Taiwanese Researchers Develop Model to Identify Internet Addiction

A research team from Taiwan has successfully developed a machine-learning model that uses electroencephalography (EEG) to identify individuals suffering from Internet addiction with an impressive accuracy rate of 86 percent. This breakthrough was announced at a press conference on March 15, 2024, by Huang Hsu-wen, an assistant investigator at the National Health Research Institutes’ National Center for Geriatrics and Welfare Research.

The study analyzed the brain wave patterns of 92 participants, which included 42 individuals diagnosed with Internet addiction and 50 healthy control subjects. Researchers observed that those in the addicted group exhibited heightened levels of phase synchronization in their resting-state EEG functional connectivity. Huang noted that these changes could be attributed to disruptions in neural systems associated with inhibitory control and reward pathways.

The findings suggest that alterations in EEG patterns may occur even before the behavioral symptoms of addiction become apparent. This highlights the potential for EEG testing, when combined with machine-learning classification models, to detect early warning signs of Internet addiction. Such early identification could empower schools and medical institutions to implement targeted interventions more effectively.

Internet addiction is characterized by prolonged online engagement, an inability to limit internet use, and a sense of discomfort when disconnected from the online world. The research was published in the journal Psychological Medicine in May 2023 and included contributions from experts such as Wu Shun-chi, a professor at National Tsing Hua University, and Huang Chih-mao, an associate professor at the University of Hong Kong, along with various research institutions in Taiwan and abroad.

The implications of this study are significant as it opens new avenues for understanding and addressing Internet addiction, a growing concern in today’s digital age. By leveraging advanced technology, researchers aim to provide clearer pathways for early detection and intervention, ultimately improving mental health outcomes for those at risk.