JLK-SDH

“JLK-SDH is a notification-only, parallel workflow tool that is intended to assist trained radiologists to identify and communicate images of specific patients to a specialist, independent of the standard of care workflow. JLK-SDH uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate user of these findings in parallel to standard of care image interpretation. JLK-SDH is a radiological computer-assisted triage and notification (CADt) software package compliant with the DICOM standard.”

“JLK-SDH uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate user of these findings in parallel to standard of care image interpretation. Utilizing an artificial intelligence algorithm, the system automatically receives and analyzes NCCT studies for image features indicating the presence of SDH and sends a notification to alert a radiologist of the case. The training dataset utilized to develop the convolutional neural network (CNN) included 29,524 non-contrast CT (NCCT) scans that had been obtained in patients with and without intracranial hemorrhage. This broad collection of both US and Out-of-US data ensures that the Al model is trained on a diverse set of cases, enhancing its applicability across different populations and clinical environments. Both the subject and predicate devices utilize artificial intelligence and machine learning (AI/ML) algorithms and mobile notification software to identify and notify specialists, respectively, of patients with the presence of suspected subdural hemorrhage (SDH) on non-contrast CT imaging of the head.”