UCLA is well-known for its state-of-the-art medical center and cutting-edge research. On April 28, the UCLA Semel Institute for Neuroscience and Human Behavior announced that one of its graduate students, Wesley Kerr, and his trainees, Akash Patel and Sarah Barritt, were selected by the Council on Undergraduate Research to present their original research on Capitol Hill in Washington, D.C., on April 29. They will present their poster entitled “Computer-Aided Diagnosis of Epilepsy Using Clinical Information.” It outlines advances in the use of computational machine learning to help healthcare professionals detect and correctly diagnose epilepsy.
Kerr noted, “This is very exciting. It’s always nice to get exposure for our work.” Typically, the Posters on the Hill exhibit selects just one or two research projects from each state to participate in the prestigious event, explained Mark Cohen, Sr. Kerr’s faculty advisor and a professor-in-residence of psychiatry in the Semel Institute for Neuroscience and Human Behavior. He added, “A large fraction of patients with seizure disorder are misdiagnosed and treated inappropriately. As such treatments carry their own risks and negative side effects, their research could positively affect the lives of millions of Americans.”
The focus of the research was to estimate the probability of epilepsy versus non-epileptic seizures based on the historical factors reported by the patient to their neurologist. Kerr noted that distinguishing between epileptic and non-epileptic seizures presents a challenge. On average, the time from the first seizure to the diagnosis of non-epileptic seizures is seven years. During that period, a majority of those patients are misdiagnosed with epilepsy and treated inappropriately with anti-epileptic medications. He explained, “This can expose patients to serious, and potentially fatal, side effects. One of our laboratory’s goals is to create an automated system that can aid physicians in distinguishing patients with epileptic and non-epileptic seizures.”
The researchers accomplished the goal of their study by reviewing outpatient clinical notes from patients with a medication-resistant seizure disorder who were later diagnosed as having epilepsy or non-epileptic seizure disorder. This was accomplished via a state-of the-art diagnostic assessment method: 72- hour in-patient closed circuit video-electroencephalography (VEEG) monitoring. Via use of a combination of the known risk factors for epilepsy and non-epileptic seizures contained in 228 clinical notes reviewed by the team, their algorithm achieved a diagnostic accuracy of 65%. At first glance this percentage may appear low; however, it is comparable to the accuracy of neurologists prior to VEEG monitoring. For this research, they used a machine learning method known as a “decision tree.”
Kerr explained, “The structure of our decision tree also provided meaningful information about the interpretation of each risk factor in each patient. For example, the risk factors for non-epileptic seizures may not be the same for women and men. This work may help diagnose, and thereby more effectively treat, patients that are in need.” In addition to benefiting patients with a seizure disorder, the computer-aided diagnostic methods developed by the researchers may be applicable to the diagnosis of other diseases in the future.
As part of their trip to Washington, the research team will meet with California state senators and representatives. They will use this forum to emphasize the importance of appropriate diagnosis in epilepsy and the academic environment at UCLA that made this research possible.