(39 days)
The RadWorks™ Medical Imaging Software is a medical device, and it has the same indications for use and target population as the legally marketed predicate devices.
The RadWorks™ medical imaging software consists of a basic module, RadWorks™ Review, and a number of optional modules, to enable the radiologist to view, retrieve, store, import process and transmit medical images. The RadWorks™ software is an open system which runs under the Microsoft® Windows NT™ operating system and it can operate on any hardware platform which meets the minimum hardware requirements and which supports the Windows NTT™ operating system. Windows NT™ based workstations can be made part of UNIX, Novell NetWare, or other networks from major vendors. RadWorks™ is a stand-alone software product and involves no hardware except (optionally) a special graphics card.
The provided document is a 510(k) Summary for the RadWorks™ Medical Imaging Software, dated July 5, 1996. It describes the device, its intended use, and argues for its substantial equivalence to predicate devices. However, it does not include specific acceptance criteria or an explicit study proving the device meets those criteria in the modern sense of a performance study with quantitative metrics.
The document states: "The RadWorks™ Medical Imaging Software is tested according to the specifications that are documented..." and "The RadWorks™ Medical Imaging Software is tested according to the Specifications national of the Research and the former as in a Software Safe ware In a Software Test Plant Quality Handbook." This implies that internal specification testing was performed, but the results of such testing are not detailed, nor are specific acceptance criteria for performance metrics (like sensitivity, specificity, accuracy, etc.) provided.
Therefore, many of the requested fields cannot be answered from the provided text.
Here's a breakdown of what can be inferred or what is explicitly missing:
1. Table of acceptance criteria and the reported device performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Not specified in this document. The document mentions testing "according to specifications" but does not define these specifications or report performance metrics against them. | Not specified in this document. |
2. Sample size used for the test set and the data provenance:
- Sample size for test set: Not specified.
- Data provenance: Not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable, as no ground truth establishment for a test set is described.
4. Adjudication method for the test set:
- Not applicable, as no ground truth establishment for a test set is described.
5. If a multi-reader, multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance:
- No, an MRMC comparative effectiveness study is not described. The document pertains to a general medical imaging software (digital image communication system) rather than an AI-assisted diagnostic tool.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- The device is a "stand-alone software product" in the sense that it operates independently and is described as a "Digital Image Communications System" for viewing, retrieving, storing, processing, and transmitting medical images. This is distinct from a standalone diagnostic algorithm performance study. The document does not describe a standalone performance study for an algorithm in a diagnostic context.
7. The type of ground truth used:
- Not applicable, as no ground truth for a diagnostic performance study is described.
8. The sample size for the training set:
- Not applicable, as this device (a digital image communication system) is not described as involving a training set in the context of machine learning.
9. How the ground truth for the training set was established:
- Not applicable, as this device is not described as involving a training set in the context of machine learning.
Summary of what the document does provide regarding testing:
- General Statement on Testing: "The RadWorks™ Medical Imaging Software is tested according to the specifications that are documented... in a Software Test Plan and Quality Handbook."
- Purpose of Testing: To assure "substantial equivalence" to predicate devices.
- Focus of the Device: It is a digital image communication system for viewing and managing medical images, offering features like interactive windowing, zooming, panning, annotation, measurement, and connectivity. It is not presented as an AI-powered diagnostic tool requiring performance metrics like sensitivity or specificity against a ground truth for lesions or conditions. Its "performance" would likely be related to functional correctness, image quality preservation, speed of display, and adherence to display standards.
§ 892.2020 Medical image communications device.
(a)
Identification. A medical image communications device provides electronic transfer of medical image data between medical devices. It may include a physical communications medium, modems, and interfaces. It may provide simple image review software functionality for medical image processing and manipulation, such as grayscale window and level, zoom and pan, user delineated geometric measurements, compression, or user added image annotations. The device does not perform advanced image processing or complex quantitative functions. This does not include electronic transfer of medical image software functions.(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 § 892.9.