Medical Video Center

Predicting Epilepsy Surgery Outcomes with Deep Learning

Using deep learning, a subset of artificial intelligence involving statistical computation, MUSC Health neurologists have developed a new method that may one day help both patients with medication-refractory epilepsy and their physicians weigh the pros and cons of brain surgery. In addition to the potential clinical implications, these findings, published in the September 2018 issue of Epilepsia, highlight how artificial intelligence is driving change in the medical field. 

Although brain surgery is often recommended to patients who do not respond to medication, many hesitate, in part due to the operative risks and in part due to limited success. To overcome this, Leonardo Bonilha, M.D., Ph.D., and his team searched for a better way to predict which patients are likely to be seizure free after surgery. 

The team turned to deep learning due to the massive amount of data analysis required. “In this study, we incorporated advanced neuroimaging and computational techniques to anticipate surgical outcomes with the goal of enhancing quality of life,” explains Neurology Department Chief Resident Ezequiel Gleichgerrcht, M.D. 

The whole-brain connectome, the key component of this study, is a map of all physical connections in a person’s brain. The map is created by in-depth analysis of diffusion magnetic resonance imaging (dMRI), which patients receive as standard- of-care prior to surgery. The neurologists used deep learning to examine the connectome, allowing for patterns to be automatically learned. 

Today, post-surgery outcomes are predicted using clinical variables that are only 50 percent accurate, while deep learning predictions were 79-88 percent accurate. 

“We are using artificial intelligence as an extra tool to make better informed decisions regarding a surgical intervention that may hold the hope for a cure of epilepsy in many patients,” summarizes Gleichgerrcht. 

--CAROLINE WALLACE
Source: Progressnotes Fall 2018


Powered by the BroadcastMed Network