(56 days)
Viz ICH is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow.
Viz ICH uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes non-contrast CT images of the brain acquired in the acute setting, and sends notifications to a neurovascular or neurosurgical specialist that a suspected intracranial hemorrhage has been identified and recommends review of those images can be previewed through a mobile application.
lmages that are previewed through the mobile application may be compressed and are for informational purposes only and not intended for diagnostic use beyond notification. Notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests. Viz ICH is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.
Viz ICH is a software-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to an appropriate specialist, such as a neurovascular specialist or neurosurgeon, independent of the standard of care workflow. The system automatically receives and analyzes non-contrast CT (NCCT) studies of patients for image features that indicate the presence of an intracranial hemorrhage (ICH) using an artificial intelligence algorithm, and upon detection of a suspected ICH, sends a notification so as to alert a specialist clinician of the case.
Viz ICH is a combination of software modules that consists of an image analysis software algorithm and mobile application software module. The Viz ICH image analysis software algorithm is an artificial intelligence machine (AI/ML) software algorithm that analyzes non-contract CT images of the head for an intracranial hemorrhage. The Viz ICH Image Analysis Algorithm is hosted on Viz.ai's servers and analyzes applicable stroke-protocoled NCCT images of the head that are acquired on CT scanners and are forwarded to Viz.ai servers. Upon detection of a suspected intracranial hemorrhage, the Viz ICH Image Analysis Algorithm sends a notification of the suspected finding.
Viz ICH includes a mobile software module that enables the end user to receive and toggle notifications for suspected intracranial hemorrhages identified by the Viz ICH Image Analysis Algorithm. The Viz ICH mobile notification software module is implemented into Viz.ai's non-diagnostic DICOM image viewer, Viz VIEW, which displays CT scans that are sent to Viz.ai's servers. When the Viz ICH mobile notification software module is enabled for a user, the user can receive and toggle the notifications for patients with a suspected intracranial hemorrhage, view a unique patient list of patients with a suspected intracranial hemorrhage, and view the non-diagnostic CT scan of the patient through the Viz VIEW mobile application. Image viewing through the mobile application interface is for nondiagnostic purposes only.
Viz ICH Acceptance Criteria and Performance Study
This document describes the acceptance criteria for the Viz ICH device and the study conducted to demonstrate its performance.
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Lower Bound 95% CI) | Reported Device Performance [95% CI] |
|---|---|---|
| Sensitivity | ≥ 80% | 95% [91% - 98%] |
| Specificity | ≥ 80% | 96% [92% - 98%] |
| AUC | Not explicitly stated (but 0.97 indicates strong performance) | 0.97 |
| Time to Alert | Not explicitly stated (but improvement over standard of care is implied) | 0.49 ± 0.08 minutes |
2. Sample Size and Data Provenance
- Test Set Sample Size: 387 Non-contrast Computed Tomography (NCCT) scans (studies).
- Data Provenance: Two clinical sites in the U.S. (Retrospective, as the study was to evaluate the performance of an already developed algorithm on existing data).
3. Number, Qualifications, and Adjudication of Experts for Ground Truth
- Number of Experts: Not explicitly stated, but referred to as "trained neuro-radiologists."
- Qualifications of Experts: "Trained neuro-radiologists." Specific years of experience are not mentioned.
- Adjudication Method: Not explicitly stated, but "ground truth as established by trained neuro-radiologists" implies a consensus or majority vote among multiple experts.
4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No. The study focuses on the standalone performance of the AI algorithm.
- Effect size of human readers with AI vs. without AI assistance: Not applicable as no MRMC study was conducted. However, the study does mention the average time to alert:
- Viz ICH: 0.49 ± 0.08 minutes
- Standard of Care: 18.3 ± 14.2 minutes
This reduction in alert time implies a significant improvement in the speed of notification for human specialists.
5. Standalone Performance
- Was a standalone (algorithm only) performance study done? Yes. The provided performance data (sensitivity, specificity, AUC) directly reflects the algorithm's performance compared to ground truth.
6. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus, specifically "ground truth as established by trained neuro-radiologists" for the presence or absence of intracranial hemorrhage.
7. Sample Size for Training Set
- Sample Size for Training Set: Not explicitly stated in the provided document.
8. How Ground Truth for Training Set Was Established
- How Ground Truth for Training Set Was Established: Not explicitly stated in the provided document. It is generally assumed that the training data ground truth would also be established by clinical experts, similar to 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.