{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T18:45:09Z","timestamp":1775501109136,"version":"3.50.1"},"posted":{"date-parts":[[2025,8,6]]},"group-title":"Ophthalmology","reference-count":86,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,12,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>The eye is a recognised source of biomarkers for cardiovascular and neurodegenerative disease risk. Here, we characterise the breadth of these associations and identify biological axes that may mediate them. Using UK Biobank data, we developed a multi-omic analysis pipeline integrating physiological, radiomic, metabolomic, and genomic information. We trained adversarial autoencoders (Ret-AAE) to represent optical coherence tomography (OCT) images and colour fundus photographs as 256-dimensional embeddings. Ret-AAE derived embeddings were associated with a range of cardiovascular and neurodegenerative diseases, including ischaemic heart disease, cerebrovascular disease, Parkinson\u2019s disease, and dementia. Examining associations across diverse omics datasets, we provide evidence linking ophthalmic imaging features to neurological and cardiovascular anatomy and function, lipid metabolism, and gene sets associated with neurodegenerative pathology. Collectively, our findings demonstrate that ophthalmic features reflect complex, multisystem biological processes, and reinforce the role of the eye as a composite indicator of systemic health.<\/jats:p>","DOI":"10.1101\/2025.08.04.25332962","type":"posted-content","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T01:55:11Z","timestamp":1754531711000},"source":"Crossref","is-referenced-by-count":1,"title":["Ophthalmic imaging as a measure of cardiovascular and neurological health: a multi-omic analysis of deep-learning derived phenotypes"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5488-5620","authenticated-orcid":false,"given":"Thomas H.","family":"Julian","sequence":"first","affiliation":[{"name":"Division of Evolution, Infection and Genomics, School of Biological Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK"},{"name":"Centre for Computational Imaging and Modelling in Medicine (CIMIM), The Christabel Pankhurst Institute, The University of Manchester, Manchester, UK"},{"name":"Manchester Royal Eye Hospital, Manchester University NHS Foundation Trust, Manchester, UK"},{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8628-5489","authenticated-orcid":false,"given":"Haoran","family":"Dou","sequence":"additional","affiliation":[{"name":"Centre for Computational Imaging and Modelling in Medicine (CIMIM), The Christabel Pankhurst Institute, The University of Manchester, Manchester, UK"},{"name":"Department of Computer Science, School of Engineering, Faculty of Science and Engineering, University of Manchester, Manchester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5108-2128","authenticated-orcid":false,"given":"Jinming","family":"Duan","sequence":"additional","affiliation":[{"name":"Centre for Computational Imaging and Modelling in Medicine (CIMIM), The Christabel Pankhurst Institute, The University of Manchester, Manchester, UK"},{"name":"Division of Informatics, Imaging, and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK"},{"name":"BHF Centre of Research Excellence, University of Manchester, Manchester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7847-6635","authenticated-orcid":false,"given":"Jinghan","family":"Huang","sequence":"additional","affiliation":[{"name":"Centre for Computational Imaging and Modelling in Medicine (CIMIM), The Christabel Pankhurst Institute, The University of Manchester, Manchester, UK"},{"name":"Department of Computer Science, School of Engineering, Faculty of Science and Engineering, University of Manchester, Manchester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Esther","family":"Yoo","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David J.","family":"Green","sequence":"additional","affiliation":[{"name":"Division of Evolution, Infection and Genomics, School of Biological Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Strange","sequence":"additional","affiliation":[{"name":"Sheffield Institute for Translational Neuroscience (SITraN), University of Sheffield, Sheffield, UK"},{"name":"NIHR Sheffield Biomedical Research Centre, Sheffield, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elham","family":"Alhathli","sequence":"additional","affiliation":[{"name":"Sheffield Institute for Translational Neuroscience (SITraN), University of Sheffield, Sheffield, UK"},{"name":"NIHR Sheffield Biomedical Research Centre, Sheffield, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"UK Biobank Eye and Vision Consortium","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Sperrin","sequence":"additional","affiliation":[{"name":"Division of Informatics, Imaging, and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9239-745X","authenticated-orcid":false,"given":"Pearse A","family":"Keane","sequence":"additional","affiliation":[{"name":"NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust, London, UK"},{"name":"Institute of Ophthalmology, University College London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily Y.","family":"Chew","sequence":"additional","affiliation":[{"name":"Division of Epidemiology and Clinical Applications, National Eye Institute\/National Institutes of Health, Bethesda, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Keavney","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Sciences, School of Medical Sciences, Faculty of Biology, Medicine, and Health, The University of Manchester, Manchester, M13 9PL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2370-8496","authenticated-orcid":false,"given":"Tomas W.","family":"Fitzgerald","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0873-8689","authenticated-orcid":false,"given":"Johnathan","family":"Cooper-Knock","sequence":"additional","affiliation":[{"name":"Sheffield Institute for Translational Neuroscience (SITraN), University of Sheffield, Sheffield, UK"},{"name":"NIHR Sheffield Biomedical Research Centre, Sheffield, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8314-8497","authenticated-orcid":false,"given":"Ewan","family":"Birney","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2675-528X","authenticated-orcid":false,"given":"Alejandro F.","family":"Frangi","sequence":"additional","affiliation":[{"name":"Centre for Computational Imaging and Modelling in Medicine (CIMIM), The Christabel Pankhurst Institute, The University of Manchester, Manchester, UK"},{"name":"Department of Computer Science, School of Engineering, Faculty of Science and Engineering, University of Manchester, Manchester, UK"},{"name":"Division of Informatics, Imaging, and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK"},{"name":"BHF Centre of Research Excellence, University of Manchester, Manchester, UK"},{"name":"NIHR Manchester Biomedical Research Centre, Manchester Academic Health Sciences Centre, University of Manchester, Manchester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0986-4123","authenticated-orcid":false,"given":"Panagiotis I.","family":"Sergouniotis","sequence":"additional","affiliation":[{"name":"Division of Evolution, Infection and Genomics, School of Biological Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK"},{"name":"Manchester Royal Eye Hospital, Manchester University NHS Foundation Trust, Manchester, UK"},{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026010105124702000_2025.08.04.25332962v3.1","doi-asserted-by":"publisher","DOI":"10.1016\/J.PRETEYERES.2025.101350"},{"key":"2026010105124702000_2025.08.04.25332962v3.2","doi-asserted-by":"crossref","first-page":"2285","DOI":"10.1007\/s00415-023-12171-6","article-title":"Retinal imaging for the assessment of stroke risk: a systematic review","volume":"271","year":"2024","journal-title":"J. Neurol"},{"key":"2026010105124702000_2025.08.04.25332962v3.3","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1038\/s41569-024-01060-8","article-title":"Standardization and clinical applications of retinal imaging biomarkers for cardiovascular disease: a Roadmap from an NHLBI workshop","volume":"22","year":"2025","journal-title":"Nat. Rev. Cardiol"},{"key":"2026010105124702000_2025.08.04.25332962v3.4","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2022-322081"},{"key":"2026010105124702000_2025.08.04.25332962v3.5","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1097\/APO.0000000000000584","article-title":"Recent advances in clinical applications of imaging in retinal diseases","volume":"12","year":"2023","journal-title":"Asia Pac. J. Ophthalmol. (Phila.)"},{"key":"2026010105124702000_2025.08.04.25332962v3.6","doi-asserted-by":"crossref","unstructured":"He, K ., et al. Masked Autoencoders Are Scalable Vision Learners. arXiv [cs.CV] (2021).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2026010105124702000_2025.08.04.25332962v3.7","doi-asserted-by":"publisher","DOI":"10.1136\/bjo-2022-321399"},{"key":"2026010105124702000_2025.08.04.25332962v3.8","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s42256-021-00427-7","article-title":"Predicting myocardial infarction through retinal scans and minimal personal information","volume":"4","year":"2022","journal-title":"Nat. Mach. Intell"},{"key":"2026010105124702000_2025.08.04.25332962v3.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"2026010105124702000_2025.08.04.25332962v3.10","doi-asserted-by":"crossref","first-page":"btae732","DOI":"10.1093\/bioinformatics\/btae732","article-title":"Autoencoder-based phenotyping of ophthalmic images highlights genetic loci influencing retinal morphology and provides informative biomarkers","volume":"41","year":"2024","journal-title":"Bioinformatics"},{"key":"2026010105124702000_2025.08.04.25332962v3.11","doi-asserted-by":"crossref","unstructured":"Maldonado-Garcia, C. et al. Predicting cardiovascular disease risk using retinal optical coherence tomography imaging. Front. Artif. Intell. 8, (2025).","DOI":"10.3389\/frai.2025.1624550"},{"key":"2026010105124702000_2025.08.04.25332962v3.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2010.11.011"},{"key":"2026010105124702000_2025.08.04.25332962v3.13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1009497"},{"key":"2026010105124702000_2025.08.04.25332962v3.14","doi-asserted-by":"crossref","first-page":"100008","DOI":"10.1016\/j.medp.2024.100008","article-title":"Structural and biochemical basis of methylmalonate semialdehyde dehydrogenase ALDH6A1","volume":"1","year":"2024","journal-title":"Medicine Plus"},{"key":"2026010105124702000_2025.08.04.25332962v3.15","doi-asserted-by":"crossref","unstructured":"Julian, T. , Fitzgerald, T. , Birney, E. & Sergouniotis, P. I . Pigmentation and retinal pigment epithelium thickness: a study of the phenotypic and genotypic relationships between ocular and extraocular pigmented tissues. Genetics (2024).","DOI":"10.1101\/2024.12.04.626809"},{"key":"2026010105124702000_2025.08.04.25332962v3.16","doi-asserted-by":"crossref","unstructured":"Green, D. J. et al. Genetic insights into foveal morphology and its associations with pigmentation and age-related macular degeneration. Ophthalmology (2025).","DOI":"10.1101\/2025.06.27.25330434"},{"key":"2026010105124702000_2025.08.04.25332962v3.17","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1038\/s41436-020-00997-8","article-title":"Dopachrome tautomerase variants in patients with oculocutaneous albinism","volume":"23","year":"2021","journal-title":"Genet. Med"},{"key":"2026010105124702000_2025.08.04.25332962v3.18","doi-asserted-by":"crossref","unstructured":"Lyraki, R. et al. Characterization of a novel RP2-OSTF1 interaction and its implication for actin remodelling. J. Cell Sci. 131, (2018).","DOI":"10.1242\/jcs.211748"},{"key":"2026010105124702000_2025.08.04.25332962v3.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2013.10.022"},{"key":"2026010105124702000_2025.08.04.25332962v3.20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1010583"},{"key":"2026010105124702000_2025.08.04.25332962v3.21","doi-asserted-by":"crossref","unstructured":"Le Goallec, A. , Diai, S. , Vincent, T. & Patel, C. J . Comparing the genetic and environmental architecture of blood count, blood biochemistry and urine biochemistry biological ages with machine learning. Health Informatics (2021).","DOI":"10.1101\/2021.07.05.21260032"},{"key":"2026010105124702000_2025.08.04.25332962v3.22","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1007\/s11357-024-01481-w","article-title":"Genomic determinants of biological age estimated by deep learning applied to retinal images","volume":"47","year":"2025","journal-title":"GeroScience"},{"key":"2026010105124702000_2025.08.04.25332962v3.23","doi-asserted-by":"crossref","first-page":"4387","DOI":"10.3390\/ijms23084387","article-title":"The relaxin-3 receptor, RXFP3, is a modulator of aging-related disease","volume":"23","year":"2022","journal-title":"Int. J. Mol. Sci."},{"key":"2026010105124702000_2025.08.04.25332962v3.24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004219"},{"key":"2026010105124702000_2025.08.04.25332962v3.25","doi-asserted-by":"crossref","unstructured":"Julian, T. H. et al. Phenome-wide Mendelian randomisation analysis identifies causal factors for age-related macular degeneration. Elife 12, (2023).","DOI":"10.7554\/eLife.82546"},{"key":"2026010105124702000_2025.08.04.25332962v3.26","doi-asserted-by":"crossref","first-page":"7720","DOI":"10.1038\/s41467-023-43125-1","article-title":"Choroidal and retinal thinning in chronic kidney disease independently associate with eGFR decline and are modifiable with treatment","volume":"14","year":"2023","journal-title":"Nat. Commun"},{"key":"2026010105124702000_2025.08.04.25332962v3.27","doi-asserted-by":"crossref","unstructured":"Wei, J. , Wong, L. C. & Boland, S . Lipids as emerging biomarkers in neurodegenerative diseases. Int. J. Mol. Sci. 25, (2023).","DOI":"10.3390\/ijms25010131"},{"key":"2026010105124702000_2025.08.04.25332962v3.28","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.tem.2022.02.001","article-title":"Lipids and lipoproteins in cardiovascular diseases: a classification","volume":"33","year":"2022","journal-title":"Trends Endocrinol. Metab"},{"key":"2026010105124702000_2025.08.04.25332962v3.29","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awab420"},{"key":"2026010105124702000_2025.08.04.25332962v3.30","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2020.00598"},{"key":"2026010105124702000_2025.08.04.25332962v3.31","doi-asserted-by":"publisher","DOI":"10.1038\/s41582-022-00618-9"},{"key":"2026010105124702000_2025.08.04.25332962v3.32","first-page":"e1581","article-title":"Retinal optical coherence tomography features associated with incident and prevalent Parkinson disease","volume":"101","year":"2023","journal-title":"Neurology"},{"key":"2026010105124702000_2025.08.04.25332962v3.33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-55198-7"},{"key":"2026010105124702000_2025.08.04.25332962v3.34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0131389"},{"key":"2026010105124702000_2025.08.04.25332962v3.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.semcdb.2015.03.002"},{"key":"2026010105124702000_2025.08.04.25332962v3.36","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1038\/s41531-023-00570-5","article-title":"\u03b1-Synuclein pathology in post-mortem retina and optic nerve is specific for \u03b1-synucleinopathies","volume":"9","year":"2023","journal-title":"NPJ Parkinsons Dis"},{"key":"2026010105124702000_2025.08.04.25332962v3.37","doi-asserted-by":"crossref","unstructured":"Paj\u0105k, B. , Kania, E. & Orzechowski, A . Killing Me Softly: Connotations to Unfolded Protein Response and Oxidative Stress in Alzheimer\u2019s Disease. Oxidative Medicine and Cellular Longevity 2016, (2016).","DOI":"10.1155\/2016\/1805304"},{"key":"2026010105124702000_2025.08.04.25332962v3.38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2008.06.008"},{"key":"2026010105124702000_2025.08.04.25332962v3.39","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1038\/s41467-024-55635-7","article-title":"Multi-omic spatial effects on high-resolution AI-derived retinal thickness","volume":"16","year":"2025","journal-title":"Nat. Commun"},{"key":"2026010105124702000_2025.08.04.25332962v3.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50309-w"},{"key":"2026010105124702000_2025.08.04.25332962v3.41","doi-asserted-by":"crossref","first-page":"e014654","DOI":"10.1161\/JAHA.119.014654","article-title":"Exploring associations between cardiac structure and retinal vascular geometry","volume":"9","year":"2020","journal-title":"J. Am. Heart Assoc"},{"key":"2026010105124702000_2025.08.04.25332962v3.42","doi-asserted-by":"crossref","first-page":"14797","DOI":"10.1038\/s41598-020-71385-0","article-title":"Associations between cardiac function and retinal microvascular geometry among Chinese adults","volume":"10","year":"2020","journal-title":"Sci. Rep"},{"key":"2026010105124702000_2025.08.04.25332962v3.43","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1038\/s42256-024-00801-1","article-title":"Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology","volume":"6","year":"2024","journal-title":"Nat. Mach. Intell"},{"key":"2026010105124702000_2025.08.04.25332962v3.44","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1038\/s42003-024-06096-7","article-title":"Unsupervised deep representation learning enables phenotype discovery for genetic association studies of brain imaging","volume":"7","year":"2024","journal-title":"Commun. Biol"},{"key":"2026010105124702000_2025.08.04.25332962v3.45","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwx246"},{"key":"2026010105124702000_2025.08.04.25332962v3.46","unstructured":"Kingma, D. P. & Welling, M . Auto-Encoding Variational Bayes. arXiv [stat.ML] (2013)."},{"key":"2026010105124702000_2025.08.04.25332962v3.47","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001779"},{"key":"2026010105124702000_2025.08.04.25332962v3.48","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2018-025077"},{"key":"2026010105124702000_2025.08.04.25332962v3.49","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1167\/tvst.11.7.12","article-title":"AutoMorph: Automated retinal vascular morphology quantification via a deep learning pipeline","volume":"11","year":"2022","journal-title":"Transl. Vis. Sci. Technol"},{"key":"2026010105124702000_2025.08.04.25332962v3.50","unstructured":"Graham, M . OCT-Converter: Tools for Extracting the Raw Optical Coherence Tomography (OCT) and Fundus Data from Proprietary File Formats. (Github)."},{"key":"2026010105124702000_2025.08.04.25332962v3.51","unstructured":"Makhzani, A. , Shlens, J. , Jaitly, N. , Goodfellow, I. & Frey, B . Adversarial Autoencoders. arXiv [cs.LG] (2015)."},{"key":"2026010105124702000_2025.08.04.25332962v3.52","doi-asserted-by":"crossref","unstructured":"Ouyang, D ., et al. Efficient multi-scale attention module with cross-spatial learning. arXiv [cs.CV] (2023).","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"2026010105124702000_2025.08.04.25332962v3.53","doi-asserted-by":"crossref","unstructured":"Gao, S. & Zhuang, X . Multi-scale deep neural networks for real image super-resolution. arXiv [cs.CV] (2019).","DOI":"10.1109\/CVPRW.2019.00252"},{"key":"2026010105124702000_2025.08.04.25332962v3.54","unstructured":"Pihlgren, G. G. , et al. A systematic performance analysis of deep perceptual loss networks: Breaking transfer learning conventions. arXiv [cs.CV] (2023)."},{"key":"2026010105124702000_2025.08.04.25332962v3.55","unstructured":"Simonyan, K. & Zisserman, A . Very deep convolutional networks for large-scale image recognition. arXiv [cs.CV] (2014)."},{"key":"2026010105124702000_2025.08.04.25332962v3.56","unstructured":"Fu, C. , Chen, H. , Ruan, N. & Jia, W . Label smoothing and adversarial robustness. arXiv [cs.CV] (2020)."},{"key":"2026010105124702000_2025.08.04.25332962v3.57","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2019.73002"},{"key":"2026010105124702000_2025.08.04.25332962v3.58","unstructured":"Weights & Biases: The AI Developer Platform. Weights & Biases https:\/\/wandb.ai\/site\/ (2024)."},{"key":"2026010105124702000_2025.08.04.25332962v3.59","unstructured":"Loshchilov, I. & Hutter, F . Decoupled weight decay regularization. arXiv [cs.LG] (2017)."},{"key":"2026010105124702000_2025.08.04.25332962v3.60","unstructured":"Paszke, A. , et al. PyTorch: An imperative style, high-performance deep learning library. arXiv [cs.LG] (2019)."},{"key":"2026010105124702000_2025.08.04.25332962v3.61","doi-asserted-by":"crossref","first-page":"205","DOI":"10.21105\/joss.00205","article-title":"hdbscan: Hierarchical density based clustering","volume":"2","year":"2017","journal-title":"J. Open Source Softw"},{"key":"2026010105124702000_2025.08.04.25332962v3.62","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2026010105124702000_2025.08.04.25332962v3.63","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"2026010105124702000_2025.08.04.25332962v3.64","unstructured":"External Info: Data_providers_and_dates. https:\/\/biobank.ndph.ox.ac.uk\/ukb\/exinfo.cgi?src=Data_providers_and_dates."},{"key":"2026010105124702000_2025.08.04.25332962v3.65","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.21105\/joss.01317","article-title":"C. lifelines: survival analysis in Python","volume":"4","author":"Davidson-Pilon","year":"2019","journal-title":"J. Open Source Softw"},{"key":"2026010105124702000_2025.08.04.25332962v3.66","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/34.1-2.28"},{"key":"2026010105124702000_2025.08.04.25332962v3.67","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36231-7"},{"key":"2026010105124702000_2025.08.04.25332962v3.68","doi-asserted-by":"publisher","DOI":"10.26398\/IJAS.0036-004"},{"key":"2026010105124702000_2025.08.04.25332962v3.69","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.116745"},{"key":"2026010105124702000_2025.08.04.25332962v3.70","doi-asserted-by":"crossref","unstructured":"Xia, C. H. et al. Linked dimensions of psychopathology and connectivity in functional brain networks. Nat. Commun. 9, (2018).","DOI":"10.1038\/s41467-018-05317-y"},{"key":"2026010105124702000_2025.08.04.25332962v3.71","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005752"},{"key":"2026010105124702000_2025.08.04.25332962v3.72","doi-asserted-by":"publisher","DOI":"10.1038\/S41588-021-00870-7"},{"key":"2026010105124702000_2025.08.04.25332962v3.73","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.1608"},{"key":"2026010105124702000_2025.08.04.25332962v3.74","doi-asserted-by":"publisher","DOI":"10.1186\/s13742-015-0047-8"},{"key":"2026010105124702000_2025.08.04.25332962v3.75","unstructured":"MSigDB. https:\/\/www.gsea-msigdb.org\/gsea\/msigdb\/human\/collections.jsp."},{"key":"2026010105124702000_2025.08.04.25332962v3.76","doi-asserted-by":"publisher","DOI":"10.1038\/nature15393"},{"key":"2026010105124702000_2025.08.04.25332962v3.77","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3211"},{"key":"2026010105124702000_2025.08.04.25332962v3.78","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-021-00954-4"},{"key":"2026010105124702000_2025.08.04.25332962v3.79","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0184-y"},{"key":"2026010105124702000_2025.08.04.25332962v3.80","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13690-5"},{"key":"2026010105124702000_2025.08.04.25332962v3.81","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-020-00776-w"},{"key":"2026010105124702000_2025.08.04.25332962v3.82","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0058-3"},{"key":"2026010105124702000_2025.08.04.25332962v3.83","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehaa1040"},{"key":"2026010105124702000_2025.08.04.25332962v3.84","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. , et al. Grad-CAM: Visual explanations from deep networks via Gradient-based localization. arXiv [cs.CV] (2016).","DOI":"10.1109\/ICCV.2017.74"},{"key":"2026010105124702000_2025.08.04.25332962v3.85","first-page":"1407","volume-title":"28th European Signal Processing Conference (EUSIPCO)","volume":"2020","year":"2021"},{"key":"2026010105124702000_2025.08.04.25332962v3.86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.08.04.25332962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:42:29Z","timestamp":1768509749000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.08.04.25332962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1101\/2025.08.04.25332962","relation":{},"subject":[],"published":{"date-parts":[[2025,8,6]]},"subtype":"preprint"}}