BriefCase

BriefCase is an AI-powered software designed to expedite the triage of non-enhanced head CT scans by rapidly identifying and notifying clinicians of suspected Intracranial Hemorrhage in adult and transitional adolescent patients. Its methodology relies on a deep learning algorithm, trained on an extensive dataset, to analyze images in parallel with standard workflows, significantly reducing time-to-notification and demonstrating high sensitivity and specificity for ICH detection.

BriefCase is a radiological computer-aided triage and notification software designed to analyze non-enhanced head CT images for adults and transitional adolescents aged 18 and older. Its primary purpose is to assist hospital networks and appropriately trained medical specialists in workflow triage by flagging and communicating suspected positive findings of Intracranial Hemorrhage (ICH) pathologies. The system utilizes an artificial intelligence algorithm to analyze DICOM images, highlighting cases with detected findings on a standalone desktop application that operates in parallel with the standard of care image interpretation. It provides notifications, including compressed, non-diagnostic preview images, to alert clinicians to potential ICH cases, but importantly does not alter the original medical images and is not intended for diagnostic use beyond notification; clinical judgment based on original images remains paramount. The BriefCase system architecture includes an Aidoc Hospital Server for image acquisition, an Aidoc Cloud Server for AI-based image processing, and an Aidoc Desktop Application for workflow integration and notification display. DICOM images are de-identified and processed chronologically, with the software flagging suspected cases and sending notifications to the desktop application, thereby facilitating user prioritization. A pivotal multicenter study involving 220 cases demonstrated high performance, with a sensitivity of 96.15% and specificity of 94.83% for ICH detection, exceeding the 80% performance goal. The device also showed a mean time-to-notification of 33.5 seconds for true positive cases, facilitating earlier attention to critical findings. This version of BriefCase features improved algorithm performance due to training on a larger dataset compared to its predicate.

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 algorithm's performance vary with different subtypes or severities of Intracranial Hemorrhage (e.g., epidural, subdural, subarachnoid, intraparenchymal)?; What was the composition and size of the "larger data set" used for training the improved algorithm, and how does it compare to the dataset used for the predicate device?; While race distribution was unavailable for the study, were there any investigations into potential performance biases related to other demographic factors or image acquisition parameters from different scanner models/manufacturers?; What is the practical false positive notification rate in a real-world, high-volume clinical setting, and what is the typical clinician response or workflow impact when a false positive is flagged by BriefCase?; Are there plans to expand the BriefCase platform's capabilities to detect other acute neurological conditions beyond ICH on non-enhanced head CTs, or to analyze other imaging modalities or anatomical regions?