Related Experiment Video
Updated: May 3, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
8.1K
Multiple screen addiction and neurological complaints in adolescents: A machine learning-based classification model
Seda Göger1, Elif Sarica Darol2, Süleyman Uzun3
1Sakarya University, Vocational School of Health Services, Sakarya, Türkiye.
Acta Psychologica
|February 22, 2026
Summary
Multiple screen addiction is linked to neurological issues. Machine learning effectively identified this connection, aiding early detection and personalized care for this growing public health concern.
Area of Science:
- Neurology
- Public Health
- Machine Learning
Background:
- Multiple screen addiction is a significant public health issue, particularly affecting young individuals.
- Early identification and classification of screen addiction are crucial for preventing neurological complications.
Purpose of the Study:
- To assess multiple screen addiction using machine learning.
- To investigate the correlation between multiple screen addiction and neurological complaints.
Main Methods:
- A cross-sectional study involving 406 participants was conducted.
- Machine learning algorithms (KNN, Ensemble, SVM, Decision Tree) were employed for classification.
- Data were collected from a neurology outpatient clinic between November 2023 and March 2024.
Main Results:
- The K-Nearest Neighbors (KNN) algorithm demonstrated the highest classification performance.
- The Decision Tree algorithm showed the lowest classification performance.
- A significant relationship was found between multiple screen addiction and neurological complaints, successfully classified by machine learning.
Conclusions:
- Multiple screen addiction is strongly associated with various neurological complaints.
- Machine learning provides an effective tool for analyzing this association.
- This research supports the use of machine learning by healthcare professionals for addiction scoring, monitoring, and personalized interventions.
