Impact of Internet Derived Information Obstruction Treatment (IDIOT) Syndrome-a student cohort study

Abstract

Internet Derived Information Obstruction Treatment (IDIOT) Syndrome, a modern phenomenon caused by the constant availability of internet medical content, has received attention for its impact on mental health. It explains the pattern of frequent, excessive health-related internet searches that cause increased anxiety and distress. This study looks into the frequency and impact of IDIOT Syndrome among technical students. It attempts to look into mental health issues caused by frequent health-related searches and suggests Risk Score using machine learning and deep learning models.A survey was conducted among 450 technical students, collecting data on search frequency, time spent on health searches, and website visits. Pre-processing included normalization, TF-IDF feature engineering, and risk level encoding. Random Forest Classifier and Linear Regression were used for classification and prediction, with statistical validation to ensure data reliability.

Excessive health searches correlated with increased anxiety. High-risk individuals spent 82.5 minutes daily on searches and visited health websites 20 times weekly. The Random Forest model had 68% accuracy, while Linear Regression predicted risk scores with R² as 0.62 and MSE as 1.35. Cronbach's Alpha was 0.87, according to the statistical analysis.  This study focuses the importance of machine learning in determining IDIOT Syndrome risk levels and their harmful impacts. The findings represent the need for early intervention. Future research should explore real-time monitoring, sentiment analysis, and larger sample sizes for improved accuracy.