(133 days)
The VMS+ 3.0 is an adjunct to existing ultrasound imaging systems and is intended to record, analyze, store and retrieve digital ultrasound images for computerized 3-dimensional image processing.
The VMS+ 3.0 is indicated for use where Left Ventricle (LV), Right Ventricle (RV), Left Atrium (LA), and Right Atrium (RA) volumes and ejection fractions are warranted or desired
The VMS+ was cleared under 510(k) (K173810) for use in evaluation where Right Ventricle (RV). Left Ventricle (LV). Right Atrium (RA), and Left Atrium (RA) volumes and eiection fractions are warranted or desired. The modified VMS+ (VMS+ 3.0) has the same operating principle and employs the same fundamental scientific technology to that of the cleared device.
The Ventripoint Medical System Plus (VMS+) 3.0 is a modified version of a previously cleared device (VMS+). The FDA letter and 510(k) summary do not detail a study involving AI assistance or a multi-reader multi-case (MRMC) comparative effectiveness study, nor do they specify acceptance criteria related to a general performance benchmark table or expert-based ground truth establishment as one might find for an AI/ML device.
Instead, the documentation focuses on demonstrating substantial equivalence to the predicate device (GE EchoPAC) and the reference device (VMS+) by showing that the modifications do not introduce new questions of safety or effectiveness and that the device performs as intended and as well as the predicate device(s).
Here's an breakdown of the information that is available and a note on what is not provided in the given text:
Acceptance Criteria & Device Performance:
The document broadly states that "Predefined acceptance criteria were applied during testing and were met" for specific types of nonclinical performance bench studies. However, the specific quantitative acceptance criteria for performance metrics (e.g., accuracy, precision) of volume measurements are not explicitly provided in a table within this document. It states that the device "delivers volume measurements that are equivalent in accuracy when compared with volumes obtained using the legally marketed VMS+."
| Acceptance Criteria (Generic Statement) | Reported Device Performance (General Statement) |
|---|---|
| Predefined acceptance criteria for nonclinical performance bench testing were applied and met. | VMS+ 3.0 delivers volume measurements that are equivalent in accuracy when compared with volumes obtained using the legally marketed VMS+. Test results demonstrate the device is as safe, as effective, performs as intended and as well as the predicate device (VMS+). |
| Software verification and validation test reports were successful according to acceptance criteria. | The verification and validation of existing and new features demonstrate that VMS+ 3.0 performs as intended, specifications conform to user needs and intended uses, and that requirements implemented can be consistently fulfilled. |
| Compliance with ISO 10993-1 for biocompatibility. | Patient contacting components comply with ISO 10993-1. |
| Compliance with IEC 60601-1 for electrical safety and essential performance. | Complies with IEC 60601-1. |
| Compliance with IEC 60601-1-2 for electromagnetic compatibility (EMC). | Complies with IEC 60601-1-2. |
Study Details (Based on the provided text):
-
Sample Size used for the test set and data provenance:
- The document mentions "nonclinical performance bench study" and "software verification and validation testing" but does not specify the sample size (e.g., number of cases or patients) used for these tests.
- The document does not specify the country of origin of the data or whether the data was retrospective or prospective. Given it's a bench study and software V&V, it likely refers to engineered test data or data from phantoms/previous device performance.
-
Number of experts used to establish the ground truth for the test set and qualifications of those experts:
- The document does not specify a number of experts, their qualifications, or their role in establishing ground truth for the test set as one might expect for a clinical performance study. The ground truth appears to be based on comparison to a previously cleared device's performance benchmarks.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- The document does not mention any adjudication method for a test set based on expert review.
-
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, an MRMC comparative effectiveness study was not explicitly mentioned or detailed. The device appears to be an image analysis system, but the submission focuses on its equivalence to a previous version and predicate, not on human-AI interaction or improvement. The document explicitly states "No clinical tests were conducted to support substantial equivalence for the subject device."
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The "nonclinical performance bench study" and "software verification and validation" would represent standalone performance assessments of the algorithm and system. The text states these tests demonstrate the device "performs as intended" and "delivers volume measurements that are equivalent in accuracy when compared with volumes obtained using the legally marketed VMS+." This implies an algorithm-only evaluation against established benchmarks from the reference device.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The "ground truth" for the nonclinical performance bench study was the "volumes obtained using the legally marketed VMS+" (the reference device). This implies a comparison to the established performance of a prior cleared device, rather than an independent expert consensus, pathology, or outcomes data.
-
The sample size for the training set:
- The document describes the VMS+ 3.0 as an updated version of a previous device utilizing a "Knowledge-Based Reconstruction (KBR) algorithm." It does not specify a separate "training set" in the context of machine learning model development. For "knowledge-based" systems, the "training" often refers to the creation and refinement of the underlying rules and models based on anatomical principles and potentially a dataset of examples. The document does not provide a sample size for a training set.
-
How the ground truth for the training set was established:
- As this is described as a "Knowledge-Based Reconstruction (KBR) algorithm" and an update to an existing system, the concept of "ground truth for a training set" as typically applied to large-scale deep learning models is not explicitly detailed. The "ground truth" for developing such a knowledge-based system would involve meticulously defined anatomical landmarks and their relationships, likely established through anatomical studies or prior medical imaging analysis principles. The document does not provide details on how the original knowledge base was implicitly "trained" or how its "ground truth" was established.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(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).