(14 days)
Diagnostic ultrasound imaging or fluid flow analysis of the human body as follows: Abdominal, Cardiac, Small Organ, Pediatric, Fetal, Intra-Operative, Transesophageal, Transvaginal, Transrectal, Peripheral Vascular, Neonatal and Adult Cephalic. Cardiac is Adult and Pediatric. Small organ includes breast.
Strain Rate Imaging is a modification to the motion analysis capability of the System FiVe / EchoPac. It gives the user the ability to assess the rate of deformation in tissue. When used for cardiac analysis, the user can assess the rate of dimensional changes in the myocardium during the cardiac cycle in a manner similar to tissue velocity imaging. Strain rate can also describe the resistance of tissue objects to external compression.
The provided document does not contain details about specific acceptance criteria or a study that rigorously proves the device meets those criteria in a quantitative sense as typically seen for AI/ML devices. Instead, it focuses on demonstrating substantial equivalence to a predicate device and adherence to general safety standards.
Here's an analysis based on the available information:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not report specific quantitative acceptance criteria or detailed device performance metrics for the Strain Rate Imaging functionality. The evaluation for substantial equivalence primarily relies on non-clinical tests related to safety and general performance of the Doppler technology, and a claim that no clinical tests were required.
Therefore, a table with quantitative acceptance criteria and reported device performance cannot be generated from this document.
2. Sample Size Used for the Test Set and Data Provenance:
The document states: "Strain Rate Imaging is implemented with Doppler technology which has undergone testing with phantoms and test objects with known characteristics to assure the accuracy of dimensional and dynamic measurements."
- Sample Size for Test Set: Not specified. The phrase "phantoms and test objects" suggests a limited number of controlled, non-human samples.
- Data Provenance: Not explicitly stated, but it's in vitro (phantoms and test objects) rather than clinical. It is a non-clinical evaluation.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified. The document only mentions "testing with phantoms and test objects with known characteristics," implying that the "ground truth" for these tests was derived from the known characteristics of the phantoms/objects themselves, not expert adjudication of images.
4. Adjudication Method for the Test Set:
- Adjudication method: Not applicable/None mentioned. Since the testing was reportedly done on phantoms and test objects with known characteristics, the ground truth would inherently be these known characteristics, not subject to expert adjudication of potentially ambiguous clinical findings.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Was an MRMC study done? No. The document explicitly states: "Clinical Tests: None required." Therefore, no comparative effectiveness study with human readers (with or without AI assistance) was conducted or reported.
- Effect size of human readers improvement with AI vs without AI assistance: Not applicable, as no MRMC study was performed.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
- Was a standalone performance study done? The document describes non-clinical tests on phantoms and test objects "to assure the accuracy of dimensional and dynamic measurements." This constitutes a standalone evaluation of the Strain Rate Imaging technology, but within the context of a general ultrasound system, not as a separate AI algorithm being evaluated for specific clinical performance metrics. The focus is on the accuracy of the Doppler technology to measure strain rate from these objects. No specific metrics like sensitivity, specificity, or AUC are provided for this standalone performance.
7. Type of Ground Truth Used:
- Type of Ground Truth: "Known characteristics" of phantoms and test objects. This is an in vitro ground truth for assessing the fundamental measurements of the Doppler technology. It is not expert consensus, pathology, or outcomes data from human subjects.
8. Sample Size for the Training Set:
The document does not mention any training set. This is consistent with devices from this era (1999) that were typically based on conventional signal processing and image reconstruction techniques, rather than machine learning algorithms requiring explicit training data. The device is a modification to existing Doppler technology.
9. How the Ground Truth for the Training Set Was Established:
Not applicable, as no training set is mentioned in the document.
Summary of Acceptance and Evidence:
The acceptance of the GE Vingmed System FiVe Diagnostic Ultrasound System / EchoPac with Strain Rate Imaging was based on:
- Demonstrating substantial equivalence to an existing predicate device (GE Vingmed Ultrasound System FiVe diagnostic ultrasound system / EchoPac, 510(k) Number K963315).
- Compliance with applicable medical device safety standards (acoustic output, biocompatibility, thermal, electrical, and mechanical safety).
- Non-clinical testing of the Doppler technology using phantoms and test objects with known characteristics to ensure accuracy of dimensional and dynamic measurements.
The key point is that for this device, a 510(k) submission from 1999, the regulatory pathway relied on demonstrating safety and effectiveness by showing it was substantially equivalent to a device already on the market, rather than requiring extensive clinical trials or performance assessments with quantitative acceptance criteria typically associated with modern AI/ML devices.
§ 892.1560 Ultrasonic pulsed echo imaging system.
(a)
Identification. An ultrasonic pulsed echo imaging system is a device intended to project a pulsed sound beam into body tissue to determine the depth or location of the tissue interfaces and to measure the duration of an acoustic pulse from the transmitter to the tissue interface and back to the receiver. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A biopsy needle guide kit intended for use with an ultrasonic pulsed echo imaging system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.