Yamashita Okito, Yamashita Ayumu, Takahara Yuji, Sakai Yuki, Okamoto Yasumasa, Okada Go, Takamura Masahiro, Nakamura Motoaki, Itahashi Takashi, Hanakawa Takashi, Togo Hiroki, Yoshihara Yujiro, Murai Toshiya, Okada Tomohisa, Narumoto Jin, Takahashi Hidehiko, Takagishi Haruto, Hosomi Koichi, Kasai Kiyoto, Okada Naohiro, Abe Osamu, Imamizu Hiroshi, Hayashi Takuya, Koike Shinsuke, Tanaka Saori C, Kawato Mitsuo
RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.
Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan.
Mol Psychiatry. 2025 Aug 7. doi: 10.1038/s41380-025-03134-6.
Resting-state functional connectivity (rsFC) is increasingly used to develop biomarkers for psychiatric disorders. Despite progress, development of the reliable and practical FC biomarker remains an unmet goal, particularly one that is clinically predictive at the individual level with generalizability, robustness, and accuracy. In this study, we propose a new approach to profile each connectivity from diverse perspective, encompassing not only disorder-related differences but also disorder-unrelated variations attributed to individual difference, within-subject across-runs, imaging protocol, and scanner factors. By leveraging over 1500 runs of 10-min resting-state data from 84 traveling-subjects across 29 sites and 900 participants of the case-control study with three psychiatric disorders, the disorder-related and disorder-unrelated FC variations were estimated for each individual FC. Using the FC profile information, we evaluated the effects of the disorder-related and disorder-unrelated variations on the output of the multi-connectivity biomarker trained with ensemble sparse classifiers generalizable to the multicenter data. Our analysis revealed hierarchical variations in individual functional connectivity, ranging from within-subject across-run variations, individual differences, disease effects, inter-scanner discrepancies, and protocol differences, which were drastically inverted by the sparse machine-learning algorithm. We found this inversion mainly attributed to suppression of both individual difference and within-subject across-runs variations relative to the disorder-related difference by weighted-summation of the selected FCs and ensemble averaging. This comprehensive approach will provide an analytical tool to develop reliable individual-level biomarkers.
静息态功能连接性（rsFC）越来越多地用于开发精神疾病的生物标志物。尽管取得了进展，但开发可靠且实用的功能连接性生物标志物仍然是一个未实现的目标，尤其是在个体水平上具有临床预测性、可推广性、稳健性和准确性的生物标志物。在本研究中，我们提出了一种新方法，从不同角度描绘每个连接性，不仅包括与疾病相关的差异，还包括由于个体差异、受试者内跨扫描、成像协议和扫描仪因素导致的与疾病无关的变异。通过利用来自29个地点的84名流动受试者的1500多次10分钟静息态数据运行以及900名患有三种精神疾病的病例对照研究参与者的数据，估计了每个个体功能连接性的与疾病相关和与疾病无关的功能连接性变异。利用功能连接性概况信息，我们评估了与疾病相关和与疾病无关的变异对使用可推广到多中心数据的集成稀疏分类器训练的多连接性生物标志物输出的影响。我们的分析揭示了个体功能连接性的分层变异，范围从受试者内跨扫描变异、个体差异、疾病效应、扫描仪间差异和协议差异，而稀疏机器学习算法极大地扭转了这些差异。我们发现这种扭转主要归因于通过对所选功能连接性进行加权求和和集成平均，相对于与疾病相关的差异，个体差异和受试者内跨扫描变异受到了抑制。这种综合方法将为开发可靠的个体水平生物标志物提供一种分析工具。
