{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["21(1)"],"submitter":["Chen Z"],"pubmed_abstract":["<h4>Background</h4>The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.<h4>Methods</h4>Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psych"],"journal":["BMC medicine"],"pagination":["241"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10318841"],"repository":["biostudies-literature"],"pubmed_title":["Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry."],"pmcid":["PMC10318841"],"pubmed_authors":["Chuan-Peng H","Gu X","Li C","Feng Z","Chen J","Xiao Z","Eickhoff SB","Hu B","Miao K","Dai X","Liu X","Chen Z","Leonov A","Becker B","Tang Y"],"additional_accession":[]},"is_claimable":false,"name":"Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry.","description":"<h4>Background</h4>The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.<h4>Methods</h4>Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psych","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Jul","modification":"2025-04-26T18:44:46.11Z","creation":"2025-04-06T15:53:10.179Z"},"accession":"S-EPMC10318841","cross_references":{"pubmed":["37400814"],"doi":["10.1186/s12916-023-02941-4"]}}