(36 days)
The Protura Couch Software is interface between a record and verify system, linear accelerator (Linac) software, Linac safeguard systems, and/or image guidance systems and the Protura Couch. The Protura Couch Software is also capable of operating the Protura Couch (6 Degree Axis Couch).
The proposed device, the Protura Couch Software (MT6XSMEU), is patient positioning software used in radiation treatments in conjunction with an Image Guided Radiation Therapy (IGRT) system. The Protura Couch Software interfaces with the Protura Couch Hardware (K031866) and is intended to position the patient after diagnostic decisions have been made based on results from an IGRT system. The Protura Couch Software allows the user to control patient positioning with six degrees of freedom from outside of the treatment room. The Protura Couch Software also includes the ability to interface with a record and verify system, Linac software, Linac safeguard systems, and/or image guidance systems.
The provided text describes a 510(k) summary for the Protura Couch Software (device name: MT6XSMEU) by MED-TEC, Inc. d/b/a CIVCO Medical Solutions. This software is designed for patient positioning in radiation therapy.
Here's an analysis of the acceptance criteria and study information, based solely on the provided document:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state quantitative acceptance criteria in a table format. Instead, it describes performance testing conducted. The reported device performance is that "All testing confirmed that the Protura Couch Software is safe and effective for its intended use" and that it is "substantially equivalent to the predicate device in regards to safety, effectiveness, and performance."
The characteristics tested include:
- Movement of the Protura Couch
- Interfacing with External Systems
- Couch Pedestal and Isocenter Alignment
- Patient Record Handling
Without specific numerical targets for these characteristics, a precise table of acceptance criteria and reported performance cannot be generated. The document indicates these tests were performed and passed.
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
The document does not specify a sample size for the test set. It mentions "non-clinical performance testing" but does not detail the number of test cases, simulated patients, or data points used. Data provenance is also not mentioned, as no clinical data or data from human subjects was used for testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)
This information is not applicable and hence not provided. As the testing was "non-clinical" and involved evaluating software functionality and interface, there was no need for experts to establish ground truth in the context of medical image interpretation or patient outcomes.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
This information is not applicable and hence not provided. The non-clinical performance data described does not involve expert adjudication as it pertains to software functionality and system interfaces, not diagnostic or prognostic outcomes requiring consensus.
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
No MRMC study was performed or is mentioned. The device is software for controlling a radiation therapy couch, not an AI for image interpretation or diagnosis that would typically be evaluated with human readers.
6. If a standalone (i.e., algorithm only without human-in-the loop performance) was done
Yes, based on the description, the performance testing appears to be a standalone evaluation of the software's functionality and its ability to interface with other systems and control the couch. The "non-clinical performance data" section describes testing conducted on the software itself and its interactions, without human-in-the-loop performance being a primary evaluation point for its safety and effectiveness.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The concept of "ground truth" as typically applied in AI/clinical studies (e.g., expert consensus for diagnosis, pathological findings) is not relevant here. For this device (software controlling a medical couch), the "ground truth" would be the expected functional behavior and precise physical movements of the couch, as defined by engineering specifications and safety standards. The testing verified that the software met these operational specifications.
8. The sample size for the training set
This information is not applicable and not provided. The Protura Couch Software is described as an interface and control system, programmed in C#. It is not an AI/machine learning model that typically requires a distinct "training set" in the sense of labeled data for learning.
9. How the ground truth for the training set was established
This information is not applicable and not provided, for the same reasons as in point 8.
§ 892.5770 Powered radiation therapy patient support assembly.
(a)
Identification. A powered radiation therapy patient support assembly is an electrically powered adjustable couch intended to support a patient during radiation therapy.(b)
Classification. Class II.