@misc{oai:repo.qst.go.jp:00066491,
 author = {八幡, 憲明 and 八幡 憲明},
 month = {Sep},
 note = {Although autism spectrum disorder (ASD) is a serious lifelong condition, its underlying neural mechanism remains unclear. Recently, using resting-state functional-connectivity MRI (rs-fcMRI) techniques, attempts have been made to develop classifiers of ASD and typically developed (TD) individuals, and thereby to identify the abnormality of functional connections (FCs) in ASD. However, none of the previous classifiers has ever been successfully validated for an independent cohort because of overfitting and the interferential effects of nuisance variables such as measurement conditions and demographic distributions. Here, using a multiple-site data set from Japan, we developed an ASD classifier by focusing on abnormal FCs in ASD as revealed by rs-fcMRI. We developed a novel machine-learning algorithm that automatically identified a small number of abnormal FCs in ASD. The resultant classifier attained high accuracy for a Japanese discovery cohort, and furthermore, demonstrated a remarkable degree of generalization for two independent cohorts in the US and Japan. We also found that the developed classifier did not distinguish individuals with major depressive disorder and attention-deficit hyperactivity disorder from their controls but moderately distinguished patients with schizophrenia from their controls. These results leave open the viable possibility of exploring neuroimaging-based dimensions that quantify the multiple-disorder spectrum. In this symposium, I will discuss its clinical implication. This research was supported by SRPBS of AMED., 第39回 日本生物学的精神医学会・第47回 日本神経精神薬理学会 合同年会},
 title = {安静時機能的結合による自閉スペクトラム症の神経基盤理解と臨床応用の可能性},
 year = {2017}
}