Jacquelyn Corley, MD, is a neurosurgical resident at Duke Neurosurgery in Raleigh, N.C.
Complex neurosurgical procedures require intricate care, particularly in cases of traumatic brain injury. Operating has the potential to save a patient's life but also carries risk if something goes wrong.
Researchers are developing artificial intelligence systems to predict outcomes and help surgeons decide whether to operate on patients with traumatic brain injury.
Three insights on AI in neurosurgery, according to Dr. Corley via Stat News:
1. AI has been enabled by advances in patient data from EHRs and innovations in patient monitoring and imaging. Computers can learn by recognizing patterns in sample training data and apply new rules to patient data for more accurate diagnoses and treatments.
2. Neurosurgeons are using statistical models without AI to make decisions. The International Mission for Prognosis and Analysis of Clinical Trials in traumatic brain injury model enters key data into the algorithm and the computer calculates the probability of death or disability six months after the incident.
3. AI could make outcome predictions more accurate. A study from Burlington-based University of Vermont demonstrated that artificial neural networks have better predictive abilities for traumatic brain injury patients than seasoned neurosurgeons.