(324 days)
The Adapt™ is an AC powered, automated adaptometer (biophotometer), intended to measure the time for retinal adaptation after exposure to an adapting light.
The AdaptTM is an AC-powered, automated, adaptometer (biophotometer).
Here's an analysis of the provided 510(k) summary regarding the Acceptance Criteria and Study to prove device performance:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Agreement with Predicate Device: High correlation in dark adaptation speed (rod-cone break and rod intercept parameters). | Agreement Study: Dark adaptation speed parameters found to be "highly correlated" between Adapt™ and the predicate device. |
| Precision/Reproducibility: Consistent dark adaptation speed measurements over time. | Precision Study: Dark adaptation speeds for the Adapt™ were "highly correlated" between the first and second visits for both parameters. |
| Precision comparable to Predicate Device: The precision of the new device should not be worse than the predicate. | Precision Study: The precision of the Adapt™ was "comparable to the predicate." |
| Meet Product Specifications and Performance Requirements: (General criteria for verification testing) | Verification Testing: Demonstrated that the device met product specifications and performance requirements for various subsystems (Flash, Stimulus, Fixation Light, etc.). |
Important Note: The provided 510(k) summary does not explicitly state quantitative acceptance criteria (e.g., "correlation coefficient > 0.9"). The criteria are described qualitatively as "highly correlated" and "comparable."
2. Sample Size Used for the Test Set and Data Provenance
- Agreement Study: 12 adults with a range of eye health status. Data provenance is not explicitly stated (e.g., country of origin) but is implied to be prospective for the purpose of the study.
- Precision Study:
- 14 adults with normal retinal health.
- 8 patients with age-related macular degeneration (AMD).
- Separate group of 6 normal adults (for predicate comparison).
- Data provenance is not explicitly stated but is implied to be prospective for the purpose of the study.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
This information is not provided in the 510(k) summary. The device measures an objective physiological parameter (retinal adaptation time), so the "ground truth" would likely be derived from the device measurements themselves or comparison to a gold-standard device, not from expert interpretation of images or clinical assessments.
4. Adjudication Method for the Test Set
This information is not applicable as the device is for objective measurement of retinal adaptation, not for diagnostic interpretation requiring human adjudication of findings. Therefore, no adjudication method (like 2+1 or 3+1) would be relevant.
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
An MRMC study was not done. This device is an automated adaptometer and does not involve human readers interpreting images or data where AI assistance would be a factor. It directly measures a physiological response.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, the studies described (Agreement Study and Precision Study) demonstrate the standalone performance of the Adapt™ device. It takes measurements directly without human interpretation as part of its core function, other than operation of the device and subject engagement.
7. The Type of Ground Truth Used
The "ground truth" for the performance studies appears to be the measurements obtained from the predicate device (Goldmann-Weekers adaptometer) for the Agreement Study. For the Precision Study, the ground truth for reproducibility is the repeatability of the Adapt™'s own measurements and comparison to the repeatability of the predicate device. It's a comparative performance study against an established method.
8. The Sample Size for the Training Set
This information is not provided and is likely not applicable in the traditional sense of a machine learning-based device that requires a distinct "training set." The Adapt™ is described as an "AC-powered, automated adaptometer (biophotometer)" controlled by software, implying a rule-based or algorithm-driven system rather than a deep learning model that learns from large datasets. Its performance is validated through verification and clinical performance testing.
9. How the Ground Truth for the Training Set Was Established
As noted above, a distinct "training set" with established ground truth as understood in machine learning is not described or implied for this device. The device's operation is based on established biophysical principles of dark adaptation and implemented through software control. Verification and validation testing ensure the software correctly implements these principles and meets product specifications.
§ 886.1050 Adaptometer (biophotometer).
(a)
Identification. An adaptometer (biophotometer) is an AC-powered device that provides a stimulating light source which has various controlled intensities intended to measure the time required for retinal adaptation (regeneration of the visual purple) and the minimum light threshold.(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.