(98 days)
Brainomix Triage LVO 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.
Brainomix Triage LVO 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 of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes CT angiogram images of the brain acquired in the acute setting, and sends notifications to a neurovascular specialist that a suspected large vessel occlusion (LVO) has been identified and recommends review of those images. Images can be previewed through a mobile application or via email. Brainomix Triaqe LVO is intended to analyze terminal ICA and MCA-M1 vessels for LVOs.
lmages that are previewed through the mobile application are compressed and are for informational purposes only and not intended for diagnostic use beyond notification. Notified clinicians are responsible for viewing noncompressed 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.
Brainomix Triage LVO 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.
Brainomix 360 Triage LVO is a radiological computer aided triage and notification (CADt) software package compliant with the DICOM standard and running on an off-the-shelf physical or virtual server.
The Triage LVO module is a CTA processing module which operates within the integrated Brainomix 360 Platform to provide triage and notification of suspected LVO. Brainomix 360 Triage LVO is a stand-alone software device which uses machine learning algorithms that uses advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics to automatically identify suspected LVO on CTA imaging in the acute setting. The output of the module is a priority notification to clinicians indicating the suspicion of LVO based on positive findings. Specifically, Brainomix 360 Triage LVO is optimized to evaluate occlusions of the intracranial internal carotid artery (ICA) and proximal middle cerebral artery (M1 segment). The Triage LVO module uses the basic services supplied by the Brainomix 360 Platform including DICOM processing, job management, imaging module execution and imaging output including the notification and compressed image.
Brainomix 360 Triage LVO notification capabilities enable clinicians to review and preview images via mobile app notification. Alternatively, intended users can also access the notification (a "Suspected LVO" flag) and straightened images via the Brainomix 360 web user interface. Images that are previewed via mobile app are compressed, are for preview informational purposes only, and not intended for diagnostic use beyond notification.
The device is intended for use as an additional tool for assisting study triage within existing patient pathways. It does not replace any part of the current standard of care. It is designed to assist in prioritization of studies for reading within a worklist, in addition to any other pre-existing formal or informal methods of study prioritization in place. Specifically, it does not remove cases from a reading queue and operates in parallel to the standard of care. This device is not intended to replace the usual methods of communication and transfer of information in the current standard of care.
Brainomix 360 Triage LVO notification capabilities enable clinicians to preview compressed and informational images through via mobile application with preview of unprocessed image attachments. Alternatively, the user may review unprocessed images via web user interface on a radiology workstation.
Here's a breakdown of the acceptance criteria and the study proving the device's performance, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance (95% CI) | Goal |
|---|---|---|
| Sensitivity (Positive %) | 90% (84.2-94.3) | ≥ 80% (lower bound) |
| Specificity (Negative %) | 92.9% (88.0-94.3) | ≥ 80% (lower bound) |
| Time-to-Notification | 86.3 to 178.2 seconds | ≤ 3.5 minutes |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 308 CTA scans (studies)
- Data Provenance: Retrospective study. Data were obtained from 14 different hospitals and clinics in the U.S. The majority of patients were scanned at Mayo Clinic Rochester (N=129) and Boston Medical Centre (N=179), with 56 scans transferred from 11 hospitals in the Massachusetts area. The patient cohort was enriched to ensure an approximately equal balance of LVO positive and negative studies and to ensure the distribution of clinical and demographic variables (e.g., age and gender) for generalizability.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Two ground truthers, with a third ground truther used in the event of disagreement.
- Qualifications: All truthers were US board-certified neuroradiologists.
4. Adjudication Method for the Test Set
- Adjudication Method: 2+1 (Two ABR-certified neuroradiologists reviewed each case, and a third neuroradiologist provided consensus in the event of disagreement).
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was it done? No, the document only describes a standalone performance evaluation of the device.
- Effect size of human readers improving with AI vs. without AI assistance: Not applicable, as no MRMC study was performed or reported.
6. Standalone Performance Study
- Was it done? Yes, a standalone performance evaluation was done. The study assessed the device's image analysis in terms of sensitivity and specificity against a ground truth established by expert neuroradiologists.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus by US board-certified neuroradiologists.
8. Sample Size for the Training Set
- Sample Size: Over 1600 CT brain imaging studies.
9. How the Ground Truth for the Training Set was Established
- Ground Truth Establishment: The dataset used to train the algorithm was labeled by "trained radiologists" regarding the presence of LVO.
§ 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.