BriefCase

BriefCase is an artificial intelligence-powered software designed to analyze non-enhanced head CT images for the detection of Intracranial Hemorrhage, providing rapid notifications to radiologists to expedite triage. Its methodology involves a deep learning algorithm processing images in parallel to standard care, aiming to significantly reduce the time to radiologist review for critical findings.

BriefCase is a radiological computer-aided triage and notification software designed to assist in the analysis of non-enhanced head CT images. Its primary purpose is to help hospital networks and radiologists improve workflow triage by flagging and communicating suspected findings of Intracranial Hemorrhage (ICH). The system utilizes an artificial intelligence algorithm, specifically a deep learning model trained on medical images, to process DICOM images. These images are received, de-identified, and analyzed chronologically. The software operates through three modules: an Aidoc Hospital Server, an Aidoc Cloud Server, and an Aidoc Worklist Application installed on the radiologist's desktop. When suspected ICH is detected, the Worklist Application provides pop-up notifications, including patient identifiers and a compressed, non-diagnostic preview image, prompting earlier review of the full images in the PACS system. This process runs in parallel with the standard of care, without altering original images or removing cases from the existing queue. The performance of BriefCase was evaluated in a retrospective, multicenter study involving 198 non-contrast head CT cases. The software demonstrated high accuracy in identifying ICH, achieving a sensitivity of 93.6% and a specificity of 92.3%, both exceeding the predefined 80% performance goal. A key secondary endpoint measured the potential clinical benefit in worklist prioritization. For 59 true positive ICH cases, the mean time-to-notification by BriefCase was 4.5 minutes, significantly shorter than the mean standard of care time-to-exam-open of 72.6 minutes. This resulted in a statistically significant mean time saving of approximately 68.1 minutes, highlighting the device's capability to facilitate earlier attention to critical cases. The results suggest BriefCase effectively improves triage efficiency by providing timely notifications for suspected ICH.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the BriefCase algorithm's performance (sensitivity and specificity) for ICH detection vary across different subtypes or severities of intracranial hemorrhage?; What is the real-world impact on patient outcomes or length of hospital stay when BriefCase is integrated into clinical workflow, beyond the measured time-to-notification?; How does the de-identification process ensure patient privacy while maintaining image integrity for accurate AI analysis, particularly when data is processed via a cloud server?; What are the computational requirements and processing time per study in a high-volume clinical setting, and how does this scale with increasing caseload?; Beyond ICH, are there plans to expand the BriefCase platform's AI capabilities to detect other acute neurological conditions visible on non-contrast head CTs?