biostudies-literatureAtabaki-Pasdar NNovo Nordisk FoundationInnovative Medicines InitiativeWellcome Trust Senior InvestigatorKnut and Alice Wallenberg FoundationHenning och Johan Throne-HolstsNNF Center for Basic Metabolic ResearchNIHErling-Persson FoundationScience for Life LaboratorySwedish Foundation for Strategic ResearchEuropean Research CouncilNIDDK NIH HHSNIHR Exeter Clinical Research FacilitySteno Diabetes Center Copenhagen (SDCC)Medical Research CouncilNational Institute for Health Research (NIHR)Novo Nordisk Foundation Center for Protein ResearchWellcome TrustNovo Nordisk FondenNIHR clinical senior lecturer fellowshipHans Werthéne1003149https://www.ebi.ac.uk/biostudies/studies/S-EPMC7304567biostudies-literatureUnknown17(6)<h4>Background</h4>Non-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in individuals with and without type 2 diabetes (T2D). Early diagnosis of NAFLD is important, as this can help prevent irreversible damage to the liver and, ultimately, hepatocellular carcinomas. We sought to expand etiological understanding and develop a diagnostic tool for NAFLD using machine learning.<h4>Methods and findings</h4>We utilized the baseline data from IMI DIRECT, a multicenter prospective cohort study of 3,029 European-ancestry adults recently diagnosed with T2D (n = 795) or at high risk of developing the disease (n = 2,234). Multi-omics (genetic, transcriptomic, proteomic, and metabolomic) and clinical (liver enzymes and other serological biomarkers, anthPLoS medicinePredicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts.PMC730456717/0005624Hansen GroupNNF18OC0031650CS-2015-15-018SDCC 3.F CMPU01 DK105535115317 (DIRECT)106130U01-DK105535MC_UU_12015/3090532Pedersen GroupNNF17OC0027594NF-SI-0617-10090NNF14CC0001PI Søren BrunakNNF15OC0016692681742203141MC_UU_00006/4098381ERC-2015-CoG - 681742_NASCENTNF-SI-0616-10080212259Ohlsson MMcCarthy MICederberg HFrost GHaussler RSMutie PMVinuela AVangipurapu JBell JDDale MThomas CEHansen THBrunak SForgie IMMahajan AFitipaldi HRutters FKurbasic AKoivula RWFrau FMcEvoy DDermitzakis EWalker MPavo IKennedy GSharma S't Hart LMPedersen HKJones AGHeggie AAdamski JHattersley ATAtabaki-Pasdar NKokkola TRidderstrale MLaakso MMari AFranks PWMasi FHaid MDawed AYAllin KHMusholt PBBeulens JWJThomsen HSRaverdy VPearson ERMcDonald TJChabanova ERuetten HElders PJMSchwenk JMGupta RFernandez JPedersen OBrage SPomares-Millan HThomas ELGiordano GNHansen THong MGVestergaard HPattou FfalsePredicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts.<h4>Background</h4>Non-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in individuals with and without type 2 diabetes (T2D). Early diagnosis of NAFLD is important, as this can help prevent irreversible damage to the liver and, ultimately, hepatocellular carcinomas. We sought to expand etiological understanding and develop a diagnostic tool for NAFLD using machine learning.<h4>Methods and findings</h4>We utilized the baseline data from IMI DIRECT, a multicenter prospective cohort study of 3,029 European-ancestry adults recently diagnosed with T2D (n = 795) or at high risk of developing the disease (n = 2,234). Multi-omics (genetic, transcriptomic, proteomic, and metabolomic) and clinical (liver enzymes and other serological biomarkers, anth2020-01-01T00:00:00Z2020 Jun2026-05-04T10:20:04.935Z2025-06-01T12:32:19.38ZS-EPMC73045673255919410.1371/journal.pmed.1003149