{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T12:47:46Z","timestamp":1785415666987,"version":"3.56.0"},"posted":{"date-parts":[[2026,7,21]]},"group-title":"Health Informatics","reference-count":67,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000848","name":"University of Edinburgh","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000848","id-type":"DOI","asserted-by":"crossref"}]},{"award":["Enrichment Scheme"],"award-info":[{"award-number":["Enrichment Scheme"]}],"id":[{"id":"https:\/\/ror.org\/035dkdb55","id-type":"ROR","asserted-by":"publisher"}]},{"name":"National Institute for Health Research (NIHR) Artificial Intelligence and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC) grant","award":["NIHR202639"],"award-info":[{"award-number":["NIHR202639"]}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"crossref","award":["1154623N"],"award-info":[{"award-number":["1154623N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>INTRODUCTION<\/jats:title>\n                  <jats:p>The biomarker-based amyloid\/ tau\/ neurodegeneration (A\/T\/N) framework has become a popular staging method for Alzheimer\u2019s disease (AD) research. Previous studies use the framework either as a rule-based or data-driven approach but typically sacrifice either adaptivity or interpretability.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>METHODS<\/jats:title>\n                  <jats:p>We present an interpretable, hybrid method, called Neurosymodal Data Fusion, for predicting incident AD in the ADNI dataset. Specifically, we encode the A\/T\/N framework as a logic program, where the input biomarker features are extracted by one or more neural networks.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>RESULTS<\/jats:title>\n                  <jats:p>Our pipeline predicted four-year incident AD with a sensitivity of up to 0.84. Additionally, our models learned scores for each A\/T\/N profile, denoting relative importances to model predictions. These scores also indicated that empirically-derived cut-off values for the A and T criteria might be uninformative for the ADNI data.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>DISCUSSION<\/jats:title>\n                  <jats:p>Our pipeline provides a novel way to use the A\/T\/N framework that could potentially improve early AD screening years before clinical manifestations.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.07.19.26358425","type":"posted-content","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T23:00:14Z","timestamp":1784674814000},"source":"Crossref","is-referenced-by-count":0,"title":["Encoding Discordance in the Alzheimer\u2019s Disease A\/T\/N Framework"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6618-3370","authenticated-orcid":false,"given":"Lauren Nicole","family":"DeLong","sequence":"first","affiliation":[{"name":"The School of Informatics, University of Edinburgh, EH8 9AB, Edinburgh, United Kingdom"},{"name":"Cancer Research UK Scotland Institute, G61 1BD, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7773-7786","authenticated-orcid":false,"given":"Yasamin","family":"Salimi","sequence":"additional","affiliation":[{"name":"Department of Biomedical AI & Data Science, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), 53757, Sankt Augustin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helena","family":"Balabin","sequence":"additional","affiliation":[{"name":"Laboratory for Cognitive Neurology, Department of Neurosciences, Leuven Brain Institute, KU Leuven, 3001, Leuven, Belgium"},{"name":"Language Intelligence and Information Retrieval Lab, Department of Computer Science, KU Leuven, 3001, Leuven, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4556-6799","authenticated-orcid":false,"given":"Paola","family":"Galdi","sequence":"additional","affiliation":[{"name":"The School of Informatics, University of Edinburgh, EH8 9AB, Edinburgh, United Kingdom"},{"name":"Cancer Research UK Scotland Institute, G61 1BD, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6867-9836","authenticated-orcid":false,"given":"Jacques D.","family":"Fleuriot","sequence":"additional","affiliation":[{"name":"The School of Informatics, University of Edinburgh, EH8 9AB, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Brennan","sequence":"additional","affiliation":[{"name":"Centre for Clinical Brain Sciences, University of Edinburgh, EH16 4SB, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026072308501170000_2026.07.19.26358425v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(20)32205-4"},{"key":"2026072308501170000_2026.07.19.26358425v1.2","doi-asserted-by":"publisher","DOI":"10.1002\/alz.13016"},{"key":"2026072308501170000_2026.07.19.26358425v1.3","doi-asserted-by":"publisher","DOI":"10.1111\/JGS.17345"},{"key":"2026072308501170000_2026.07.19.26358425v1.4","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-016-0227-5"},{"key":"2026072308501170000_2026.07.19.26358425v1.5","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.jalz.2011.03.003","article-title":"Toward defining the preclinical stages of Alzheimer\u2019s disease: Recommendations from the National Institute on Aging-Alzheimer\u2019s Association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","year":"2011","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.6","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.jalz.2011.03.005","article-title":"The diagnosis of dementia due to Alzheimer\u2019s disease: recommendations from the National Institute on Aging-Alzheimer\u2019s Association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","year":"2011","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.7","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000002923"},{"key":"2026072308501170000_2026.07.19.26358425v1.8","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.jalz.2011.03.008","article-title":"The diagnosis of mild cognitive impairment due to Alzheimer\u2019s disease: recommendations from the National Institute on Aging-Alzheimer\u2019s Association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","year":"2011","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.9","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1002\/alz.12387","article-title":"Unraveling the heterogeneity in Alzheimer\u2019s disease progression across multiple cohorts and the implications for data-driven disease modeling","volume":"18","year":"2022","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.10","doi-asserted-by":"publisher","DOI":"10.1017\/S1355617713000313"},{"key":"2026072308501170000_2026.07.19.26358425v1.11","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.jalz.2014.03.005","article-title":"Susceptibility of the conventional criteria for mild cognitive impairment to false-positive diagnostic errors","volume":"11","year":"2015","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.12","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.jalz.2016.07.005","article-title":"The DIAN-TU Next Generation Alzheimer\u2019s prevention trial: adaptive design and disease progression model","volume":"13","year":"2017","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.13","doi-asserted-by":"publisher","DOI":"10.1007\/s13311-022-01225-8"},{"key":"2026072308501170000_2026.07.19.26358425v1.14","doi-asserted-by":"publisher","DOI":"10.1007\/s11065-017-9363-3"},{"key":"2026072308501170000_2026.07.19.26358425v1.15","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA research framework: toward a biological definition of Alzheimer\u2019s disease","volume":"14","year":"2018","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.16","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.111.090340"},{"key":"2026072308501170000_2026.07.19.26358425v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/aps.2017.28"},{"key":"2026072308501170000_2026.07.19.26358425v1.18","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.4103\/1673-5374.193234","article-title":"Neurofibrillary tangles in Alzheimer\u2019s disease: elucidation of the molecular mechanism by immunohistochemistry and tau protein phospho-proteomics","volume":"11","year":"2016","journal-title":"Neural Regen Res"},{"key":"2026072308501170000_2026.07.19.26358425v1.19","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2310168"},{"key":"2026072308501170000_2026.07.19.26358425v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-021-01263-2"},{"key":"2026072308501170000_2026.07.19.26358425v1.21","doi-asserted-by":"crossref","first-page":"1996","DOI":"10.1002\/acn3.51196","article-title":"Discordant Alzheimer\u2019s neurodegenerative biomarkers and their clinical outcomes","volume":"7","year":"2020","journal-title":"Ann Clin Transl Neurol"},{"key":"2026072308501170000_2026.07.19.26358425v1.22","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1002\/alz.12292","article-title":"Application of the ATN classification scheme in a population without dementia: findings from the EPAD cohort","volume":"17","year":"2021","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.23","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1001\/jamaneurol.2022.2967","article-title":"The ATN framework\u2014moving preclinical Alzheimer disease to clinical relevance","volume":"79","year":"2022","journal-title":"JAMA Neurol"},{"key":"2026072308501170000_2026.07.19.26358425v1.24","first-page":"e12226","article-title":"The worldwide Alzheimer\u2019s disease neuroimaging initiative: ADNI-3 updates and global perspectives","volume":"7","year":"2021","journal-title":"Alzheimer\u2019s & Dementia: Translational Research & Clinical Interventions"},{"key":"2026072308501170000_2026.07.19.26358425v1.25","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.jalz.2018.12.009","article-title":"Early versus late MCI: Improved MCI staging using a neuropsychological approach","volume":"15","year":"2019","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.26","doi-asserted-by":"crossref","first-page":"1855","DOI":"10.1002\/alz.12491","article-title":"Predictive value of ATN biomarker profiles in estimating disease progression in Alzheimer\u2019s disease dementia","volume":"17","year":"2021","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.27","doi-asserted-by":"crossref","first-page":"35","DOI":"10.5603\/RPOR.a2021.0005","article-title":"T1-weighted and T2-weighted MRI image synthesis with convolutional generative adversarial networks","volume":"26","year":"2021","journal-title":"Reports of Practical Oncology and Radiotherapy"},{"key":"2026072308501170000_2026.07.19.26358425v1.28","doi-asserted-by":"crossref","first-page":"7340","DOI":"10.1002\/alz.14165","article-title":"The ADNI PET Core at 20","volume":"20","year":"2024","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.29","doi-asserted-by":"publisher","DOI":"10.1002\/ana.21610"},{"key":"2026072308501170000_2026.07.19.26358425v1.30","doi-asserted-by":"publisher","DOI":"10.1186\/S13195-022-00961-5\/TABLES\/4"},{"key":"2026072308501170000_2026.07.19.26358425v1.31","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.jalz.2005.06.003","article-title":"Ways toward an early diagnosis in Alzheimer\u2019s disease: the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI)","volume":"1","year":"2005","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.32","first-page":"87","article-title":"A nonparametric method for automatic correction of intensity nonuniformity in MRI data","volume":"17","year":"2002","journal-title":"IEEE Trans Med Imaging"},{"key":"2026072308501170000_2026.07.19.26358425v1.33","unstructured":"Glover GH , Pelc NJ. Method for correcting image distortion due to gradient nonuniformity 1986."},{"key":"2026072308501170000_2026.07.19.26358425v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.09.015"},{"key":"2026072308501170000_2026.07.19.26358425v1.35","first-page":"13","article-title":"Nipype: a flexible, lightweight and extensible neuroimaging data processing framework in python","volume":"5","year":"2011","journal-title":"Front Neuroinform"},{"key":"2026072308501170000_2026.07.19.26358425v1.36","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.12917"},{"key":"2026072308501170000_2026.07.19.26358425v1.37","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-021-00836-1"},{"key":"2026072308501170000_2026.07.19.26358425v1.38","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaz2387"},{"key":"2026072308501170000_2026.07.19.26358425v1.39","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1001\/jamaneurol.2019.4749","article-title":"Characterization of Alzheimer disease biomarker discrepancies using cerebrospinal fluid phosphorylated tau and AV1451 positron emission tomography","volume":"77","year":"2020","journal-title":"JAMA Neurol"},{"key":"2026072308501170000_2026.07.19.26358425v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021"},{"key":"2026072308501170000_2026.07.19.26358425v1.41","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awv283"},{"key":"2026072308501170000_2026.07.19.26358425v1.42","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1016\/j.jalz.2019.05.006","article-title":"Frequency and longitudinal clinical outcomes of Alzheimer\u2019s AT (N) biomarker profiles: a longitudinal study","volume":"15","year":"2019","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.43","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30077-7"},{"key":"2026072308501170000_2026.07.19.26358425v1.44","doi-asserted-by":"crossref","unstructured":"Filip P , Bednarik P , Eberly LE , Moheet A , Svatkova A , Grohn H , et al. Different FreeSurfer versions might generate different statistical outcomes in case\u2013control comparison studies. Neuroradiology 2022:1\u20139.","DOI":"10.1007\/s00234-021-02862-0"},{"key":"2026072308501170000_2026.07.19.26358425v1.45","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-54204-z"},{"key":"2026072308501170000_2026.07.19.26358425v1.46","first-page":"1","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"8","year":"2021","journal-title":"J Big Data"},{"key":"2026072308501170000_2026.07.19.26358425v1.47","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2026072308501170000_2026.07.19.26358425v1.48","doi-asserted-by":"crossref","unstructured":"Mann HB , Whitney DR . On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics 1947:50\u201360.","DOI":"10.1214\/aoms\/1177730491"},{"key":"2026072308501170000_2026.07.19.26358425v1.49","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences","volume":"20","year":"1958","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2026072308501170000_2026.07.19.26358425v1.50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3420218"},{"key":"2026072308501170000_2026.07.19.26358425v1.51","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2015.2460697"},{"key":"2026072308501170000_2026.07.19.26358425v1.52","first-page":"25134","article-title":"Scallop: From probabilistic deductive databases to scalable differentiable reasoning","volume":"34","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026072308501170000_2026.07.19.26358425v1.53","doi-asserted-by":"crossref","first-page":"185","DOI":"10.14283\/jpad.2023.100","article-title":"Data-driven thresholding statistically biases ATN profiling across cohort datasets","volume":"11","year":"2024","journal-title":"J Prev Alzheimers Dis"},{"key":"2026072308501170000_2026.07.19.26358425v1.54","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1136\/bmj.308.6943.1552","article-title":"Diagnostic tests. 1: Sensitivity and specificity","volume":"308","year":"1994","journal-title":"BMJ: British Medical Journal"},{"key":"2026072308501170000_2026.07.19.26358425v1.55","unstructured":"Van Rijsbergen CJ . Information Retrieval, 2nd edn. Newton, MA 1979."},{"key":"2026072308501170000_2026.07.19.26358425v1.56","doi-asserted-by":"crossref","unstructured":"Naidu G , Zuva T , Sibanda EM . A review of evaluation metrics in machine learning algorithms. Computer science on-line conference, 2023, p. 15\u201325.","DOI":"10.1007\/978-3-031-35314-7_2"},{"key":"2026072308501170000_2026.07.19.26358425v1.57","doi-asserted-by":"crossref","unstructured":"Ho TK. Random decision forests. Proceedings of 3rd international conference on document analysis and recognition, vol. 1, 1995, p. 278\u201382.","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"2026072308501170000_2026.07.19.26358425v1.58","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-32833-1_77"},{"key":"2026072308501170000_2026.07.19.26358425v1.59","unstructured":"Fisher RA . Statistical methods for research workers. Oliver and Boyd; 1928."},{"key":"2026072308501170000_2026.07.19.26358425v1.60","doi-asserted-by":"crossref","first-page":"957","DOI":"10.3233\/JAD-230678","article-title":"Where Should I Draw the Line: PET-Driven, Data-Driven, or Manufacturer Cut-Off?","volume":"98","year":"2024","journal-title":"Journal of Alzheimer\u2019s Disease"},{"key":"2026072308501170000_2026.07.19.26358425v1.61","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1002\/alz.13449","article-title":"The Alzheimer\u2019s Disease Neuroimaging Initiative in the era of Alzheimer\u2019s disease treatment: A review of ADNI studies from 2021 to 2022","volume":"20","year":"2024","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026072308501170000_2026.07.19.26358425v1.62","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.3233\/JAD-240116","article-title":"Semantic harmonization of Alzheimer\u2019s disease datasets using AD-Mapper","volume":"99","year":"2024","journal-title":"Journal of Alzheimer\u2019s Disease"},{"key":"2026072308501170000_2026.07.19.26358425v1.63","doi-asserted-by":"crossref","unstructured":"Lavin A . Neuro-symbolic neurodegenerative disease modeling as probabilistic programmed deep kernels. International Workshop on Health Intelligence, 2021, p. 49\u201364.","DOI":"10.1007\/978-3-030-93080-6_5"},{"key":"2026072308501170000_2026.07.19.26358425v1.64","unstructured":"He Y , Wang Z , Zhang Y , Dan T , Chen T , Wu G , et al. NeuroSymAD: A Neuro-Symbolic Framework for Interpretable Alzheimer\u2019s Disease Diagnosis. ArXiv Preprint ArXiv:250300510 2025."},{"key":"2026072308501170000_2026.07.19.26358425v1.65","doi-asserted-by":"crossref","first-page":"181","DOI":"10.3389\/fpubh.2018.00181","article-title":"Phenotypic heterogeneity in dementia: a challenge for epidemiology and biomarker studies","volume":"6","year":"2018","journal-title":"Front Public Health"},{"key":"2026072308501170000_2026.07.19.26358425v1.66","doi-asserted-by":"crossref","unstructured":"Balabin H , Tamm B , Spruyt L , Dusart N , Kabouche I , Eycken E , et al. Natural language processing-based classification of early Alzheimer\u2019s disease from connected speech. Alzheimer\u2019s & Dementia 2025:e14530.","DOI":"10.1002\/alz.14530"},{"key":"2026072308501170000_2026.07.19.26358425v1.67","doi-asserted-by":"crossref","first-page":"122807","DOI":"10.1016\/j.eswa.2023.122807","article-title":"A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations","volume":"242","year":"2024","journal-title":"Expert Syst Appl"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.07.19.26358425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:50:24Z","timestamp":1784821824000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.07.19.26358425"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":67,"URL":"https:\/\/doi.org\/10.64898\/2026.07.19.26358425","relation":{},"subject":[],"published":{"date-parts":[[2026,7,21]]},"subtype":"preprint"}}