(83 days)
KODAK DIGITAL SCIENCE Distributed Medical Imagers are computer peripheral printing devices used to make hard copy of medical images and reports on paper and/or film.
KODAK DIGITAL SCIENCE 3600 Distributed Medical Imager is designed for mid to high end desktop Referral Imaging and Distributed Medical Imaging applications printing color or monochrome images on Medical Paper and/or Film Media up to 11x14 inch, with dual media supply trays and optional network interfacing.
KODAK DIGITAL SCIENCE 1200 Distributed Medical Imager is designed for low end to mid range desktop Referral Imaging and Distributed Medical Imaging applications printing color or monochrome images on Medical paper and/or film up to 8.5x11 inch, with a single media supply tray.
Here's an analysis of the provided text regarding the Eastman Kodak Company KODAK DIGITAL SCIENCE Distributed Medical Imagers (K983905), focusing on the acceptance criteria and the study to prove device performance.
Important Note: The provided document is a 510(k) summary for a medical device that acts as a printer. Therefore, the "acceptance criteria" and "study" are not related to diagnostic accuracy or clinical outcomes as one might expect for a diagnostic AI device. Instead, they focus on the device's technical specifications and substantial equivalence to a predicate device. The information provided is primarily about comparing the new device's features and performance parameters to an already approved device.
Acceptance Criteria and Reported Device Performance
The core of the "acceptance criteria" for these devices is demonstrating substantial equivalence to a predicate device, the KODAK EKTASCAN Medical Color Imager 2000PS (KEMCI 2000PS) (K951948). The performance is reported by comparing the specifications of the new devices to the predicate.
| Acceptance Criteria (Implied by Substantial Equivalence to Predicate) | KODAK DIGITAL SCIENCE 3600 DMI Performance | KODAK DIGITAL SCIENCE 1200 DMI Performance |
|---|---|---|
| Purpose and Functionality: Computer peripheral printing device for hard copy of medical images and reports on paper/film. | Yes (Inkjet printing) | Yes (Inkjet printing) |
| Printing Method: Produce monochrome or color images. | Inkjet | Inkjet |
| Interfaces: Similar connectivity options. | Parallel: IEEE 1284, Optional: Ethernet | Parallel: IEEE 1284 |
| Standards Compliance: Meet relevant safety and regulatory standards. | UL, CSA, FCC, EN50082, etc. | UL, CSA, FCC, EN50082, etc. |
| Print Media Types: Printing on coated paper, transparency, plain paper, card stock. | Coated Paper, Transparency (blue), Plain Paper, Card Stock | Coated Paper, Transparency (blue), Plain Paper, Card Stock |
| Monochrome Printing: Capability to print in black and white. | Yes | Yes |
| Color Printing: Capability to print in color. | Yes | Yes |
| Output Print Quality: The new devices' output is "similar" to the predicate. (Detailed resolution improvement noted) | 1200 dots per inch | 1200 dots per inch |
Explanation of Substantial Equivalence: The document asserts that the new devices' purpose and functionality are "substantially equivalent" to the predicate. The basis for this is that all devices are computer peripheral printing devices printing monochrome or color images on paper or transparency media. The key technological difference is the printing method (Inkjet for new devices vs. Thermal Dye Sublimation for the predicate). However, the submission concludes that, despite this difference, "the function and output of the SE devices is similar to that of the predicate device" and that they are "as safe and effective as the predicate device."
Study Details:
Given that this is a 510(k) submission for a printer, and not a diagnostic AI device, the concepts of "test set," "ground truth," and "multi-reader multi-case (MRMC) studies" are not directly applicable in the conventional sense. The "study" here is essentially the comparison of specifications and technical performance to demonstrate substantial equivalence to the predicate device.
-
Sample size used for the test set and the data provenance:
- Test Set Description / Sample Size: Not applicable in the context of a "test set" for diagnostic performance. The evaluation is based on comparing the published specifications and performance characteristics of the new devices against those of the predicate device.
- Data Provenance: The data provenance is from the manufacturer's own specifications and testing, likely internal engineering and quality assurance tests performed during the development of these printers. The document does not specify the country of origin for this data or if it was retrospective or prospective, but it would inherently be prospective testing of the newly manufactured devices.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable. There is no "ground truth" in the diagnostic sense for a printer. The "truth" is whether the printer meets its mechanical and output specifications (e.g., resolution, media handling, color accuracy, interface compatibility), which would be verified by engineering tests against predetermined design specifications.
-
Adjudication method for the test set:
- Not applicable. There is no adjudication method described because there isn't a diagnostic ground truth or expert interpretation involved.
-
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 was done. This type of study is irrelevant for a medical image printer. The device's purpose is to produce physical copies of images/reports, not to aid in interpretation or diagnosis.
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Not applicable. This device is a peripheral output device, not a standalone diagnostic algorithm. Its performance is evaluated based on its ability to accurately reproduce digital images on physical media.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not applicable. For a printer, the "ground truth" would be related to engineering specifications, e.g., "does the printer accurately reproduce colors according to color calibration standards," or "does it print at 1200 DPI as specified." These are objective, measurable technical parameters, not clinical "ground truth."
-
The sample size for the training set:
- Not applicable. This device is a printer, not an AI/ML algorithm that requires a "training set."
-
How the ground truth for the training set was established:
- Not applicable, as there is no training set.
§ 892.2040 Medical image hardcopy device.
(a)
Identification. A medical image hardcopy device is a device that produces a visible printed record of a medical image and associated identification information. Examples include multiformat cameras and laser printers.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.