records, and § 820.198, with respect to complaint files.