Research Projects

The COVID-19 pandemic significantly increased children's screen time due to limited outdoor play and social interaction, leading to concerns about its impact on brain development. Prolonged exposure to blue light-emitting devices like televisions, tablets, and smartphones has been linked to behaviors resembling autism, known as "pseudo-autism" or "virtual autism." These behaviors include reduced social engagement, impaired eye contact, repetitive movements, and delayed speech development. Unlike autism, which has genetic causes, pseudo-autism is triggered by excessive screen use and can improve when screen time is reduced and children re-engage in real-world activities. Despite these observations, screen addiction disorder (SAD) remains an underexplored condition. Currently, there are no established diagnostic tools or targeted interventions for pseudo-autism or SAD, presenting a gap in managing the growing issue of screen dependency in children. This project, "GadgetsGhatao," seeks to address this public health concern by providing a neurobiological framework for identifying, assessing, and managing screen addiction in children. The primary objective of this project is to develop standardized neurosignal biomarkers to facilitate early detection, assess severity, and differentiate SAD from other developmental issues. This will be achieved by analyzing electroencephalogram (EEG) data to identify unique brainwave patterns associated with SAD. Machine learning models will be applied to classify SAD based on these brainwave data, offering reliable diagnostic criteria and enabling personalized intervention strategies to support children affected by excessive screen use. Current research highlights that screen addiction is increasingly recognized as a behavioral disorder with neurological, psychological, and clinical effects; however, standardized EEG biomarkers specific to SAD remain undeveloped. Observational studies and preliminary EEG research indicate altered brainwave patterns in SAD, but limited sample diversity and lack of screen usage variation hinder defining precise EEG markers for screen addiction. This project aims to bridge these gaps by creating standardized EEG biomarkers tailored to SAD, improving early detection and distinguishing SAD from autism or other developmental issues. The "GadgetsGhatao" project further investigates how different screen types uniquely affect brain function to better understand digital engagement’s influence on child development. Through machine learning models, it will classify SAD severity and identify EEG patterns linked to addiction intensity, aiming to create intervention strategies that promote a shift from screen dependency to healthier digital habits. This project lays essential groundwork for managing screen dependency disorders, particularly pseudo-autism, by developing neurosignal biomarkers and ML diagnostic tools to support children’s neurological health amidst growing screen exposure.