Objective ADHD Diagnosis Using Convolutional Neural Networks Over Daily-Life Activity Records

Attention Deficit/Hyperactivity Disorder (ADHD) is the most common neurobehavioral disorder in children and adolescents. However, its etiology is still unknown, and this hinders the existence of reliable, fast and inexpensive standard diagnostic methods. Objective: This paper proposes an end-to-end...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2020-09, Vol.24 (9), p.2690-2700
Main Authors: Amado-Caballero, Patricia, Casaseca-de-la-Higuera, Pablo, Alberola-Lopez, Susana, Andres-de-Llano, Jesus Maria, Villalobos, Jose Antonio Lopez, Garmendia-Leiza, Jose Ramon, Alberola-Lopez, Carlos
Format: Article
Language:English
Subjects:
actigraphy
ADHD
Artificial neural networks
Attention deficit hyperactivity disorder
Children
Convolutional Neural Network (CNN)
Deep learning
Diagnosis
Diagnostic systems
Electroencephalography
Etiology
Functional magnetic resonance imaging
Machine learning
Medical diagnosis
Neural networks
Pediatrics
Sleep
Spectrograms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Attention Deficit/Hyperactivity Disorder (ADHD) is the most common neurobehavioral disorder in children and adolescents. However, its etiology is still unknown, and this hinders the existence of reliable, fast and inexpensive standard diagnostic methods. Objective: This paper proposes an end-to-end methodology for automatic diagnosis of the combined type of ADHD. Methods: Diagnosis is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks to classify spectrograms of activity windows. Results: We achieve up to {\text{97.62}\%} average sensitivity, {\text{99.52}\%} specificity and AUC values over {\text{99}\%}. Overall, our figures overcome those obtained by actigraphy-based methods reported in the literature as well as others based on more expensive (and not so convenient) acquisition methods. Conclusion: These results reinforce the idea that combining deep learning techniques together with actimetry can lead to a robust and efficient system for objective ADHD diagnosis. Significance: Reliance on simple activity measurements leads to an inexpensive and non-invasive objective diagn-ostic method, which can be easily implemented with daily devices.
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2020.2964072