(267 days)
The Specular Microscope CEM-530 is a non-contact ophthalmic microscope, optical pachymeter, and camera intended for examination of the corneal endothelium and for measurement of the thickness of the cornea.
The Nidek Specular Microscope CEM-530 provides non-contact, high magnification image capture of the endothelium enabling observation of the size and shape of cells. Information such as the number of endothelial cells, cell density, and cell area is analyzed through the captured images. The captured images and analysis results of the endothelium are used in intraocular or corneal surgery, postoperative follow-up, and corneal observation such as for endothelial disorders or the corneal state of patients who wear extended-wear contact lenses. Observation is possible in the central area (visual angle: 5°) and peripheral area (visual angle: 27°) using a periphery capture function as well as in the center of the captured images and analysis results can be printed on the built-in printer or optional video printer, or output to an external device over LAN connection. In addition to the specular microscopy, the corneal thickness can be optically measured in a non-contact method. The CEM-530 has auto-tracking and auto-shooting functions. Results can be printed using the built-in thermal printer or captured images can be transferred to a filing system via LAN connection. The Specular Microscope CEM-530 cleared in this 510(k) is identical to the Specular Microscope CEM-530 cleared in K130565 with the addition of a new analysis mode: Center Point Method. All other aspects of the cleared device remain unchanged.
The provided document describes the predicate device and the clinical study conducted for the Nidek Specular Microscope CEM-530. It focuses on demonstrating substantial equivalence to a predicate device (Konan CellChek Plus) rather than establishing novel acceptance criteria for an AI algorithm. Therefore, many of the requested items related to AI-specific acceptance criteria and study methodologies (e.g., sample size for training set, number of experts for ground truth, MRMC study effect size) are not applicable as this submission predates the widespread use and specific regulatory requirements for AI/ML medical devices.
However, based on the information provided, we can infer and or extract the following:
1. A table of acceptance criteria and the reported device performance:
The acceptance criteria are implicitly defined by demonstrating "agreement, accuracy and precision" with the predicate device. The performance data is presented as statistical measures comparing the CEM-530 with the Konan CellCheChek Plus. The key metrics studied are:
- Endothelial Cell Density (CD)
- Coefficient of Variation of Endothelial Cell Area (CV)
- % Hexagonality (% HEX)
Here's a summary derived from the "Device Comparisons" section in Table 2 for "All Subjects - Effectiveness Population":
| Performance Metric | Acceptance Criteria (Implied: Substantially Equivalent to Predicate) | Reported Device Performance (NIDEK CEM-530 vs. Konan CellChek Plus) (All Subjects) |
|---|---|---|
| Endothelial Cell Density (CD) | Agreement with predicate | Mean Difference (SD): 45.7 (104.11) cells/mm² |
| 95% LOA: (-162.5, 253.9) | ||
| Precision (Repeatability and Reproducibility) | Repeatability SD: 48.9 | |
| Reproducibility SD: 60.9 | ||
| Coeff. of Variation (CV) | Agreement with predicate | Mean Difference (SD): -7.6 (3.00)% |
| 95% LOA: (-13.6, -1.6) | ||
| Precision (Repeatability and Reproducibility) | Repeatability SD: 1.5 | |
| Reproducibility SD: 1.8 | ||
| % Hexagonality (% HEX) | Agreement with predicate | Mean Difference (SD): -2.9 (5.90)% |
| 95% LOA: (-14.6, 8.9) | ||
| Precision (Repeatability and Reproducibility) | Repeatability SD: 3.5 | |
| Reproducibility SD: 4.0 |
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size:
- Agreement Study: 74 subjects (28 non-pathologic young eye, 27 non-pathologic adult eye, 19 pathologic adult eye).
- Precision Study: 47 subjects (15 non-pathologic young eye, 16 non-pathologic adult eye, 16 pathologic adult eye).
- Historical Data (for comparison in precision study): 62 subjects (from CEM-530-US-001 study, for Konan CellChek Plus).
- Data Provenance: The study was a "prospective clinical study." The document does not explicitly state the country of origin, but given the sponsor (Nidek Co., Ltd. Japan) and the contact person (Ora, Inc. Massachusetts), it is likely an international or US-based study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This information is not provided in the document. The ground truth for this device (a specular microscope) is the "manual measurements" performed by operators using the predicate device, or direct measurements from the Nidek CEM-530 and then compared. This is not an AI-based system where human experts would individually label data for ground truth in the same way. The document refers to "operators" and "machines" performing measurements, implying the ground truth is derived directly from the measurement devices themselves.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
This information is not applicable as the ground truth is established by the device's measurements, not by expert consensus requiring adjudication.
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:
This was not an MRMC comparative effectiveness study and does not involve AI assistance for human readers. It's a device comparison study evaluating agreement and precision between a new device and a predicate device in performing direct measurements of corneal parameters. Therefore, the effect size of human reader improvement with AI assistance is not applicable.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
The device (Specular Microscope CEM-530) itself performs measurements, and the "Center Point Method" is an analysis mode within the device. The study evaluates the performance of this device in a clinical setting. While it's an "algorithm" making measurements, it's not described as a separate AI algorithm being tested in isolation. The study compares the device's performance (including its internal algorithms) against a predicate device. This is primarily a device-to-device comparison study, not a standalone AI algorithm performance study in the contemporary sense.
7. The type of ground truth used:
The ground truth is derived from the measurements obtained from a legally marketed predicate device (Konan CellChek Plus), against which the Nidek Specular Microscope CEM-530's measurements are compared for agreement and precision. This is essentially a "comparator device" ground truth.
8. The sample size for the training set:
This information is not applicable. The CEM-530 is a medical measurement device, not an AI/ML system that undergoes a separate training phase with a large dataset. The "Center Point Method" is an analysis mode, likely based on established algorithms for image analysis rather than a data-driven machine learning model requiring a "training set" in the common AI sense.
9. How the ground truth for the training set was established:
This information is not applicable as there is no mention of a traditional AI "training set" in the document.
§ 886.1850 AC-powered slitlamp biomicroscope.
(a)
Identification. An AC-powered slitlamp biomicroscope is an AC-powered device that is a microscope intended for use in eye examination that projects into a patient's eye through a control diaphragm a thin, intense beam of light.(b)
Classification. Class II (special controls). The device, when it is intended only for the visual examination of the anterior segment of the eye, is classified as Group 1 per FDA-recognized consensus standard ANSI Z80.36, does not provide any quantitative output, and is not intended for screening or automated diagnostic indications, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 886.9.