Neurology Machine Learning Improves Early Surgery Referrals for Epilepsy Patients
Published July 2021 | Acta Neurologica Scandinavica
An artificial intelligence algorithm developed at Cincinnati Children’s can identify epilepsy surgery candidates earlier in the disease process.
Judith Dexheimer, PhD, and colleagues Hansel Greiner, MD, and Ben Wissel, PhD, MD-PhD candidate at the University of Cincinnati, have completed multiple studies to verify the algorithm’s methods, check for racial bias, and guide the tools to improve the technology.
The algorithm runs on a software program embedded into a hospital’s electronic health record (EHR). Using natural language processing techniques, it analyzes previous provider notes for each patient with an upcoming appointment in the epilepsy clinic. The algorithm considers the words, tone, and themes in the notes, and uses a scoring system to identify patients who meet neurosurgical criteria.
When patients are identified, the algorithm sends reminders to providers. Doctors who receive notices are three times more likely to refer patients for a surgery consult, Dexheimer says.
The team soon will deploy the device at UC Health in Cincinnati and at other pediatric centers and community hospitals to verify its use at other centers and answer the question, “Can we use it at a community hospital and identify patients who should be referred to a specialty hospital?” Greiner says.
Currently there is no universal standard for neurosurgical intervention referrals for adults or children. The goal is to reduce the time to initial surgery evaluation for patients with intractable epilepsy. The national average in pediatrics is 10 years.
The machine learning algorithm is a collaborative project from the John Pestian Lab at Cincinnati Children’s and the hospital’s divisions of Biostatistics and Epidemiology, Emergency Medicine, Biomedical Informatics, Neurology, and Neurosurgery.
