Author Interviews, Brain Injury, CT Scanning, Emergency Care, Lancet, Technology / 16.10.2018
AI: Deep Learning Algorithms Can Detect Critical Head CT Findings
MedicalResearch.com Interview with:
Sasank Chilamkurthy
AI Scientist,
Qure.ai
MedicalResearch.com: What is the background for this study?
Response: Head CT scan is one of the most commonly used imaging protocols besides chest x-ray. They are used for patients with symptoms suggesting stroke, rise in intracranial pressure or head trauma. These manifest in findings like intracranial haemorrhage, midline shift or fracture.
Scans with these critical findings need to be read immediately. But radiologists evaluate the scans on first-come-first-serve basis or based on stat/routine markers set by clinicians. If the scans with critical findings are somehow pushed to the top of radiologists’ work list, it could substantially decrease time to diagnosis and therefore decrease mortality and morbidity associated with stroke/head trauma.
Sasank Chilamkurthy
AI Scientist,
Qure.ai
MedicalResearch.com: What is the background for this study?
Response: Head CT scan is one of the most commonly used imaging protocols besides chest x-ray. They are used for patients with symptoms suggesting stroke, rise in intracranial pressure or head trauma. These manifest in findings like intracranial haemorrhage, midline shift or fracture.
Scans with these critical findings need to be read immediately. But radiologists evaluate the scans on first-come-first-serve basis or based on stat/routine markers set by clinicians. If the scans with critical findings are somehow pushed to the top of radiologists’ work list, it could substantially decrease time to diagnosis and therefore decrease mortality and morbidity associated with stroke/head trauma.











Dr. Adrian Harel[/caption]
Dr. Adrian Harel, PhD
Chief Executive Officer
Medicortex Finland
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: Every 15 seconds, someone in the United States suffers a new head injury. Of the 2.5M people treated in hospital emergency rooms each year, 80,000 become permanently disabled because of TBI. Currently, there are no reliable diagnostic tests to assess the presence or severity of an injury on-site, nor are there any pharmaceutical therapies that could stop the secondary injury from spreading. Accurate diagnostics would benefit especially mild cases of TBI (concussions), which, if occurring repeatedly, may cause neurodegenerative conditions such as Chronic Traumatic Encephalopathy (which is typical for athletes in NFL and Ice-hockey).
We have performed extensive preclinical research comparing fluid biopsies from normal and injured lab animals. The results showed some unique biomarkers released as a biodegradation products after head injury. The data served as the basis and confirmation for our patent applications to protect the biomarker concept.
Medicortex has completed a clinical proof-of-concept trial in collaboration with Turku University Hospital (Tyks). Samples from 12 TBI patients and 12 healthy volunteers were collected and analyzed for the presence and for the level of the biomarker in state-of-the-art laboratories. The study demonstrated the diagnostic potential of the new biomarker in humans and it confirmed the prior preclinical findings. This was a significant milestone for Medicortex.













