biostudies-literatureEnzer NACOPD FoundationNHLBI NIH HHSNational Heart, Lung, and Blood Institute17981https://www.ebi.ac.uk/biostudies/studies/S-EPMC11297919biostudies-literatureUnknown14(1)Low muscle mass is associated with numerous adverse outcomes independent of other associated comorbid diseases. We aimed to predict and understand an individual's risk for developing low muscle mass using proteomics and machine learning. We identified eight biomarkers associated with low pectoralis muscle area (PMA). We built three random forest classification models that used either clinical measures, feature selected biomarkers, or both to predict development of low PMA. The area under the receiver operating characteristic curve for each model was: clinical-only = 0.646, biomarker-only = 0.740, and combined = 0.744. We displayed the heterogenetic nature of an individual's risk for developing low PMA and identified two distinct subtypes of participants who developed low PMA. While additioScientific reportsProteomics and machine learning in the prediction and explanation of low pectoralis muscle area.PMC11297919K08HL145118R01 HL153460T32HL105346T32 HL007633R01 HL149861T32HL007633U01HL089897R01 HL116931R01HL116931U01 HL089897L70 HL165665R01 HL173017U01 HL089856T32 HL105346R01 HL122464K08 HL145118R01 HL164824Diaz AARuiz MEWilson SChiles JCortese EPhelan JRosiello RWest AGlosser KJaksha JConsolaro PBruening EBlum MLGCastro VGaeckle NThomashow BGuo CWilensky KAsh SYD'Souza BMMcEvoy CLaroia AJacobson FLSoler XPonce MCutlip CSprenger KKunisaki KMWu TDBillings JHassler MOates GKirshenboim ZAllen TLSciurba FDass CKazerooni EMichelson JConrad DHardy SAnzueto AMiller LBailey WCMielke JYun KCharpentier MEnzer NASingh SPLopez VWashko GRNath HBarr RGFeeley NMaselli-Caceres DKuhn JDGil MHan MKLee CZhao LEngel ELynch DAShenoy KSears LLawson DBon JMason SKirk DSuri RCurtis JLMarentette KMcGonagle FJameson LWestney GQuerido GLabaki WAdams NWendt CHComellas AKligerman SHersh CPChiles JWYen ARegan EDransfield MTLaFon DCGalban CJGagne SMBarry JKaroleski CBailey MPHoth KFMartineau AKuck LWang AAdams SGDavis SLincoln RWells MSasse CDelancy JBhatt SPManapragada PBowler RPHowell WEstepar RSJForeman MGHsiao AMacDonald DAddi SHanania NASalas PSFlenaugh ELPolverino FBertrand LFoster DRysso KHawn JBodduluri SIyer AGarcia ENoren BChampagne JDeMeo DLChoi BDitter TShirahata TSheridan RFortis SBoriek AGrumley SChandra DHeinz BMarchetti Nde Rosen VVLCriner GJSwenson SBaldomero ARuvuna LNarendra DSelwood KAtik MBenos PTMonaco TMcDonald MLDuesterbeck AGirard TFinigan JArminavage DDuin JBautista GYun JHGregg RCOPDGene Study ConsortiumFlorez EGebrekristos HQuraishi MYuan NFWade RCMcCloskey LPecheco WSrivastava-Malhotra SAustin JHMfalseProteomics and machine learning in the prediction and explanation of low pectoralis muscle area.Low muscle mass is associated with numerous adverse outcomes independent of other associated comorbid diseases. We aimed to predict and understand an individual's risk for developing low muscle mass using proteomics and machine learning. We identified eight biomarkers associated with low pectoralis muscle area (PMA). We built three random forest classification models that used either clinical measures, feature selected biomarkers, or both to predict development of low PMA. The area under the receiver operating characteristic curve for each model was: clinical-only = 0.646, biomarker-only = 0.740, and combined = 0.744. We displayed the heterogenetic nature of an individual's risk for developing low PMA and identified two distinct subtypes of participants who developed low PMA. While additio2024-01-01T00:00:00Z2024 Aug2026-07-14T19:46:08.866Z2025-02-19T04:40:58.983ZS-EPMC112979193909765810.1038/s41598-024-68447-y