학술논문
Deploying unsupervised clustering analysis to derive clinical phenotypes and risk factors associated with mortality risk in 2022 critically ill patients with COVID-19 in Spain
Document Type
Report
Author
Rodríguez, Alejandro; Ruiz-Botella, Manuel; Martín-Loeches, Ignacio; Jimenez Herrera, María; Solé-Violan, Jordi; Gómez, Josep; Bodí, María; Trefler, Sandra; Papiol, Elisabeth; Díaz, Emili; Suberviola, Borja; Vallverdu, Montserrat; Mayor-Vázquez, Eric; Albaya Moreno, Antonio; Canabal Berlanga, Alfonso; Sánchez, Miguel; del Valle Ortíz, María; Ballesteros, Juan Carlos; Martín Iglesias, Lorena; Marín-Corral, Judith; López Ramos, Esther; Hidalgo Valverde, Virginia; Vidaur Tello, Loreto Vidaur; Sancho Chinesta, Susana; Gonzáles de Molina, Francisco Javier; Herrero García, Sandra; Sena Pérez, Carmen Carolina; Pozo Laderas, Juan Carlos; Rodríguez García, Raquel; Estella, Angel; Ferrer, Ricard; Loza, Ana; Zapata, Diego Matallana; Torres, Isabel Díaz; Cuadros, Sonia Ibaéez; Nuéez, María Recuerda; Pérez, Maria Luz Carmona; Ramos, Jorge Gómez; Casas, Alba Villares; Cantón, María Luisa; Contreras, José Javier González; Chomón, Helena Pérez; Chicote, Nerissa Alvarez; González, Alberto Sousa; De Alba Aparicio, María; Laderas, Juan Carlos Pozo; Cano, Sara Moreno; García, Ruth Jorge; Montori, Laura Sánchez; García, Sandra Herrero; Moreno, Paula Abanses; García, Carlos Mayordomo; Bonet, Tomás Mallor; Bonafonte, Paula Omedas; Gonzalez, Enric Franquesa; Vidales, Nestor Bueno; Buil, Paula Ocabo; Arbeloa, Carlos Serón; Sancho, Isabel; Ibaéez, Pablo Guerrero; Gutierrez, Pablo; Valdovinos, María Concepción; Canto, Raquel; Mariéo, Ana Luz Balán; Fernández, María José Gutiérrez; Cuadrado, Marta Martín; Arias, Belén García; Espina, Lorena Forcelledo; Soria, Lucía Viéa; Iglesias, Lorena Martín; Amor, Lucía López; Rey, Elisabet Fernández; Prieto, Emilio García; Ruíz, Débora Fernández; González, Carla Martínez; Socias, Lorenzo; Borges-Sá, Marcio; Pérez, María Aranda; Socias, Antonia; Goytisolo, José Ma Bonell; Mayayo, Inmaculada Alcalde; Corradini, Carlos; Ceniceros, Isabel; Rodríguez, Edwin; Rota, Jose Ignacio Ayestarán; Novo, Mariana Andrea Novo; Climent, Joaquim Colomina; Castilla, Albert Figueras; Rullan, Tomàs Leal; Sastre, Maria Magdalena Garcias; Senoff, Rossana Pérez; Bouza, Ramón Fernández-Cid; González, Juan Carlos Martín; Ortiz, Carmen Pérez; Santana, José Luciano Cabrera; Agra, Juan José Cáceres; Romero, Domingo González; Ortega, Ana Casamitjana; Gómez, Luis Alberto Ramos; Solé-Violán, Jordi; Moreno, Gerard; Claverias, Laura; Carbonell, Raquel; Esteve, Erika; Olona, Montserrat; Teixidó, Xavier; Vidal, Monserrat Vallverdú; Garrido, Begoéa Balsera; Gallofré, Elisabeth Papiol; Martell, Raquel Albertos; Peéarrocha, Rosa Alcaráz; Casals, Xavier Nuvials; Roca, Ricard Ferrer; Vázquez, Eric Adrián Mayor; Campo, Ferrán Roche; Martínez, Pablo Concha; Llasat, Diego Franch; Masclanz, Joan Ramón; Pérez, Purificación; Muéoz, Rosana; Vila, Clara; de Molina, Francisco Javier González; Moya, Elisabeth Navas; Trenado, Josep; Vallverdú, Imma; Castaéé, Eric; Santos, Emili Díaz; Goma, Gemma; Moglia, Edgar; Moreno, Antonio Albaya; Crespo, Carlos Marian; Pérez, Carmen Carolina Sena; Linde, Francisca Arbol; Donaire, Diana Monge; Martínez, Vega Losada; Castroviejo, Nuria Rodrigo; Ferrigno, Gerardo; Beltrán, Reyes; Sanmartino, Carolina; Maján, Concepción Tarancón; Gutiérrez, Alfredo Marcos; Valverde, Virginia Hidalgo; López, Caridad Martín; Badallo, Oihane; del Valle Ortiz, María; Arlanzón, Rebeca Vara; Posadilla, David Iglesias; Recio, María Teresa; Laza, Enrique Laza; Curto, Elena Gallego; García, Ma Carmen Sánchez; Díaz-Tavora, Miguel; Mancha, Rosa; Montes, Ana Ortega; Barbachano, Isabel Gallego; Mantiéán, Eva Sanmartín; Cordero, María Lourdes; García, Raquel María Rodríguez; Zapata, Jorge Gámez; Vázquez, María Gestal; Orjales, María José Castro; Diéguez, María Isabel Ãlvarez; Velasco, Carmen Rivero; Massa, Beatriz Lence; Varela, Ignacio Martínez; Tejedor, Alberto Hernández; Ramos, Esther Ma López; Elvira, Laura Alcázar Sánchez; Montero, Rocío Molina; Delgado, Ma Consuelo Pintado; de la Peéa, María Trascasa MuéozMuéoz; de Zárate Ansotegui, Yaiza Betania Ortiz; Aranda, Alejandra Acha; Lucas, Juan Higuera; Giralt, Juan Antonio Sanchez; Llano, Marta Chicot; Fernández, Nuria Arevalillo; Galindo, Marta Sánchez; Ruiz, Ricardo Andino; Berlanga, Alfonso Canabal; Nieto, Mercedes; Sarmiento, Eduardo Arias; Blázquez, Adoración Bueno; de la Casa, Rosa María; Martín, Fátima; López, Samuel González; Q uintana, Elena Martínez; Rueda, Bernardo Gil; Caéigral, Ãurea Higon; Gómez, Laura López; Delis, Pablo Safwat Bayoumi; Muore, Augusto Montenegro; Luengas, Ãngel Andrés Agamez; Soler, Enriqueta Andreu; Pérez, Ana Beatriz Pérez; de Gea García, José Higinio; Rubio, Rubén Jara; Cámara, Silvia Sánchez; Flores, Alba Moreno; Sánchez, José Moya; Martínez, Daniel Francisco Pérez; del Rey Carrión, Ma Desamparados; Lledó, María José Rico; Navarro, Juana María Serrano; Ruíz, Juan Francisco Martín; Hidalgo, Julián Triviéo; Ferrer, Ãfrica López; Navalón, Isabel Cremades; Payá, Josefa Murcia; Gallego, JM Allegre; del Carmen Lorente, María; Gonsalvez, Marta; Natera, Ruth González; de Murillo, Raquel Garrido López; Gros, Tania Ojuel; Viguera, Raquel Flecha; González, Isabel López; Herrera, Adriana García; Tello, Loreto Vidaur; Aseguinolaza, Maialen; Eguibar, Itziar; Bulnes, María Luisa Cantón; Contreras, Jose Javier González; Chicote, Nerissa Ãlvarez; Parra, Asunción Marqués; Marti, Sergio García; Aguilar, Alberto Lorenzo; Bosch, Laura Bellver; Sanchez, Victor Gascón; De la Guía Ortega, Sonia; Montell, Martín Parejo; Muncharaz, Alberto Belenguer; Garces, Hector Hernández; Montero, Victor Ramírez; Gómez, Mónica Crespo; Algarra, Verónica Martí; Chinesta, Susana Sancho; Cervera, Joaquin Arguedas; Cebrian, Faustino Ãlvarez; Pérez, Begoéa Balerdi; Fores, Rosa Jannone; de Maglia, Javier Botella; Monleón, Nieves Carbonell; Franco, Jose Ferreres; Lazaro, Ainhoa Serrano; Díaz, Mar Juan; Cortés, María Luisa Blasco; Fayos, Laura; Giménez, Julia; Soriano, Gaspar; Navarro, Ricardo; Mas, Sonia; Bisbal, Elena; Albert, Laura; Romero, Johncard; Cabreara, Juan Fernández; Ortíz, Andrea; Ribas, Antonio Margarit
Source
Critical Care. February 15, 2021, Vol. 25 Issue 1
Subject
Language
English
ISSN
1364-8535
Abstract
Author(s): Alejandro Rodríguez[sup.1,2] , Manuel Ruiz-Botella[sup.3] , Ignacio Martín-Loeches[sup.4] , María Jimenez Herrera[sup.5] , Jordi Solé-Violan[sup.6] , Josep Gómez[sup.3] , María Bodí[sup.1,2] , Sandra Trefler[sup.1] , Elisabeth Papiol[sup.7] , Emili [...]
Background The identification of factors associated with Intensive Care Unit (ICU) mortality and derived clinical phenotypes in COVID-19 patients could help for a more tailored approach to clinical decision-making that improves prognostic outcomes. Methods Prospective, multicenter, observational study of critically ill patients with confirmed COVID-19 disease and acute respiratory failure admitted from 63 ICUs in Spain. The objective was to utilize an unsupervised clustering analysis to derive clinical COVID-19 phenotypes and to analyze patient's factors associated with mortality risk. Patient features including demographics and clinical data at ICU admission were analyzed. Generalized linear models were used to determine ICU morality risk factors. The prognostic models were validated and their performance was measured using accuracy test, sensitivity, specificity and ROC curves. Results The database included a total of 2022 patients (mean age 64 [IQR 5-71] years, 1423 (70.4%) male, median APACHE II score (13 [IQR 10-17]) and SOFA score (5 [IQR 3-7]) points. The ICU mortality rate was 32.6%. Of the 3 derived phenotypes, the A (mild) phenotype (537; 26.7%) included older age (< 65 years), fewer abnormal laboratory values and less development of complications, B (moderate) phenotype (623, 30.8%) had similar characteristics of A phenotype but were more likely to present shock. The C (severe) phenotype was the most common (857; 42.5%) and was characterized by the interplay of older age (> 65 years), high severity of illness and a higher likelihood of development shock. Crude ICU mortality was 20.3%, 25% and 45.4% for A, B and C phenotype respectively. The ICU mortality risk factors and model performance differed between whole population and phenotype classifications. Conclusion The presented machine learning model identified three clinical phenotypes that significantly correlated with host-response patterns and ICU mortality. Different risk factors across the whole population and clinical phenotypes were observed which may limit the application of a "one-size-fits-all" model in practice. Keywords: Severe SARS-CoV-2 infection, Phenotypes, Risk factors, Prognosis, Machine learning
Background The identification of factors associated with Intensive Care Unit (ICU) mortality and derived clinical phenotypes in COVID-19 patients could help for a more tailored approach to clinical decision-making that improves prognostic outcomes. Methods Prospective, multicenter, observational study of critically ill patients with confirmed COVID-19 disease and acute respiratory failure admitted from 63 ICUs in Spain. The objective was to utilize an unsupervised clustering analysis to derive clinical COVID-19 phenotypes and to analyze patient's factors associated with mortality risk. Patient features including demographics and clinical data at ICU admission were analyzed. Generalized linear models were used to determine ICU morality risk factors. The prognostic models were validated and their performance was measured using accuracy test, sensitivity, specificity and ROC curves. Results The database included a total of 2022 patients (mean age 64 [IQR 5-71] years, 1423 (70.4%) male, median APACHE II score (13 [IQR 10-17]) and SOFA score (5 [IQR 3-7]) points. The ICU mortality rate was 32.6%. Of the 3 derived phenotypes, the A (mild) phenotype (537; 26.7%) included older age (< 65 years), fewer abnormal laboratory values and less development of complications, B (moderate) phenotype (623, 30.8%) had similar characteristics of A phenotype but were more likely to present shock. The C (severe) phenotype was the most common (857; 42.5%) and was characterized by the interplay of older age (> 65 years), high severity of illness and a higher likelihood of development shock. Crude ICU mortality was 20.3%, 25% and 45.4% for A, B and C phenotype respectively. The ICU mortality risk factors and model performance differed between whole population and phenotype classifications. Conclusion The presented machine learning model identified three clinical phenotypes that significantly correlated with host-response patterns and ICU mortality. Different risk factors across the whole population and clinical phenotypes were observed which may limit the application of a "one-size-fits-all" model in practice. Keywords: Severe SARS-CoV-2 infection, Phenotypes, Risk factors, Prognosis, Machine learning