Machine Learning for Early Detection of Hypoxic‑Ischemic Brain Injury After Cardiac Arrest



    • Despite the many advances in the field of resuscitation post cardiac arrest, hypoxic-ischemic brain injury (HIBI) leaves many survivors with severe neurological disability. Patients who remain comatose at 24–72 h or more after resuscitation undergo neuroprognostication, aimed to detect signs of HIBI and predict projected long-term neurological function.
    • Establishing whether a patient who survived a cardiac arrest has suffered HIBI shortly after return of spontaneous circulation (ROSC) can be of paramount importance for informing families and identifying patients who may benefit the most from neuroprotective therapies. The radiographic hallmark of HIBI is cerebral edema, commonly evaluated on head computed tomography (HCT) as effacement of sulci and diminished gray–white matter differentiation in cortical and deep brain structures.
    • The faculty inventor developed a deep learning (AI) technique which automatically assesses the very first initial HCT scan based on a deep Transfer Learning technique developed for the early detection of HIBI after cardiac arrest.
    • The technology allows accurate identification of a HCT signature of  HIBI within the first 3 hours after ROSC in comatose survivors of a cardiac arrest rather than the reliance of a series of follow-up scans at later timepoints that confer much lower sensitivity. 








    • This is a unique approach as there are no imaging-based method/analyses to identify early on whether or not a patient will exhibit Hypoxic Ischemic Brain Injury (HIBI).
    • The AI system improves prognosis of surviving patients of Hypoxic Ischemic Brain Injury (HIBI) after cardiac arrest by allowing and facilitating earlier treatment.
    • The system also helps in clinical treatment decisions for broad patient segment demonstrating similar symptoms.
    • These AI algorithms are easily integrated into a multitude of image analysis software packages which are commercially available and already deployed in clinical settings. 





    Reference ID

    Have Questions?

    Michael Hinton

    Contact Michael Hinton, Manager, Technology Marketing, who can provide more detail about this technology, discuss the licensing process, and connect you with the inventor.

    This site uses cookies and other tracking technologies to assist with navigation and your ability to provide feedback, analyze your use of products and services, assist with our promotional and marketing efforts.