Researchers from Korea, the U.S., and New Zealand have confirmed the possibility of diagnosing otorhinolaryngology and neurological diseases by combining artificial intelligence (AI) with electroencephalography (EEG), Seoul National University Bundang Hospital (SNUBH) said Wednesday.

The research team focused on the lack of real-life data to prove that when particular frequencies replace alpha waves in a brainwave, it can cause a variety of neurological disorders. Professors Song Jae-jin from SNUBH, Sven Vanneste from the University of Texas and Dirk De Ridder from the University of Otago led the research group,

The team expects that an accurate analysis of EEG could diagnose patients' otorhinolaryngology and neurological diseases, and also offer clues to identify the cause of the disease.

In line with its hypothesis, the EEG analysis revealed that current density was significantly different in 264 healthy subjects compared with control subjects -- 153 patients with tinnitus, 78 with chronic pain, 31 with Parkinson's disease, and 15 with depression.

Based on this information, researchers confirmed for the first time that by analyzing a person’s brain wave with a machine learning AI system they could differentiate healthy people from sick ones.

As a result, the AI system recorded a diagnose accuracy of 88 percent for tinnitus, 92 percent for chronic pain, 94 percent for Parkinson's disease and 75 percent for depression. The results of the study showed that AI system, based on EEG, is an objective diagnostic method for diseases.

“This study has significance as it opened up the possibility of developing an objective diagnostic method based on precision medicine such as artificial intelligence,” Professor Song said. “I would like to develop an objective diagnosis method of various otolaryngology, neurology, and mental health medical diseases through continuous large-scale research on the matter.”

The results of the research were published in the latest issue of Nature Communications.