Neurologists from Stanford University have been working with a specialist in computer music to develop a diagnostic tool that can translate the brain’s activity into sounds so that so-called silent seizures can be detected.
“This technology will enable nurses, medical students and physicians themselves to actually assess their patient right there and they will be able to determine if the patient is having silent seizures,” said Josef Parvizi, a professor of neurology and neurological sciences.
The desire for a brain “stethoscope” was driven by the fact that many epileptic seizures go undetected and untreated. Although people may think that seizures cause convulsions, that is not actually the case, particularly among critically ill patients in intensive care units, explains Parvizi. Almost 90% of those patients will have silent seizures that, although though not visible, can still damage the brain if they are prolonged.
Parvizi says the solution to this problem was reached after watching Kronos Quartet perform a piece of music based on data recorded by a scientific instrument aboard the Voyager space probe.
He thought something similar could be done using recordings brain-wave data and so sent this information to music professor Chris Chafe, who used it to modulate the singing sounds of a computer-synthesized voice.
Once he sent me the files and I listened to them, I was literally in shock, because it was so intuitive. You could hear the transition from non-seizure to seizure so easily, that I just basically picked up the phone and told Chris that we have something right here.”
Josef Parvizi, Professor at Stanford University
To test whether people other than neurologists could hear the difference between normal brain activity and a seizure using the brain stethoscope, medical student Kapil Gururangan and clinical assistant professor of neurology Babak Razavi, gathered 84 electroencephalograms or EEGs, 32 of which included either a seizure or features typical of one.
They turned the EEG samples into music using Chafe’s algorithm and played them to 34 medical students and 30 nurses at Stanford.
Despite not being trained in epilepsy, the students and nurses were able to discern seizures and seizure-like events from normal brain waves and accurately detect seizures more than 95% of the time. They also accurately identified samples with seizure-like features about 75% of the time.
The question now that we have to figure out is: How are actual physicians going to use this tool and how do physicians use this information in their decision-making?”