Machine Learning Optimizes Outcome Prediction in Traumatic Brain Injuries

University of Pittsburgh School of Medicine data scientists and UPMC neurotrauma surgeons have created a prognostic model that uses automated brain scans and machine learning to inform outcomes in patients with severe traumatic brain injuries (TBI). Their findings are published in the journal Radiology, in a paper titled, "Outcome Prediction in Patients with Severe Traumatic Brain Injury Using Deep Learning from Head CT Scans." The researchers demonstrated that their advanced machine-learning algorithm can analyze brain scans and relevant clinical data from TBI patients to quickly and accurately predict survival and recovery six months after the injury. "Every day, in hospitals across the United States, care is withdrawn from patients who would have otherwise returned to independent living," said co-senior author David Okonkwo, MD, PhD, professor of neurological surgery at Pitt and UPMC. "The majority of people who survive a critical period in an acute care setting make a meaningful recovery--which further underscores the need to identify patients who are more likely to recover."