Multiple screen addiction and neurological complaints in adolescents: A machine learning-based classification model.

INTRODUCTION

Multiple screen addiction is a growing public health problem, especially among young people. Early detection and classification of screen addiction are important for the prevention of neurological complaints.

OBJECTIVE

The current study aimed to determine the status of multiple screen addiction with machine learning and to identify the relationship between multiple screen addiction and neurological complaints.

METHODS

This cross-sectional and correlational study was conducted with 406 participants. The data were collected from November 13, 2023, to March 4, 2024, in the neurology outpatient clinic of a training and research hospital. The dataset created in the study was trained with machine learning algorithms, and classification was provided. K-Nearest Neighbors (KNN), Ensemble, Support Vector Machine (SVM), Decision Tree machine learning algorithms, and Confusion Matrix were used for classification.

RESULTS

In the study, KNN was the algorithm with the highest classification performance, while Decision Tree was the algorithm with the worst performance. Moreover, it was determined that multiple screen addiction and neurological complaints were related, and these complaints were successfully evaluated through machine learning classification.

CONCLUSIONS

Multi-screen addiction is closely linked to numerous neurological complaints, and machine learning can effectively uncover and analyze this association. As a foundational step, this study paves the way for family physicians and healthcare professionals to utilize machine learning in calculating individuals' addiction scores, monitoring addiction patterns, and providing personalized recommendations.