(196 days)
BriefCase is a radiological computer aided triage and notification software indicated for use in the analysis of chest CTs (with or without contrast). The device is intended to assist hospital networks and appropriately trained medical specialists in workflow triage by flagging and communication of suspect cases of three or more acute Rib fracture (RibFx) pathologies.
BriefCase uses an artificial intelligence algorithm to analyze images and flag suspect cases on a standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for suspect cases. 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 svstem is based on an algorithm programmed component and is comprised 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) for image acquisition; (2) Aidoc Cloud Server (ACS) for image processing; and (3) Aidoc Worklist Application for workflow integration, installed on the radiologist' desktop and provides the user interface in which notifications from the BriefCase software are received.
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 Worklist desktop application, thereby prompting triage and prioritization by the attending radiologist. 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 notifications on LVO cases, and a neuro-radiologist would opt to divert PE notifications. 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 notification by center. Activating the filter does not impact the order in which notifications are presented in the Aidoc worklist application.
The Worklist Application displays the pop-up text notifications of new suspected studies when they come in. Notifications are in the form of a small pop-up containing patient name, accession number and the relevant pathology (e.g., RibFx). A list of all incoming suspect cases is also displayed. Hovering over a notification or a case in the worklist 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 radiologist with notification facilitates earlier triaqe 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 summary of the acceptance criteria and study details for the Aidoc Medical, Ltd.'s BriefCase for RibFx Triage device, based on the provided document:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| AUC >= 0.95 (lower bound of 95% CI) | AUC: 0.976 (95% CI: 0.960, 0.991) |
| Sensitivity >= 80% (lower bound of 95% CI) | Sensitivity: 96.7% (95% CI: 90.6%, 99.6%) |
| Specificity >= 80% (lower bound of 95% CI) | Specificity: 90.4% (95% CI: 85.2%, 94.3%) |
Study Details
2. Sample Size and Data Provenance for Test Set
- Sample Size (Test Set): 279 cases (91 ground truth positive cases with 3+ rib fractures, 188 ground truth negative cases).
- Data Provenance:
- Country of Origin: 3 clinical study sites (2 in the US, 1 outside the US). 70.9% of cases were from US sites.
- Retrospective/Prospective: Retrospective.
3. Number of Experts and Qualifications for Ground Truth (Test Set)
- Number of Experts: Two radiologists.
- Qualifications: Not explicitly stated beyond "radiologists."
4. Adjudication Method for Test Set
- Adjudication Method: Two radiologists performed ground truthing, with an additional third radiologist used to resolve inconsistencies. This implies a 2+1 adjudication model.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study: No, a standalone (algorithm only) performance study was conducted. There is no mention of a human-in-the-loop study to evaluate the improvement of human readers with AI assistance.
- Effect Size of Human Readers Improvement (if applicable): Not applicable as no MRMC study was performed. However, a secondary endpoint evaluated a "time-to-notification" metric to suggest potential clinical benefit for workflow prioritization.
6. Standalone (Algorithm Only) Performance Study
- Standalone Study: Yes, the primary endpoint evaluated the software's performance (AUC, Sensitivity, Specificity) in identifying rib fractures on its own.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (two radiologists with a third for inconsistencies).
8. Sample Size for Training Set
- Sample Size (Training Set): Not explicitly provided in the excerpt. The document states "No patient data were reused between the training and the pivotal datasets."
9. How the Ground Truth for the Training Set Was Established
- Ground Truth Establishment (Training Set): Not explicitly detailed in the excerpt. It states the model was "trained" on RibFx images, but the method for establishing the ground truth for those specific training images is not described. It can be inferred that a similar expert review process would have been used.
§ 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.