<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><submitter>MULTI consortium</submitter><funding>NIA NIH HHS</funding><pubmed_abstract>Disease heterogeneity and commonality pose significant challenges to precision medicine, as traditional approaches frequently focus on single disease entities and overlook shared mechanisms across conditions&lt;sup>1&lt;/sup>. Inspired by pan-cancer&lt;sup>2&lt;/sup> and multi-organ research&lt;sup>3&lt;/sup>, we introduce the concept of "pan-disease" to investigate the heterogeneity and shared etiology in brain, eye, and heart diseases. Leveraging individual-level data from 129,340 participants, as well as summary-level data from the MULTI consortium, we applied a weakly-supervised deep learning model (Surreal-GAN&lt;sup>4,5&lt;/sup>) to multi-organ imaging, genetic, proteomic, and RNA-seq data, identifying 11 AI-derived biomarkers - called Multi-organ AI Endophenotypes (MAEs) - for the brain (Brain 1-6), eye (E</pubmed_abstract><journal>medRxiv : the preprint server for health sciences</journal><pagination>2025.08.09.25333350</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12363687</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>Multi-organ AI Endophenotypes Chart the Heterogeneity of Pan-disease in the Brain, Eye, and Heart.</pubmed_title><pmcid>PMC12363687</pmcid><funding_grant_id>RF1 AG092412</funding_grant_id><funding_grant_id>RF1 AG054409</funding_grant_id><pubmed_authors>Zalesky A</pubmed_authors><pubmed_authors>Duggan MR</pubmed_authors><pubmed_authors>Erus G</pubmed_authors><pubmed_authors>Tian YE</pubmed_authors><pubmed_authors>Srinivasan D</pubmed_authors><pubmed_authors>Bai W</pubmed_authors><pubmed_authors>Walker KA</pubmed_authors><pubmed_authors>Anagnostakis F</pubmed_authors><pubmed_authors>Boquet-Pujadas A</pubmed_authors><pubmed_authors>Yang Z</pubmed_authors><pubmed_authors>Davatzikos C</pubmed_authors><pubmed_authors>Wen J</pubmed_authors><pubmed_authors>Joynes CM</pubmed_authors><pubmed_authors>Patel PJ</pubmed_authors><pubmed_authors>MULTI consortium</pubmed_authors></additional><is_claimable>false</is_claimable><name>Multi-organ AI Endophenotypes Chart the Heterogeneity of Pan-disease in the Brain, Eye, and Heart.</name><description>Disease heterogeneity and commonality pose significant challenges to precision medicine, as traditional approaches frequently focus on single disease entities and overlook shared mechanisms across conditions&lt;sup>1&lt;/sup>. Inspired by pan-cancer&lt;sup>2&lt;/sup> and multi-organ research&lt;sup>3&lt;/sup>, we introduce the concept of "pan-disease" to investigate the heterogeneity and shared etiology in brain, eye, and heart diseases. Leveraging individual-level data from 129,340 participants, as well as summary-level data from the MULTI consortium, we applied a weakly-supervised deep learning model (Surreal-GAN&lt;sup>4,5&lt;/sup>) to multi-organ imaging, genetic, proteomic, and RNA-seq data, identifying 11 AI-derived biomarkers - called Multi-organ AI Endophenotypes (MAEs) - for the brain (Brain 1-6), eye (E</description><dates><release>2025-01-01T00:00:00Z</release><publication>2025 Aug</publication><modification>2026-06-19T03:16:49.51Z</modification><creation>2026-06-19T03:07:39.208Z</creation></dates><accession>S-EPMC12363687</accession><cross_references><pubmed>40832432</pubmed><doi>10.1101/2025.08.09.25333350</doi></cross_references></HashMap>