Artificial intelligence for children with attention deficit/hyperactivity disorder: a scoping review DOI Creative Commons
Bo Sun, Fei Cai, Hui‐Man Huang

et al.

Experimental Biology and Medicine, Journal Year: 2025, Volume and Issue: 250

Published: April 24, 2025

Attention deficit/hyperactivity disorder is a common neuropsychiatric that affects around 5%-7% of children worldwide. Artificial intelligence provides advanced models and algorithms for better diagnosis, prediction classification attention disorder. This study aims to explore artificial used the prediction, early diagnosis as reported in literature. A scoping review was conducted line with PRISMA-ScR (Preferred Reporting Items Systematic Reviews Meta-Analyses Extension Scoping Reviews) guidelines. Out 1994 publications, 52 studies were included review. The articles use 3 different purposes. Of these articles, techniques mostly (38/52, 79%). Magnetic resonance imaging (20/52, 38%) most frequently data articles. Most sets size <1,000 samples (28/52, 54%). Machine learning prominent branch studies, support vector machine algorithm (34/52, 65%). commonly validation k-fold cross-validation higher level accuracy (98.23%) found Convolutional Neural Networks algorithm. an overview research on disorder, providing further clinical decision-making healthcare.

Language: Английский

Enhancing task fMRI individual difference research with neural signatures DOI Creative Commons
David A. A. Baranger, Aaron J. Gorelik, Sarah E. Paul

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 31, 2025

Abstract Task-based functional magnetic resonance imaging (tb-fMRI) has advanced our understanding of brain-behavior relationships. Standard tb-fMRI analyses suffer from limited reliability and low effect sizes, machine learning (ML) approaches often require thousands subjects, restricting their ability to inform how brain function may arise contribute individual differences. Using data 9,024 early adolescents, we derived a classifier (‘neural signature’) distinguishing between high working memory loads in an emotional n-back fMRI task, which captures differences the separability activation two task conditions. Signature predictions were more reliable had stronger associations with performance, cognition, psychopathology than standard estimates regional activation. Further, signature was sensitive required smaller training sample (N=320) ML approaches. Neural signatures hold tremendous promise for enhancing informativeness research revitalizing its use.

Language: Английский

Citations

0
Artificial intelligence for children with attention deficit/hyperactivity disorder: a scoping review DOI Creative Commons
Bo Sun, Fei Cai, Hui‐Man Huang

et al.

Experimental Biology and Medicine, Journal Year: 2025, Volume and Issue: 250

Published: April 24, 2025

Attention deficit/hyperactivity disorder is a common neuropsychiatric that affects around 5%-7% of children worldwide. Artificial intelligence provides advanced models and algorithms for better diagnosis, prediction classification attention disorder. This study aims to explore artificial used the prediction, early diagnosis as reported in literature. A scoping review was conducted line with PRISMA-ScR (Preferred Reporting Items Systematic Reviews Meta-Analyses Extension Scoping Reviews) guidelines. Out 1994 publications, 52 studies were included review. The articles use 3 different purposes. Of these articles, techniques mostly (38/52, 79%). Magnetic resonance imaging (20/52, 38%) most frequently data articles. Most sets size <1,000 samples (28/52, 54%). Machine learning prominent branch studies, support vector machine algorithm (34/52, 65%). commonly validation k-fold cross-validation higher level accuracy (98.23%) found Convolutional Neural Networks algorithm. an overview research on disorder, providing further clinical decision-making healthcare.

Language: Английский

Citations

0