Machine learning to predict major bleeding during anticoagulation for venous thromboembolism: possibilities and limitations

Predictive tools for major bleeding (MB) using machine learning (ML) might be advantageous over traditional methods. We used data from the Registro Informatizado de Enfermedad TromboEmbólica (RIETE) to develop ML algorithms to identify patients with venous thromboembolism (VTE) at increased risk of...

Descripción completa

Detalles Bibliográficos
Autores: Mora, D., Mateo, J., Nieto, J.A., Bikdeli, B., Yamashita, Y., Barco, S., Jimenez, D., Demelo-Rodriguez, P., Rosa, V., Yoo, H.H.B., Sadeghipour, P., Monreal, M., Adarraga, M.D., Alberich-Conesa, A., Alonso-Carrillo, J., Agudo, P., Amado, C., Amorós, S., Arcelus, J.I., Ballaz, A., Barba, R., Barbagelata, C., Barrón, M., Barrón-Andrés, B., Blanco-Molina, A., Botella, E., Carrero-Arribas, R., Casado, I., Chasco, L., Criado, J., del Toro, J., De Ancos, C., De Juana-Izquierdo, C., Demelo-Rodríguez, P., Díaz-Brasero, A.M., Díaz-Pedroche, M.C., Díaz-Peromingo, J.A., Díaz-Simón, R., Dubois Silva, Alvaro, Escribano, J.C., Espósito, F., Falgá, C., Farfán-Sedano, A.I., Fernández-Aracil, C., Fernández-Capitán, C., Fernández-Jiménez, B., Fernández-Muixi, J., Fernández-Reyes, J.L., Font, C., Francisco, I., Galeano-Valle, F., García, M.A., García de Herreros, M., García-Bragado, F., García-González, C., García-Ortega, A., Gavín-Sebastián, O., Gil-De Gómez, M., Gil-Díaz, A., Gómez-Cuervo, C., Gómez-Mosquera, A.M., González-Martínez, J., Grau, E., Guirado, L., Gutiérrez, J., Hernández-Blasco, L., Jaras, M.J., Jiménez, D., Jou, I., Joya, M.D., Lacruz, B., Lainez-Justo, S., Lecumberri, R., Lobo, J.L., López-De la Fuente, M., López-Jiménez, L., López-Miguel, P., López-Núñez, J.J., López-Reyes, R., López-Ruiz, A., López-Sáez, J.B., Lorente, M.A., Lorenzo, A., Lumbierres, M., Madridano, O., Maestre, A., Marcos, M., Martín-Guerra, J.M., Martín-Martos, F., Mas-Maresma, L., Mellado, M., Mena, E., Mercado, M.I., Moisés, J., Muñoz-Blanco, A., Muñoz-Gamito, G., Núñez Fernández, Manuel Jesús, Osorio, J., Otalora, S., Pacheco-Gómez, N., Parra, P., Pedrajas, J.M., Pérez-Ductor, C., Pérez-Pérez, J.L., Peris, M.L., Pesce, M.L., Porras, J.A., Poyo-Molina, J., Puchades, R., Riera-Mestre, A., Rivera-Civico, F., Rivera Gallego, Alberto, Roca, M., Rodríguez-Cobo, A., Rubio, C.M., Ruiz-Giménez, N., Ruiz-Ruiz, J., Salgueiro, G., Sancho, T., Sendín, V., Sigüenza, P., Soler, S., Suriñach, J.M., Tiberio, G., Tolosa, C., Torres, M.I., Trujillo-Santos, J., Uresandi, F., Usandizaga, E., Valle, R., Varona, J.F., Vela, J.R., Vidal, G., Villalobos, A., Villares, P., Ay, C., Nopp, S., Pabinger, I., Engelen, M., Verhamme, P., Verstraete, A., Arguello, J.D., Montenegro, A.C., Roa, J., Malý, R., Accassat, S., Bertoletti, L., Bura-Riviere, A., Catella, J., Chopard, R., Couturaud, F., Espitia, O., Grange, C., Leclercq, B., Le Mao, R., Mahé, I., Moustafa, F., Plaisance, L., Poenou, G., Sarlon-Bartoli, G., Suchon, P., Versini, E., Schellong, S., Braester, A., Brenner, B., Kenet, G., Najib, D., Tzoran, I., Basaglia, M., Bilora, F., Bortoluzzi, C., Brandolin, B., Ciammaichella, M., Colaizzo, D., De Angelis, A., Dentali, F., Di Micco, P., Grandone, E., Imbalzano, E., Merla, S., Pesavento, R., Prandoni, P., Scarinzi, P., Siniscalchi, C., Taflaj, B., Tufano, A., Visonà, A., Vo Hong, N., Zalunardo, B., Kigitovica, D., Skride, A., Fonseca, S., Manuel, M., Meireles, J., Bosevski, M., Zdraveska, M., Bounameaux, H., Mazzolai, L., Aujayeb, A., Caprini, J.A., Weinberg, I., Bui, H.M.
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Servizo Galego de Saúde (SERGAS)
Repositorio:RUNA. Repositorio da Consellería de Sanidade e Sergas
OAI Identifier:oai:runa.sergas.gal:20.500.11940/21701
Acceso en línea:https://portalcientifico.sergas.gal//documentos/6433d316e8f2fa0e62f2c0fa
http://hdl.handle.net/20.500.11940/21701
Access Level:acceso abierto
Palabra clave:Humans
Venous Thromboembolism
Registries
Hemorrhage
Predictive Value of Tests
Anticoagulants
Pulmonary Embolism
AS A Coruña
CHUAC
AS Pontevedra
CHUP
AS Vigo
CHUVI
Descripción
Sumario:Predictive tools for major bleeding (MB) using machine learning (ML) might be advantageous over traditional methods. We used data from the Registro Informatizado de Enfermedad TromboEmbólica (RIETE) to develop ML algorithms to identify patients with venous thromboembolism (VTE) at increased risk of MB during the first 3 months of anticoagulation. A total of 55 baseline variables were used as predictors. New data prospectively collected from the RIETE were used for further validation. The RIETE and VTE-BLEED scores were used for comparisons. External validation was performed with the COMMAND-VTE database. Learning was carried out with data from 49 587 patients, of whom 873 (1.8%) had MB. The best performing ML method was XGBoost. In the prospective validation cohort the sensitivity, specificity, positive predictive value and F1 score were: 33.2%, 93%, 10%, and 15.4% respectively. F1 value for the RIETE and VTE-BLEED scores were 8.6% and 6.4% respectively. In the external validation cohort the metrics were 10.3%, 87.6%, 3.5% and 5.2% respectively. In that cohort, the F1 value for the RIETE score was 17.3% and for the VTE-BLEED score 9.75%. The performance of the XGBoost algorithm was better than that from the RIETE and VTE-BLEED scores only in the prospective validation cohort, but not in the external validation cohort.

Similares en LA Referencia