Constable Paul A, Pinzon-Arenas Javier O, Mercado Diaz Luis Roberto, Lee Irene O, Marmolejo-Ramos Fernando, Loh Lynne, Zhdanov Aleksei, Kulyabin Mikhail, Brabec Marek, Skuse David H, Thompson Dorothy A, Posada-Quintero Hugo
Caring Futures Institute, College of Nursing and Health Sciences, Flinders University, Adelaide 5000, SA, Australia.
Biomedical Engineering Department, University of Connecticut, Storrs, CT 06269, USA.
Bioengineering (Basel). 2024 Dec 28;12(1):15. doi: 10.3390/bioengineering12010015.
Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity disorder (ADHD). In a series of ERGs collected in ASD ( = 77), ADHD ( = 43), ASD + ADHD ( = 21), and control ( = 137) groups, this analysis explores the use of machine learning and feature selection techniques to improve the classification between these clinically defined groups. Standard time domain and signal analysis features were evaluated in different machine learning models. For ASD classification, a balanced accuracy (BA) of 0.87 was achieved for male participants. For ADHD, a BA of 0.84 was achieved for female participants. When a three-group model (ASD, ADHD, and control) the BA was lower, at 0.70, and fell further to 0.53 when all groups were included (ASD, ADHD, ASD + ADHD, and control). The findings support a role for the ERG in establishing a broad two-group classification of ASD or ADHD, but the model's performance depends upon sex and is limited when multiple classes are included in machine learning modeling.
视网膜电图（ERG）显示了典型发育人群与被诊断为自闭症谱系障碍（ASD）或注意力缺陷多动障碍（ADHD）的人群之间的差异。在一系列收集自ASD组（n = 77）、ADHD组（n = 43）、ASD + ADHD组（n = 21）和对照组（n = 137）的ERG中，本分析探索了使用机器学习和特征选择技术来改善这些临床定义组之间的分类。在不同的机器学习模型中评估了标准时域和信号分析特征。对于ASD分类，男性参与者的平衡准确率（BA）达到了0.87。对于ADHD，女性参与者的BA达到了0.84。当采用三组模型（ASD、ADHD和对照组）时，BA较低，为0.70，而当纳入所有组（ASD、ADHD、ASD + ADHD和对照组）时，BA进一步降至0.53。这些发现支持了ERG在建立ASD或ADHD的宽泛两组分类中的作用，但模型的性能取决于性别，并且在机器学习建模中纳入多个类别时受到限制。
