(211 days)
BriefCase is a radiological computer aided triage and notification software indicated for use in the analysis of head CTA images in adults or transitional adolescents aged 18 and older. The device is intended to assist hospital networks and appropriately trained medical specialists in workflow triage by flagging and communication of suspected positive findings of complete Large Vessel Occlusion (LVO) - MCA-M1, PCA-P1, ACA-A1, ICA, Basilar; and Medium Vessel Occlusions (MeVO) - MCA-M2, MCA-proximal M3, PCA-P2, PCA-proximal P3, ACA-A2, ACA-proximal A3, and Vertebral-V4.
BriefCase uses an artificial intelligence algorithm to analyze images and highlight cases with detected findings on a standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected findings. Notifications include compressed preview images that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.
The results of BriefCase are intended to be used in conjunction with other patient information and based on their professional judgment, to assist with triage/prioritization of medical images. Notified clinicians are responsible for viewing full images per the standard of care.
BriefCase is a radiological computer-assisted triage and notification software device. The software system is based on an algorithm programmed component and consists of a standard off-the-shelf operating system, the Microsoft Windows server 2012 64bit, and additional applications, which include PostgreSQL, DICOM module and the BriefCase Image Processing Application. The device consists of the following three modules: (1) Aidoc Hospital Server (AHS/Orchestrator) for image acquisition: (2) Aidoc Cloud Server (ACS) for image processing; and (3) Aidoc Desktop Application for workflow integration.
DICOM images are received, saved, filtered and de-identified before processing. Filtration matches metadata fields with keywords. Series are processed chronologically by running the algorithms on each series to detect suspected cases. The software then flags suspect cases by sending notifications to the desktop application, thereby facilitating triage and prioritization by the user. As the BriefCase software platform harbors several triage algorithms, the user may opt to filter out notifications by pathology, e.g., a chest radiologist may choose to filter out alerts on VO cases, and a neuro-radiologist would opt to divert PE alerts. Where several medical centers are linked to a shared PACS, a user may read cases for a certain center but not for another, and thus may opt to filter out alerts by center. Activating the filter does not impact the order in which notifications are presented in the Aidoc desktop application.
The desktop application feed displays all incoming suspect cases, each notified case in a line. Hovering over a line in the feed pops up a compressed, low-quality, grayscale, unannotated image that is captioned "not for diagnostic use" and is displayed as a preview function. This compressed preview is meant for informational purposes only, does not contain any marking of the findings, and is not intended for primary diagnosis beyond notification.
Presenting the users with worklist prioritization facilitates earlier triage by prompting the user to assess the relevant original images in the PACS. Thus, the suspect case receives attention earlier than would have been the case in the standard of care practice alone.
Here's a breakdown of the acceptance criteria and study details for the Aidoc Medical, Ltd. BriefCase device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Performance Goal) | Reported Device Performance | 95% Confidence Interval |
|---|---|---|---|
| Primary Endpoints | |||
| Sensitivity | 80% | 91.3% | 83.6%, 96.2% |
| Specificity | 80% | 85.6% | 80.6%, 89.7% |
| Secondary Endpoints | |||
| Time-to-Notification | Comparable to predicate device | 2.23 minutes | 2.22 - 2.23 minutes |
| NPV | Not explicitly stated | 98.9% | 4.66% - 99.4% |
| PPV | Not explicitly stated | 41.3% | 34.1% - 49.0% |
| PLR | Not explicitly stated | 6.34% | 97.9% - 8.63% |
| NLR | Not explicitly stated | 0.10% | 0.05% - 0.20% |
2. Sample Size for the Test Set and Data Provenance
- Sample Size: 342 cases
- Data Provenance: Retrospective, from 5 US-based clinical sites. The cases were distinct in time or center from the cases used to train the algorithm.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: 3
- Qualifications: US board-certified Neurologists.
4. Adjudication Method for the Test Set
- Method: Majority voting among the three expert reviewers.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No MRMC comparative effectiveness study involving human readers with and without AI assistance was described in the provided text. The study primarily focused on the standalone performance of the AI algorithm.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- Yes, a standalone study was conducted. The performance metrics (sensitivity, specificity, time-to-notification, etc.) are reported for the BriefCase software's analysis of head CTA images in identifying Vessel Occlusion (VO).
7. Type of Ground Truth Used
- Expert consensus (as determined by 3 expert US board-certified Neurologists reviewers, using majority voting).
8. Sample Size for the Training Set
- The document states that the test set cases were "all distinct in time or center from the cases used to train the algorithm," but it does not specify the sample size of the training set. There is also a mention of an "additional enriched dataset...for vessel segment-subgroup analysis on 165 positive vessel occlusions cases," though it's unclear if this was part of the original training or a supplementary dataset.
9. How the Ground Truth for the Training Set Was Established
- This information is not explicitly stated in the provided text. It is only mentioned that the algorithm was "trained on VO vs LVO (M1) images" and "deep learning algorithm trained on medical images," but the method for establishing ground truth for these training images is not detailed.
§ 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.