{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T06:01:26Z","timestamp":1785132086775,"version":"3.55.0"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Mood disorder classification from neuroimaging alone remains limited by single-modality constraints and population-level heterogeneity. This study proposes a fusion-based machine learning framework combining structural brain MRI and polygenic risk scores (PRS) derived from genome-wide association studies, alongside demographic and imaging confounder data, to classify individuals into three categories: healthy controls (HC), mania\/bipolar disorder (MBD), and major depressive disorder (MDD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data were drawn from the UK Biobank under a retrospective, cross-sectional design. Three dataset configurations were structured as an ablation study: neuroimaging-only (D1; n=426), genetics-only (D2; n=264), and full multimodal fusion (D3; n=264). T1-weighted 3D MRI volumes were converted to grayscale, and the eight axial slices with the highest Shannon entropy per participant were selected, resized to 64\u00d764 pixels, and reduced from 32,768 to 150 features via ANOVA F-test univariate selection. PRS for bipolar disorder and MDD were derived from Psychiatric Genetics Consortium GWAS summary statistics using LDpred, restricted to European ancestry participants. Six machine learning classifiers were trained under each configuration using an 80:20 stratified split with 10-fold cross-validation, with macro-averaged AUC as the primary metric.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>XGBoost achieved the strongest discriminatory performance, attaining a macro-average AUC of 0.7647 and an MDD-specific AUC of 0.8175 on the neuroimaging-only configuration, representing peak performance across all conditions. The genetics-only configuration produced substantially lower macro-average AUC values across all classifiers (XGBoost: 0.6600), consistent with the modest individual-level effect sizes of common psychiatric genetic variants. The controlled same-sample comparison between D2 and D3 revealed that the addition of MRI features improved macro-average AUC by 0.052 (XGBoost: 0.6600 to 0.7121), with the most pronounced gain observed for MBD classification (AUC 0.7160 to 0.7840). Despite its smaller sample size, D3 achieved competitive performance, suggesting that PRS may provide complementary signal, although direct comparison with D1 is limited by differences in sample composition.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These findings support the potential of interpretable, fusion-based machine learning for advancing diagnostic precision in mood disorder research, with multimodal integration of neuroimaging and genetic risk offering complementary signal beyond what either modality provides independently.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1883424","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:39:25Z","timestamp":1785130765000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal classification of mood disorders using structural MRI and polygenic risk scores: a machine learning ablation study in UK Biobank"],"prefix":"10.3389","volume":"17","author":[{"given":"Umi Kalsom","family":"Mohamad Yusof","sequence":"first","affiliation":[{"name":"School of Health and Wellbeing, University of Glasgow","place":["Glasgow, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joey","family":"Ward","sequence":"additional","affiliation":[{"name":"School of Health and Wellbeing, University of Glasgow","place":["Glasgow, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura M.","family":"Lyall","sequence":"additional","affiliation":[{"name":"School of Health and Wellbeing, University of Glasgow","place":["Glasgow, United Kingdom"]},{"name":"Centre for Clinical Brain Sciences, University of Edinburgh","place":["Edinburgh, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rona J.","family":"Strawbridge","sequence":"additional","affiliation":[{"name":"School of Health and Wellbeing, University of Glasgow","place":["Glasgow, United Kingdom"]},{"name":"Centre for Clinical Brain Sciences, University of Edinburgh","place":["Edinburgh, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"B1","article-title":"Major depressive disorder","volume-title":"Statpearls","author":"Bains","year":"2023"},{"key":"B2","article-title":"Bipolar disorder","volume-title":"Statpearls","author":"Jain","year":"2023"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2016.00063","article-title":"Multimodal neuroimaging-informed clinical applications in neuropsychiatric disorders","volume":"7","author":"O\u2019Halloran","year":"2016","journal-title":"Front Psychiatry"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac030","article-title":"Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failure","volume":"29","author":"Jabbour","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1167\/TVST.10.9.18","article-title":"Deep learning for automated diabetic retinopathy screening fused with heterogeneous data from EHRs","volume":"10","author":"Hsu","year":"2021","journal-title":"Transl Vis Sci Technol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","article-title":"Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"17981","DOI":"10.1038\/s41598-022-22514-4","article-title":"Artificial intelligence-based methods for fusion of electronic health records and imaging data","volume":"12","author":"Mohsen","year":"2022","journal-title":"Sci Rep"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dadm.2018.08.013","article-title":"Fusion of deep learning models of MRI scans, Mini-Mental State Examination, and logical memory test enhances diagnosis of mild cognitive impairment","volume":"10","author":"Qiu","year":"2018","journal-title":"Alzheimers Dement"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102550","article-title":"An enhanced multi-modal brain graph network for classifying neuropsychiatric disorders","volume":"81","author":"Liu","year":"2022","journal-title":"Med Image Anal"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.26077","article-title":"Deep multimodal predictome for studying mental disorders","volume":"44","author":"Rahaman","year":"2023","journal-title":"Hum Brain Mapp"},{"key":"B11","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1186\/s12888-020-02886-5","article-title":"Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques","volume":"20","author":"Li","year":"2020","journal-title":"BMC Psychiatry"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.1043626","article-title":"Toward attention-based learning to predict the risk of brain degeneration with multimodal medical data","volume":"16","author":"Sun","year":"2023","journal-title":"Front Neurosci"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-025-03544-x","article-title":"Machine learning-based assessment of morphometric abnormalities distinguishes bipolar disorder and major depressive disorder","volume":"67","author":"He","year":"2025","journal-title":"Neuroradiology"},{"key":"B14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jad.2025.04.135","article-title":"Machine learning based differential diagnosis of schizophrenia, major depression disorder and bipolar disorder using structural magnetic resonance imaging","volume":"383","author":"Cao","year":"2025","journal-title":"J Affect Disord"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.70347","article-title":"Neuroimaging data informed mood and psychosis diagnosis using an ensemble deep multimodal framework","volume":"46","author":"Rokham","year":"2025","journal-title":"Hum Brain Mapp"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2024.02.036","article-title":"Multimodal integration of neuroimaging and genetic data for the diagnosis of mood disorders based on computer vision models","volume":"172","author":"Lee","year":"2024","journal-title":"J Psychiatr Res"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.3562","article-title":"Deep learning models for diagnosing mood disorders using integrated MRI and genetic data","volume":"12","author":"Aziz","year":"2026","journal-title":"PeerJ Comput Sci"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-026-03889-8","article-title":"Applying machine-learning and deep-learning to predict depression from brain MRI and identify depression-related brain biology","volume":"16","author":"Poirot","year":"2026","journal-title":"Transl Psychiatry"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.11117","article-title":"Towards Alzheimer\u2019s disease classification through transfer learning","author":"Hon","year":"2017","journal-title":"arXiv"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-464091\/v1","article-title":"Deep learning in brain MRI: effect of data leakage due to slice-level split using 2D convolutional neural networks","volume":"11","author":"Yagis","year":"2021","journal-title":"Res Sq"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3390\/s23031694","article-title":"Convolution neural networks and self-attention learners for Alzheimer dementia diagnosis from brain MRI","volume":"23","author":"Carcagni","year":"2023","journal-title":"Sensors"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106201","article-title":"Multimodal ensemble model for Alzheimer\u2019s disease conversion prediction from early mild cognitive impairment subjects","volume":"151","author":"Velazquez","year":"2022","journal-title":"Comput Biol Med"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK Biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PloS Med"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.10.034","article-title":"Image processing and quality control for the first 10,000 brain imaging datasets from UK Biobank","volume":"166","author":"Alfaro-Almagro","year":"2018","journal-title":"Neuroimage"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK Biobank resource with deep phenotyping and genomic data","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"key":"B26","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1038\/s41588-019-0397-8","article-title":"Genome-wide association study identifies 30 loci associated with bipolar disorder","volume":"51","author":"Stahl","year":"2019","journal-title":"Nat Genet"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0090-3","article-title":"Genome-wide association analyses identify 44 risk variants and refine the genetic architecture of major depression","volume":"50","author":"Wray","year":"2018","journal-title":"Nat Genet"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2912815","article-title":"Reliable accuracy estimates from k-fold cross validation","volume":"32","author":"Wong","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-33820-6_8","article-title":"Performance evaluation of different machine learning methods and deep-learning based convolutional neural network for health decision making","volume-title":"Nature Inspired Computing for Data Science. Studies in Computational Intelligence","author":"Sahoo","year":"2020"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104324","article-title":"Evaluation of machine learning algorithms for health and wellness applications: a tutorial","volume":"132","author":"Tohka","year":"2021","journal-title":"Comput Biol Med"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2023.5083","article-title":"A systematic evaluation of machine learning-based biomarkers for major depressive disorder across modalities","volume":"81","author":"Winter","year":"2024","journal-title":"JAMA Psychiatry"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1883424\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:39:27Z","timestamp":1785130767000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1883424\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":31,"alternative-id":["10.3389\/fpsyt.2026.1883424"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1883424","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]},"article-number":"1883424"}}