Comprehensive evaluation of pipelines for classification of psychiatric disorders using multi-site resting-state fMRI datasets

Objective classification biomarkers that are developed using resting-state functional magnetic resonance imaging (rs-fMRI) data are expected to contribute to more effective treatment for psychiatric disorders. Unfortunately, no widely accepted biomarkers are available at present, partially because of the large variety of analysis pipelines for their development. In this study, we comprehensively evaluated analysis pipelines using a large-scale, multi-site fMRI dataset for major depressive disorder (MDD). We explored combinations of options in four sub-processes of the analysis pipelines: six types of brain parcellation, four types of functional connectivity (FC) estimations, three types of site-difference harmonization, and five types of machine-learning methods. A total of 360 different MDD classification biomarkers were constructed using the SRPBS dataset acquired with unified protocols (713 participants from four sites) as the discovery dataset, and datasets from other projects acquired with heterogeneous protocols (449 participants from four sites) were used for independent validation. We repeated the procedure after swapping the roles of the two datasets to identify superior pipelines, regardless of the discovery dataset. The classification results of the top 10 biomarkers showed high similarity, and weight similarity was observed between eight of the biomarkers, except for two that used both data-driven parcellation and FC computation. We applied the top 10 pipelines to the datasets of other psychiatric disorders (autism spectrum disorder and schizophrenia), and eight of the biomarkers exhibited sufficient classification performance for both disorders. Our results will be useful for establishing a standardized pipeline for classification biomarkers.

Authors

Institutions

Publication Details

Journal
Neural Networks
Published
2025-02-28
DOI
https://doi.org/10.1016/j.neunet.2025.107335
Citations
2
Primary Topic
Functional Brain Connectivity Studies
Type
article
Field-Weighted Citation Impact
2.86
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Comprehensive evaluation of pipelines for classification of psychiatric disorders using multi-site resting-state fMRI datasets

Kiyoto Kasai, Tomoki Tokuda, Eri Itai, Naohiro Okada et al.
2 citations
Neural Networks
Functional Brain Connectivity Studies
2.86
article

Comprehensive evaluation of pipelines for classification of psychiatric disorders using multi-site resting-state fMRI datasets

Kiyoto Kasai, Tomoki Tokuda, Eri Itai, Naohiro Okada, Hiroshi Imamizu, Saori Tanaka, S. Yokoyama, Mitsuo Kawato, Hidehiko Takahashi, Okito Yamashita, Hirotaka Yamagata, Go Okada, Hotaka Shinzato, Sotaro Momosaki, Koichi Ogawa, Yuki Sakai, Ryu-ichiro Hashimoto, Ayumu Yamashita, Yasumasa Okamoto, Takashi Itahashi, Junichiro Yoshimoto, Yuki Mitsuyama, Yuji Takahara, Hiroto Mizuta, Toshio Matsubara, Yuto Kashiwagi, Akira Kunimitsu, Koji Matsuo, Kenichiro Harada, Yoshikazu Masuda, Toshinori Yoshioka, Haruhisa Ohta
article en
2 citations

Abstract

Objective classification biomarkers that are developed using resting-state functional magnetic resonance imaging (rs-fMRI) data are expected to contribute to more effective treatment for psychiatric disorders. Unfortunately, no widely accepted biomarkers are available at present, partially because of the large variety of analysis pipelines for their development. In this study, we comprehensively evaluated analysis pipelines using a large-scale, multi-site fMRI dataset for major depressive disorder (MDD). We explored combinations of options in four sub-processes of the analysis pipelines: six types of brain parcellation, four types of functional connectivity (FC) estimations, three types of site-difference harmonization, and five types of machine-learning methods. A total of 360 different MDD classification biomarkers were constructed using the SRPBS dataset acquired with unified protocols (713 participants from four sites) as the discovery dataset, and datasets from other projects acquired with heterogeneous protocols (449 participants from four sites) were used for independent validation. We repeated the procedure after swapping the roles of the two datasets to identify superior pipelines, regardless of the discovery dataset. The classification results of the top 10 biomarkers showed high similarity, and weight similarity was observed between eight of the biomarkers, except for two that used both data-driven parcellation and FC computation. We applied the top 10 pipelines to the datasets of other psychiatric disorders (autism spectrum disorder and schizophrenia), and eight of the biomarkers exhibited sufficient classification performance for both disorders. Our results will be useful for establishing a standardized pipeline for classification biomarkers.

Neural NetworksVol. 187
Hiroshima University (JP), SHOWA Medical University (JP), Tokyo Medical and Dental University (JP), Fujita Health University (JP), Yamaguchi University (JP), Kyoto University (JP), Tokyo Metropolitan Institute of Medical Science (JP), Advanced Telecommunications Research Institute International (JP), Shionogi (Japan) (JP), Mita Hospital (JP), Tokyo Metropolitan University (JP), The University of Tokyo (JP), Nara Institute of Science and Technology (JP), Saitama Medical University (JP), Futaba (Japan) (JP)
Openalex Percentile: Top 12%
Functional Brain Connectivity Studies
2.86
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.