(123 days)
Viz AAA is a radiological computer-assisted triage and notification software device for analysis of CTA images of the abdomen. The device is intended to assist hospital networks and vascular specialists in workflow triage by flagging and prioritizing studies with suspected abdominal aortic aneurysms during routine patient care.
Viz AAA uses an artificial intelligence algorithm to analyze images and highlight studies with suspected abdominal aortic aneurysms in a standalone application for study list prioritization or triage in parallel to ongoing standard of care. The device generates compressed preview images that are meant for informational purposes only and not intended for diagnostic use. The device does not alter the original medical image and is not intended to be used as a diagnostic device.
Analyzed images are available for review through the standalone application. When viewed through the standalone application the images are for informational purposes only and not for diagnostic use. The results of Viz AAA, in conjunction with other clinical information and professional judgment, are to be used to assist with triage/prioritization of medical images. Vascular specialists who read the original medical images are responsible for the diagnostic decision. Viz AAA is limited to analysis of imaging data and should not be used inlieu of full patient evaluation or relied upon to make or confirm diagnosis.
Viz AAA is limited to detecting aneurysms at least 3 cm in diameter. Viz AAA is intended to identify infra-renal, fusiform abdominal aortic aneurysms.
Viz AAA is a radiological computer-assisted triage and notification software device for analysis of CTA images of the abdomen. The software automatically receives and analyzes CT angiogram (CTA) imaging of the abdomen for the presence of an aortic aneurysm using an artificial intelligence algorithm and highlights suspect patient imaging in a standalone application for study list prioritization or triage by vascular or endovascular specialists in parallel to standard of care image interpretation.
Viz AAA is a combination of software modules that consists of an image analysis software algorithm and mobile application software module. The Viz AAA Image Analysis Algorithm is an artificial intelligence machine learning (Al/ML) software algorithm that analyzes CTA images of the abdomen for an aortic aneurysm. Images acquired during patient care are forwarded to Viz.ai's Backend server where they are analyzed by the Viz AAA artificial intelligence algorithm for an abdominal aortic aneurysm.
Viz AAA includes a mobile software module that enables the end user to view cases identified by the Viz AAA algorithm to contain a suspected abdominal aortic aneurysm. The Viz AAA mobile software module is implemented into Viz.ai's generic non-diagnostic DICOM image mobile viewing application, Viz VIEW, which displays CTA scans that are sent to the Backend server. When the Viz AAA Mobile Software module is enabled, studies determined by the algorithm to contain a suspected abdominal aortic aneurysm are highlighted in the standalone mobile application for study list prioritization or triage in parallel to ongoing standard of care. The user can also view compressed preview images and a non-diagnostic preview of the analyzed CTA scan of the patient through the mobile application.
The preview images and additional patient imaging available through the standalone mobile application are meant for informational purposes only and not intended for diagnostic use. The results of Viz AAA, in conjunction with other clinical information and professional judgment, are to be used to assist with triage/prioritization of medical images. Vascular or endovascular specialists who read the original medical images are responsible for the diagnostic decision.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Acceptance Criteria and Device Performance Study for Viz AAA
The Viz AAA device is a radiological computer-assisted triage and notification software intended to assist in workflow triage by flagging and prioritizing studies with suspected abdominal aortic aneurysms (AAAs) during routine patient care. Importantly, the device is for triage and prioritization only and not for diagnostic use.
1. Table of Acceptance Criteria and Reported Device Performance
The core performance goals for Viz AAA were for its sensitivity and specificity in detecting AAAs.
| Performance Metric | Acceptance Criteria (Lower Bound of 95% CI) | Reported Device Performance (95% CI) | Met Criteria? |
|---|---|---|---|
| Sensitivity | > 80% | 96% [0.92, 0.98] | Yes |
| Specificity | > 80% | 95% [0.92, 0.97] | Yes |
| Area Under the Curve (AUC) | > 0.95 (point estimate) | 0.99 [0.98 - 1.00] | Yes (Exceeded) |
The study successfully met or exceeded all pre-specified performance goals.
2. Sample Size and Data Provenance
- Test Set Sample Size: 466 CTA scans.
- 167 scans with abdominal aortic aneurysm (positive cases)
- 299 scans without abdominal aortic aneurysm (negative cases)
- Data Provenance: The CTA scans were obtained from two clinical sites in the U.S. The data appears to be retrospective, as it refers to "scans were obtained" and "included in the analysis," implying pre-existing data used for verification.
3. Number and Qualifications of Experts for Ground Truth
- Number of Experts: Not explicitly stated, but implied to be multiple radiologists, as "trained radiologists" is plural.
- Qualifications of Experts: Trained radiologists with fellowship in vascular radiology.
4. Adjudication Method for the Test Set
The adjudication method used to establish ground truth is not explicitly detailed in the provided text (e.g., 2+1, 3+1). It simply states that ground truth was "established by trained radiologists with fellowship in vascular radiology."
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? The provided text does not indicate that an MRMC comparative effectiveness study was performed. The performance evaluation focuses solely on the standalone algorithm's accuracy (sensitivity, specificity, AUC) against expert-established ground truth.
- Effect Size: N/A (as no MRMC study information is provided).
6. Standalone Performance Study
- Was a standalone study done? Yes, a standalone performance study was conducted. The reported sensitivity, specificity, and AUC values directly reflect the algorithm's performance without human intervention in the loop for the performance evaluation.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert Consensus (established by trained radiologists with fellowship in vascular radiology). The text relies on this expert review of the CTA scans to determine the presence or absence of an AAA, which serves as the ground truth against which the device's output is compared.
8. Sample Size for the Training Set
The provided text does not include information about the sample size used for the training set. It only details the performance evaluation on a test set.
9. How Ground Truth for the Training Set was Established
The provided text does not include information on how the ground truth for the training set was established. It only details the ground truth establishment for the test set.
§ 892.2080 Radiological computer aided triage and notification software.
(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.