Yoshihara Yujiro, Lisi Giuseppe, Yahata Noriaki, Fujino Junya, Matsumoto Yukiko, Miyata Jun, Sugihara Gen-Ichi, Urayama Shin-Ichi, Kubota Manabu, Yamashita Masahiro, Hashimoto Ryuichiro, Ichikawa Naho, Cahn Weipke, van Haren Neeltje E M, Mori Susumu, Okamoto Yasumasa, Kasai Kiyoto, Kato Nobumasa, Imamizu Hiroshi, Kahn René S, Sawa Akira, Kawato Mitsuo, Murai Toshiya, Morimoto Jun, Takahashi Hidehiko
Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
Department of Brain Robot Interface, ATR (Advanced Telecommunications Research Institute International) Brain Information Communication Research Laboratory Group, Kyoto, Japan.
Schizophr Bull. 2020 Sep 21;46(5):1210-1218. doi: 10.1093/schbul/sbaa021.
Although the relationship between schizophrenia spectrum disorder (SSD) and autism spectrum disorder (ASD) has long been debated, it has not yet been fully elucidated. The authors quantified and visualized the relationship between ASD and SSD using dual classifiers that discriminate patients from healthy controls (HCs) based on resting-state functional connectivity magnetic resonance imaging. To develop a reliable SSD classifier, sophisticated machine-learning algorithms that automatically selected SSD-specific functional connections were applied to Japanese datasets from Kyoto University Hospital (N = 170) including patients with chronic-stage SSD. The generalizability of the SSD classifier was tested by 2 independent validation cohorts, and 1 cohort including first-episode schizophrenia. The specificity of the SSD classifier was tested by 2 Japanese cohorts of ASD and major depressive disorder. The weighted linear summation of the classifier's functional connections constituted the biological dimensions representing neural classification certainty for the disorders. Our previously developed ASD classifier was used as ASD dimension. Distributions of individuals with SSD, ASD, and HCs s were examined on the SSD and ASD biological dimensions. We found that the SSD and ASD populations exhibited overlapping but asymmetrical patterns in the 2 biological dimensions. That is, the SSD population showed increased classification certainty for the ASD dimension but not vice versa. Furthermore, the 2 dimensions were correlated within the ASD population but not the SSD population. In conclusion, using the 2 biological dimensions based on resting-state functional connectivity enabled us to discover the quantified relationships between SSD and ASD.
尽管精神分裂症谱系障碍（SSD）与自闭症谱系障碍（ASD）之间的关系长期以来一直存在争议，但尚未完全阐明。作者使用基于静息态功能连接磁共振成像将患者与健康对照（HC）区分开来的双分类器，对ASD和SSD之间的关系进行了量化和可视化。为了开发可靠的SSD分类器，将自动选择SSD特定功能连接的复杂机器学习算法应用于来自京都大学医院的日本数据集（N = 170），其中包括慢性期SSD患者。通过2个独立的验证队列以及1个包括首发精神分裂症的队列对SSD分类器的可推广性进行了测试。通过2个日本ASD和重度抑郁症队列对SSD分类器的特异性进行了测试。分类器功能连接的加权线性总和构成了代表疾病神经分类确定性的生物学维度。我们之前开发的ASD分类器用作ASD维度。在SSD和ASD生物学维度上检查了患有SSD、ASD和HC的个体分布。我们发现，SSD和ASD人群在这两个生物学维度上表现出重叠但不对称的模式。也就是说，SSD人群在ASD维度上表现出更高的分类确定性，但反之不然。此外，这两个维度在ASD人群中相关，但在SSD人群中不相关。总之，使用基于静息态功能连接的两个生物学维度使我们能够发现SSD和ASD之间的量化关系。
