%0 Journal Article
%T Graph convolutional network with attention mechanism improve major depressive depression diagnosis based on plasma biomarkers and neuroimaging data.
%A Jiang C
%A Lin B
%A Ye X
%A Yu Y
%A Xu P
%A Peng C
%A Mou T
%A Yu X
%A Zhao H
%A Zhao M
%A Li Y
%A Zhang S
%A Chen X
%A Pan F
%A Shang D
%A Jin K
%A Lu J
%A Chen J
%A Yin J
%A Huang M
%J J Affect Disord
%V 360
%N 0
%D 2024 Sep 1
%M 38824965
%F 6.533
%R 10.1016/j.jad.2024.05.136
%X <B>BACKGROUND: </B>The absence of clinically-validated biomarkers or objective protocols hinders effective major depressive disorder (MDD) diagnosis. Compared to healthy control (HC), MDD exhibits anomalies in plasma protein levels and neuroimaging presentations. Despite extensive machine learning studies in psychiatric diagnosis, a reliable tool integrating multi-modality data is still lacking.<BR><B>METHODS: </B>In this study, blood samples from 100 MDD and 100 HC were analyzed, along with MRI images from 46 MDD and 49 HC. Here, we devised a novel algorithm, integrating graph neural networks and attention modules, for MDD diagnosis based on inflammatory cytokines, neurotrophic factors, and Orexin A levels in the blood samples. Model performance was assessed via accuracy and F1 value in 3-fold cross-validation, comparing with 9 traditional algorithms. We then applied our algorithm to a dataset containing both the aforementioned protein quantifications and neuroimages, evaluating if integrating neuroimages into the model improves performance.<BR><B>RESULTS: </B>Compared to HC, MDD showed significant alterations in plasma protein levels and gray matter volume revealed by MRI. Our new algorithm exhibited superior performance, achieving an F1 value and accuracy of 0.9436 and 94.08 %, respectively. Integration of neuroimaging data enhanced our novel algorithm's performance, resulting in an improved F1 value and accuracy, reaching 0.9543 and 95.06 %.<BR><B>CONCLUSIONS: </B>This single-center study with a small sample size requires future evaluations on a larger test set for improved reliability.<BR><B>CONCLUSIONS: </B>In comparison to traditional machine learning models, our newly developed MDD diagnostic model exhibited superior performance and showed promising potential for inclusion in routine clinical diagnosis for MDD.