(156 days)
The Tag of the RFLS is intended for percutaneous placement in the breast to mark (>30 days) a lesion intended for surgical removal. Using image guidance (such as ultrasound or radiography) or aided by non-imaging guidance (RFLS), the RFID Tag is located and surgically removed with the target tissue. The RFLS is intended only for the non-imaging detection and localization of the Tag that has been implanted in a lesion intended for surgical removal.
The Tag, Tag Applicator, Tag Applicator S, LOCalizer Reader, and LOCalizer Surgical Probe are components of the Health Beacons RFID Localization System (RFLS). The proposed device is a marker-with-detector localization device that employs miniature RFID tags as markers and a handheld reader that can measure distance to the Tag. The Tag, when used in conjunction with the Reader and Surgical Probe, can be used as a guide for the surgeon during the excision of tissue. The RFLS is a prescription device meant only for use by trained professionals, specifically breast surgeons and diagnostic radiologists.
This document describes the 510(k) summary for the Health Beacons, Inc. RFID Localization System (RFLS). However, based on the provided text, there is no detailed information about acceptance criteria and a specific study proving the device meets those criteria, especially in the context of AI assistance or human reader performance improvement.
The document is a 510(k) summary for a medical device (RFID Localization System) intended to mark and locate lesions in the breast for surgical removal. While it mentions performance testing was conducted to support substantial equivalence, it does not provide the specific acceptance criteria or the results from those tests in a format that would allow filling out the requested table or answering many of the follow-up questions.
The device itself is an RFID localization system, which uses miniature RFID tags as markers and a handheld reader to measure distance to the tag. This is a physical localization device, not an AI/software-based diagnostic tool that would typically involve acceptance criteria related to sensitivity, specificity, or human reader improvement with AI assistance.
Therefore, many of the requested details, particularly those pertaining to AI/ML algorithms (e.g., acceptance criteria for diagnostic accuracy, standalone algorithm performance, MRMC studies, training/test set details, ground truth for AI models), are not applicable or not present in this specific 510(k) summary.
Here's what can be extracted and what cannot, based on the provided text:
1. A table of acceptance criteria and the reported device performance:
- Not explicitly provided in the document. The document states that "All verification and validation activities identified as necessary were performed... and results demonstrate that predetermined acceptance criteria were met." However, the specific criteria and the numerical performance results are not tabulated or detailed.
- The "performance testing" subsections (VIII) list categories of tests but not acceptance criteria or outcomes. These tests include:
- Magnetic field emission testing per IEC 60601-1-2:2014
- Delivery testing
- Deployment Force testing
- Needle Penetration Force testing
- Usability testing
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):
- Not provided. The document states "performance testing was provided," but offers no details on sample size, study design (retrospective/prospective), or data provenance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable/Not provided. This is relevant for diagnostic AI/ML devices where human expert consensus often establishes ground truth. This device is a physical localization system, not a diagnostic imaging AI.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable/Not provided. Same reasoning as point 3.
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. This device is a physical localization system; it's not an AI assisting human readers with diagnostic tasks.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable/Not provided. The device is a "marker-with-detector localization device" that involves a Tag and a Reader/Probe used by a surgeon. There isn't an "algorithm only" component in the sense of a standalone diagnostic AI.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Not explicitly stated for the listed performance tests. For a physical device, ground truth for performance tests would likely involve physical measurements (e.g., actual vs. measured distance, force applied, magnetic field readings).
8. The sample size for the training set:
- Not applicable/Not provided. This device is not an AI/ML algorithm that requires a training set.
9. How the ground truth for the training set was established:
- Not applicable/Not provided. Same reasoning as point 8.
In summary of the provided text:
This FDA 510(k) summary describes a physical medical device (RFID Localization System), not an AI/ML diagnostic software. The document asserts that performance testing was conducted and met predetermined acceptance criteria, which supported the substantial equivalence determination to a predicate device. However, it does not provide the specific numerical acceptance criteria or the detailed results of those performance tests. Information regarding sample sizes, data provenance, expert involvement for ground truth, or MRMC studies (which are highly relevant for AI/ML diagnostic devices) is absent as these concepts are not directly applicable to the type of device described.
§ 878.4300 Implantable clip.
(a)
Identification. An implantable clip is a clip-like device intended to connect internal tissues to aid healing. It is not absorbable.(b)
Classification. Class II.