A 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 an existing score. Of the 57,981 PE patients in the RIETE registry, 5,217 were eligible for inclusion. Median age was 68 years, with 50.6% men. Machine learning was based on 111 predictor variables, with 171 patients (3.3%) developing CTEPH. The CTEPH model demonstrated good performance with an AUC of 0.74 (95%CI: 0.73-0.75), significantly outperforming the existing CTEPH prediction score (0.57; 0.54-0.61). Additionally, 1,310 (25.1%) patients were defined as having post-PE syndrome six months after index PE. The post-PE syndrome model showed poorer performance with an AUC of 0.62 (0.61-0.62). Key predictor variables across both models included chest pain at presentation, PE location, troponin, side of clot, and dyspnea at presentation. Machine learning models show promise in predicting CTEPH but are less effective for post-PE syndrome. Future refinement, including integrating imaging data, is necessary to improve predictive performance and clinical utility.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2025-09-24
DOI
https://doi.org/10.1038/s41598-025-14893-1
Citations
1
Primary Topic
Venous Thromboembolism Diagnosis and Management
Type
article
Field-Weighted Citation Impact
1.87

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A machine learning approach to identify patients at risk for long-term consequences after pulmonary embolism

Lucas Monzón, Marija Zdraveska, Luis Ortega‐Paz, María Inés Mercado et al.
1 citations
Scientific Reports
Venous Thromboembolism Diagnosis and Management
1.87
article

A machine learning approach to identify patients at risk for long-term consequences after pulmonary embolism

Lucas Monzón, Marija Zdraveska, Luis Ortega‐Paz, María Inés Mercado, Juan J. López-Núñez, Remedios Otero, S. Suárez-Fernández, Marı́a Isabel Torres, S. Láinez-Justo, Clemens P. Spielvogel, Olga Gavín‐Sebastián, Pablo Demelo‐Rodríguez, Adriana Visonà, Raquel Barba, Francisco Galeano‐Valle, P. Álvarez-Vega, Farideh Tahmasbi, Laurent Bertoletti, D. Lambertenghi-Deliliers, Pierre Suchon, Cristina Gabara, Manuela Basaglia, Alberto García‐Ortega, Fernando Uresandi, Matteo Giorgi‐Pierfranceschi, P.J. Marchena, Gustavo Puche, Juan J. Alfonso, J. Meireles, F. García‐Bragado, Romain Chopard, Alejandro Pérez-Cabezas, Carmen Díaz‐Pedroche, A. Rivas, Sebastian Schellong, Ido Weinberg, S. Otálora, Luis Jara‐Palomares, Isabelle Mahé, Aitor Ballaz, A. Bura-Rivière, Olivier Espitia, Andris Skride, Thomas Vanassche, Benjamin Brenner, M. Pérez-Pinar, Antonio Molino, I. Jou, Hugo Hyung Bok Yoo, Elvira Grandone, Raimundo Tirado, Cihan Ay, Nazaret Pacheco-Gómez, P. López-Miguel, Alessandra Poz, Paolo Simioni, S. Acassat, Donatella Colaizzo, Behnood Bikdeli, Inna Tzoran, Olga Madridano, Antonella Tufano, Stefano Barco, Joseph A. Caprini, M.L. Peris, Oswaldo Ortíz, Dominick J. Angiolillo, Jesús Alonso‐Carrillo, Beniamino Zalunardo, M. L. Pesce, Farid Rashidi, L. Plaisance, Luis Blasco, Aída Gil‐Díaz, B. Fernández-Jiménez, Radován Malý, P. Agudo de Blás, Jana Hirmerová, Lucia Mazzolai, M. Saavedra Pozo, Z. Tazi-Mezalek, S. Fonseca, Patricia Sigüenza, Miguel Marcos, Iria Francisco, Ana M. Maestre, Raphaël Le Mao, Gili Kennet, Mónica Navas, Giovanni Barillari, Parham Sadeghipour, B. Barrón‐Andrés, E. Porceddu, J.B. López‐Sáez, E. Versini, C. Barbagelata, Peter Verhamme, Juan Gorostidi, José María Pedrajas, Jose Tafur Soto, J.I. Arcelus, Álvaro Dubois-Silva, A. González-Munera, Abedalrazq F. Khalil, Leyre Chasco, Stephan Nopp, Covadonga Gómez‐Cuervo, H. Bounameaux, Ramón Lecumberri, M. Monreal, I. Quéré, Jesús Aibar, Ana María Díaz-Brasero, Vanesa Sendín, Daniele Bissacco, F. Martín‐Martos, Judith Catella, Sina Keller, Mathias Brehon, A T Rocha, José Antonio Porras, Rosa Puchades, Françis Couturaud, M. Angelina-García, F. Rivera-Cívico, Alain Verstraete, A. Rodríguez-Cobo, José F. Varona, G. Sarlon-Bartoli, Gisela Claver, C. Pérez‐Ductor, R. Valle, César Marcon, Franca Bilora, Avinash Aujayeb, M.D. Joya, Juan Roa, Farès Moustafa, Paula Villares, Géraldine Poénou, Marijan Bosevski, M.A. Fidalgo, Renato Casana, Lucía Ordieres, B. Brandolin, Carmine Siniscalchi, A. Alberich-Conesa, B. Taflaj, C. De Juana-Izquierdo, Alicia Alda‐Lozano, A. Torrents-Vilar, P. Parra-Caballero, David Jiménez, Cristina Amado, Rui Marques, Javier Gutiérrez-Guisado, M. Barrón, I. Casado, Paolo Prandoni, I. Pabinger, José Luis Fernández‐Reyes, José Luís Lobo, J. Bascuñana, Luciano López-Jiménez, E. Vázquez, Ma Luisa Peris, B. Leclercq, Á. Blanco-Molina, Antonio López‐Ruiz, J.A. Nieto, C. García-González, David F. Jimenez, J. del Toro, Mauricio Ciammaichella, S. Soler, L. Guirado, E Grau, Juan Antonio Pagán, S. Pinto, M.J. Núñez-Fernández, Jesús Morales Maza, S. N. Morales, H. M. Bui, Teresa Sancho, A. C. Montenegro, P. Di Micco, J. González‐Martínez, Javier Trujillo-Santos, J.A. Díaz‐Peromingo, M. A. Gil de Gómez, José Carlos Escribano, A. Lorenzo, Manuel Monreal, A. Villalobos, G. Salgueiro, Carmen Fernández‐Capitán, M Romero-Bruguera, Ángela Sánchez-Juez, J. Pérez-Amorós, C. Gómez-Cepeda, L. A. Sota-Yoldi, C. Villarejo, J. Bustos-Carpio
article en
1 citations

Abstract

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 an existing score. Of the 57,981 PE patients in the RIETE registry, 5,217 were eligible for inclusion. Median age was 68 years, with 50.6% men. Machine learning was based on 111 predictor variables, with 171 patients (3.3%) developing CTEPH. The CTEPH model demonstrated good performance with an AUC of 0.74 (95%CI: 0.73-0.75), significantly outperforming the existing CTEPH prediction score (0.57; 0.54-0.61). Additionally, 1,310 (25.1%) patients were defined as having post-PE syndrome six months after index PE. The post-PE syndrome model showed poorer performance with an AUC of 0.62 (0.61-0.62). Key predictor variables across both models included chest pain at presentation, PE location, troponin, side of clot, and dyspnea at presentation. Machine learning models show promise in predicting CTEPH but are less effective for post-PE syndrome. Future refinement, including integrating imaging data, is necessary to improve predictive performance and clinical utility.

Scientific ReportsVol. 15(1)
Brigham and Women's Hospital (US), Hospital Sant Joan de Déu Barcelona (ES), NorthShore University HealthSystem (US), Harvard University (US), University of Padua (IT), Universidad de Alcalá (ES), Cumbria Northumberland Tyne and Wear NHS Foundation Trust (GB), Sheba Medical Center (IL), Casa Sollievo della Sofferenza (IT), Hospital Universitario La Paz (ES), Universidad Cardenal Herrera CEU (ES), Northumbria Healthcare NHS Foundation Trust (GB), Rambam Health Care Campus (IL), Instituto de Salud Carlos III (ES), Hospital de Sant Pau (ES), Centre Hospitalier Universitaire Vaudois (CH), Hospital General Universitario Gregorio Marañón (ES), Hospital Clínico San Carlos (ES), Centre Hospitalier Universitaire de Nantes (FR), Jacksonville University (US), Hôpital Louis-Mourier (FR), Massachusetts General Hospital (US), Centre Hospitalier Universitaire de Besançon (FR), Asepeyo Hospital Sant Cugat (ES), Hospital General Universitario Morales Meseguer (ES), Unidade Local de Saúde de Entre Douro e Vouga (PT), Hospital Universitari Sant Joan D'Alacant (ES), Hospital Virgen de la Luz (ES), Hospital Universitario de Guadalajara (ES), Methodology and Quality of Life Unit in Oncology (FR), Complejo Hospitalario Universitario de Santiago (ES), Consorcio Hospitalario Provincial de Castellón (ES), Hospital Universitario de Gran Canaria Doctor Negrín (ES), Complejo Hospitalario de Salamanca (ES), Centro de Investigación Biomédica en Red de Enfermedades Respiratorias (ES), Pauls Stradiņš Clinical University Hospital (LV), Biogipuzkoa Health Research Institute (ES), University Hospital of Zurich (CH), Hospital Universitario Rey Juan Carlos (ES), Hospital Universitario 12 De Octubre (ES), Hospital Sierrallana (ES), University Hospital of Geneva (CH), Hospital Txagorritxu (ES), Hospital Regional Universitario de Málaga (ES), Hospital Universitario Araba (ES), Administração Regional de Saúde de Lisboa e Vale do Tejo (PT), Hospital de Poniente (ES), Hospital San Pedro de Alcántara (ES), University Hospital Plzen (CZ), Hôpital Nord (FR), Hospital Clínic de Barcelona (ES), Hospital Universitario Virgen de las Nieves (ES), Hospital de Galdakao (ES), Hospital Universitario HM Madrid (ES), Federico II University Hospital (IT), Complejo Hospitalario de Jaén (ES), Hospital São Rafael (BR), Presidio Ospedaliero (IT), Hôpital Rangueil (FR), Hôpital Edouard Herriot (FR), Hospital Universitario Reina Sofía (ES), Krankenhaus Dresden-Friedrichstadt (DE), Hospital General Universitari de Castelló (ES), Ospedale Santa Maria della Misericordia di Udine (IT), Hospital Universitario Doctor Peset (ES), Instituto Ramón y Cajal de Investigación Sanitaria (ES), Parc Sanitari Sant Joan de Déu (ES), Imam Reza Hospital (IR), Centre Hospitalier Ibn Sina (MA), Hospital Universitario de La Princesa (ES), Fundación Santa Fe de Bogotá (CO), Centre Hospitalier Régional Universitaire de Brest (FR), Instituto de Biomedicina de Sevilla (ES), IRCCS Istituto Auxologico Italiano (IT), Clinica Universidad de Navarra (ES), Hospital Clínico Universitario Lozano Blesa (ES), Ospedale di Parma (IT), Ospedale Castelfranco Veneto (IT), Médipole Garonne (FR), Hospital de Cruces (ES), Hospital Universitario HM Sanchinarro (ES), Hospital Universitario del Vinalopó (ES), University Hospital Hradec Králové (CZ), Hospital General Universitario de Alicante Doctor Balmis (ES), Hospital Universitario Puerto Real (ES), Hospital San Pedro (ES), Donostiako Unibertsitate Ospitalea (ES), Servicio Diabetología Hospital Córdoba (AR), Complexo Hospitalario Universitario A Coruña (ES), Centro Hospitalar de Vila Nova de Gaia (PT), Hôpital Saint Eloi (FR), Hospital General Universitario de Albacete (ES), Santa Lucía University General Hospital (ES), Hospital General de Elda (ES), Hospital Valle del Nalón (ES), Hospital Universitario De Cabueñes (ES), Hospital Universitario Virgen de la Arrixaca (ES), Hospital Universitari Joan XXIII de Tarragona (ES), Hospital Universitario Lluís Alcanyís (ES), Hospital Universitario Virgen del Rocío (ES), Hospital Universitari Germans Trias i Pujol (ES), Hanoi Medical University Hospital (VN), Hospital Universitari de Girona Doctor Josep Trueta (ES), Hospital Universitario de Móstoles (ES), Hospital Comarcal de Inca (ES), Centre Hospitalier Universitaire de Saint-Étienne (FR), Shaheed Rajaei Cardiovascular Medical and Research Center (IR), Complejo Hospitalario de Pontevedra (ES), Hospital Universitario Infanta Sofía (ES), Hôpital de la Timone (FR), Istituti Ospitalieri di Cremona (IT), John Cabot University (IT), University of Florida Health Science Center (US), Universidad Católica de Murcia (ES), Tehran University of Medical Sciences (IR), Medical University of Vienna (AT), Ss. Cyril and Methodius University in Skopje (MK), Universidade Estadual Paulista (Unesp) (BR), Universidad de Navarra (ES), Florida College (US), KU Leuven (BE)
Sanofi
Openalex Percentile: Top 12%
Venous Thromboembolism Diagnosis and Management
1.87
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.