biostudies-literatureNopp SGesellschaft für Thrombose- und Hämostaseforschung32744https://www.ebi.ac.uk/biostudies/studies/S-EPMC12460599biostudies-literatureUnknown15(1)Pulmonary embolism (PE) can result in long-term sequelae, such as post-PE syndrome, including persistent dyspnea and chronic thromboembolic pulmonary hypertension (CTEPH). Existing prediction tools for severe post-PE complications lack sensitivity and specificity. This study aimed to develop a machine learning model to identify patients at risk for long-term consequences after PE. Using data from the RIETE registry, the largest prospective international PE registry, we developed supervised machine learning models to identify patients at increased risk of CTEPH and post-PE syndrome. Our approach involved data preprocessing, model training via random forest algorithm, and validation through Monte-Carlo cross-validation. The performance of the CTEPH prediction model was benchmarked against anScientific reportsA machine learning approach to identify patients at risk for long-term consequences after pulmonary embolism.PMC12460599GTH Early Career Research Grant 2023Maza JMFidalgo MASancho TTufano AChasco LDi Micco PAngelina-Garcia MVillalobos ARocha ATSiniscalchi CBascunana JGil-Diaz AVersini ERomero-Bruguera MAngiolillo DJMazzolai LLorenzo AMolino AColaizzo DPorras JADubois-Silva ANunez-Fernandez MJAlonso-Carrillo JDiaz-Pedroche MCVerhamme PAgudo de Blas PBui HMBarbagelata CAcassat SClaver GGarcia-Bragado FBura-Riviere AMonreal MBrandolin BOtalora SFernandez-Jimenez BAy CTafur JCaprini JASpielvogel CZdraveska MBarba RRoa JFernandez-Reyes JLMarcon CCasana REscribano JCLopez-Jimenez LTrujillo-Santos JGrandone EVisona AMarques RHirmerova JBilora FMartin-Martos FNieto JALainez-Justo SGomez-Cepeda CFernandez-Capitan CVillares PLopez-Nunez JJRivera-Civico FPeris MLPuchades RKhalil ABustos-Carpio JPlaisance LRivas APesce MLPerez-Amoros JParra-Caballero PSadeghipour PMaly RLopez-Ruiz ADiaz-Brasero AMGuirado LUresandi FSchellong STzoran IAlfonso JOtero RValle RDiaz-Peromingo JAVerstraete ABasaglia MDe Juana-Izquierdo CGarcia-Ortega ATorrents-Vilar AAmado CTorres MIVarona JFGavin-Sebastian ONopp SBarillari GPuche GAibar JRIETE InvestigatorsGorostidi JBrehon MPoz ASota-Yoldi LAFonseca SWeinberg ILecumberri RBallaz AFrancisco IKennet GPerez-Cabezas AOrdieres LAlda-Lozano ASoler STahmasbi FKeller SMercado MISkride ASuchon PAujayeb ABrenner BYoo HHBBarco SMarcos MOrtega-Paz LPoenou GBarron-Andres BGomez-Cuervo COrtiz OVanassche TBlanco-Molina AMarchena PJPrandoni PAlvarez-Vega PGarcia-Gonzalez CLobo JLRodriguez-Cobo ASuarez-Fernandez SMaestre AMahe IMonzon LGrau EMontenegro ACMoustafa FGonzalez-Martinez JPinto SMorales SNNavas MSZalunardo BPacheco-Gomez NHernandez-Blasco LGaleano-Valle FJara-Palomares LAlberich-Conesa AJou ICouturaud FLambertenghi-Deliliers DLopez-Miguel PJoya MDSarlon-Bartoli GTazi-Mezalek ZCasado ILeclercq BArcelus JILopez-Saez JBBounameaux HCatella JPedrajas JMGabara CChopard RBissacco DCiammaichella MMEspitia OSimioni PSanchez-Juez APerez-Ductor CLe Mao RGonzalez-Munera ATaflaj BMeireles JDemelo-Rodriguez PGil de Gomez MAPagan JPorceddu EPerez-Pinar MTirado RVillarejo CBertoletti LBikdeli BBarron MDel Toro JMadridano ORashidi FMartin-Del Pozo MGutierrez-Guisado JJimenez DPabinger IGiorgi-Pierfranceschi MSalgueiro GVazquez ESiguenza PQuere ISendin VBosevski MfalseA machine learning approach to identify patients at risk for long-term consequences after pulmonary embolism.Pulmonary embolism (PE) can result in long-term sequelae, such as post-PE syndrome, including persistent dyspnea and chronic thromboembolic pulmonary hypertension (CTEPH). Existing prediction tools for severe post-PE complications lack sensitivity and specificity. This study aimed to develop a machine learning model to identify patients at risk for long-term consequences after PE. Using data from the RIETE registry, the largest prospective international PE registry, we developed supervised machine learning models to identify patients at increased risk of CTEPH and post-PE syndrome. Our approach involved data preprocessing, model training via random forest algorithm, and validation through Monte-Carlo cross-validation. The performance of the CTEPH prediction model was benchmarked against an2025-01-01T00:00:00Z2025 Sep2026-06-03T19:34:26.745Z2026-04-30T03:12:23.133ZS-EPMC124605994099319510.1038/s41598-025-14893-1