Portal de Periódicos da CAPES

Machine learning analysis of serum biomarkers for cardiovascular risk assessment in chronic kidney disease

2019; Oxford University Press; Linguagem: Inglês

10.1093/ckj/sfz094

2048-8513

Carles Forné, Serafí Cambray, Marcelino Bermúdez-López, Elvira Fernández, Milica Božić, José Manuel Valdivielso, José Regidor, Jaume Almirall, Esther Ponz, Jesús Arteaga Coloma, Auxiliadora Bajo Rubio, Raquel Díaz, Montserrat Belart Rodríguez, Antonio Gascón, Jordi Bover Sanjuán, Josep Bronsoms Artero, J.B. Cabezuelo, Jesús Calviño Varela, Pilar Caro Acevedo, Jordi Carreras Bassa, Aleix Cases, Elisabet Massó Jiménez, Rosario Moreno López, Secundino Cigarrán, Saray López Prieto, Lourdes Comas Mongay, Isabel Comerma, Teresa Compte Jové, Marta Cuberes Izquierdo, Fernando de Álvaro, Covadonga Hevia Ojanguren, Gabriel de Arriba, Dolores del Pino, Rafael Diaz-Tejeiro Izquierdo, Francisco Ahijado Hormigos, Marta Dotori, Verónica Duarte, Sara Estupiñan Torres, José Fernández Reyes, Loreto Fernández Rodríguez, Guillermina Fernández, Antonio Galán Serrano, César García Cantón, Antonio Luis García Herrera, Mercedes García Mena, Luis Gil Sacaluga, María Aguilar, José Luis Górriz, Emma Huarte Loza, José Luis Lerma, A. Cañada, Jesús Pedro Marín Álvarez, Nàdia Martín Alemany, Jesús Martín García, Alberto Martínez Castelao, María Martínez Villaescusa, Isabel Martínez, Itsaso Larrabide Eguren, Silvia Moreno Los Huertos, Ricardo Mouzo Mirco, Antonia Munar Vila, Ana Beatriz Muñoz Díaz, Juan F. González, Javier Nieto, Agustín Carreño, Enrique Novoa Fernández, Alberto Ortíz, Beatriz Fernández, Vicente Paraíso, Miguel Pérez Fontán, Ana Peris Domingo, Celestino Piñera Haces, D. Garrido, Mario Prieto Velasco, Carmina Puig Marí, Maite Rivera, Eduardo Rubio González, M. Pilar Ruiz, Mercedes Salgueira Lazo, Ana Isabel Martínez Puerto, José Antonio Sánchez Tomero, José Emilio Hernández Sánchez, Ramon Sans Lorman, Ramón Saracho, Maria‐Rosa Sarrias, Daniel Serón, María José Soler, Clara Barrios, Fernando Henrique Sousa, D Torán, Fernando Tornero Molina, José Javier Usón Carrasco, Ildefonso Valera Cortes, Merce Vilaprinyo del Perugia, Rafael C Virto Ruiz, Vicente Pallarés‐Carratalá, C. Santos Altozano, Miguel Artigao Ródenas, Inés Gil Gil, Francisco Adan Gil, E. Criado, Rafael Durá Belinchón, Jose Ma Fernández Toro, J.A. Divisón,

Bone health and osteoporosis research

Abstract Background Chronic kidney disease (CKD) patients show an increased burden of atherosclerosis and high risk of cardiovascular events (CVEs). There are several biomarkers described as being associated with CVEs, but their combined effectiveness in cardiovascular risk stratification in CKD has not been tested. The objective of this work is to analyse the combined ability of 19 biomarkers associated with atheromatous disease in predicting CVEs after 4 years of follow-up in a subcohort of the NEFRONA study in individuals with different stages of CKD without previous CVEs. Methods Nineteen putative biomarkers were quantified in 1366 patients (73 CVEs) and their ability to predict CVEs was ranked by random survival forest (RSF) analysis. The factors associated with CVEs were tested in Fine and Gray (FG) regression models, with non-cardiovascular death and kidney transplant as competing events. Results RSF analysis detected several biomarkers as relevant for predicting CVEs. Inclusion of those biomarkers in an FG model showed that high levels of osteopontin, osteoprotegerin, matrix metalloproteinase-9 and vascular endothelial growth factor increased the risk for CVEs, but only marginally improved the discrimination obtained with classical clinical parameters: concordance index 0.744 (95% confidence interval 0.609–0.878) versus 0.723 (0.592–0.854), respectively. However, in individuals with diabetes treated with antihypertensives and lipid-lowering drugs, the determination of these biomarkers could help to improve cardiovascular risk estimates. Conclusions We conclude that the determination of four biomarkers in the serum of CKD patients could improve cardiovascular risk prediction in high-risk individuals.