Noriaki Yahata 1 , 2 , 3 , Jun Morimoto 4 , Ryuichiro Hashimoto 3 , 5 , 6 , Giuseppe Lisi 4 , Kazuhisa Shibata 3 , 7 , Yuki Kawakubo 8 , Hitoshi Kuwabara 9 , Miho Kuroda 8 , 10 , Takashi Yamada 3 , 5 , Fukuda Megumi 3 , 11 , Hiroshi Imamizu 3 , 12 , José E. Náñez Sr 13 , Hidehiko Takahashi 14 , Yasumasa Okamoto 15 , Kiyoto Kasai 16 , Nobumasa Kato 5 , Yuka Sasaki a , 3 , 7 , Takeo Watanabe 3 , 7 , Mitsuo Kawato a , 3
14 April 2016
Although autism spectrum disorder (ASD) is a serious lifelong condition, its underlying neural mechanism remains unclear. Recently, neuroimaging-based classifiers for ASD and typically developed (TD) individuals were developed to identify the abnormality of functional connections (FCs). Due to over-fitting and interferential effects of varying measurement conditions and demographic distributions, no classifiers have been strictly validated for independent cohorts. Here we overcome these difficulties by developing a novel machine-learning algorithm that identifies a small number of FCs that separates ASD versus TD. The classifier achieves high accuracy for a Japanese discovery cohort and demonstrates a remarkable degree of generalization for two independent validation cohorts in the USA and Japan. The developed ASD classifier does not distinguish individuals with major depressive disorder and attention-deficit hyperactivity disorder from their controls but moderately distinguishes patients with schizophrenia from their controls. The results leave open the viable possibility of exploring neuroimaging-based dimensions quantifying the multiple-disorder spectrum.
Autism spectrum disorder (ASD) is manifested by subtle but significant changes in the brain. Here, Yahata and colleagues devise a novel machine learning algorithm and develop a reliable ASD classifier based on brain functional connectivity, with which they quantitatively measure neuroimaging dimensions between ASD and other mental disorders.