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
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 ; Matallana Zapata, Diego ; Díaz Torres, Isabel ; Ibañez Cuadros, Sonia ; Recuerda Nuñez, María ; Carmona Pérez, Maria Luz ; Gómez Ramos, Jorge ; Villares Casas, Alba ; Cantón, María Luisa ; González Contreras, José Javier ; Pérez Chomón, Helena ; Alvarez Chicote, Nerissa ; Sousa González, Alberto ; De Alba Aparicio, María ; Moreno Cano, Sara ; Jorge García, Ruth ; Sánchez Montori, Laura ; Abanses Moreno, Paula ; Mayordomo García, Carlos ; Mallor Bonet, Tomás ; Omedas Bonafonte, Paula ; Franquesa Gonzalez, Enric ; Bueno Vidales, Nestor ; Ocabo Buil, Paula ; Serón Arbeloa, Carlos (Universidad de Zaragoza)
Resumen: 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.
Idioma: Inglés
DOI: 10.1186/s13054-021-03487-8
Año: 2021
Publicado en: Critical care 25 (2021), 63 [15 pp.]
ISSN: 1364-8535
Factor impacto JCR: 19.344 (2021)
Categ. JCR: CRITICAL CARE MEDICINE rank: 4 / 35 = 0.114 (2021) - Q1 - T1
Factor impacto CITESCORE: 14.2 - Medicine (Q1)
Factor impacto SCIMAGO: 3.218 - Critical Care and Intensive Care Medicine (Q1)
Tipo y forma: Article (Published version)
Área (Departamento): Area Medicina (Dpto. Medicina, Psiqu. y Derm.)
You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
Exportado de SIDERAL (2025-10-17-14:18:10)
Visitas y descargas
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.
Idioma: Inglés
DOI: 10.1186/s13054-021-03487-8
Año: 2021
Publicado en: Critical care 25 (2021), 63 [15 pp.]
ISSN: 1364-8535
Factor impacto JCR: 19.344 (2021)
Categ. JCR: CRITICAL CARE MEDICINE rank: 4 / 35 = 0.114 (2021) - Q1 - T1
Factor impacto CITESCORE: 14.2 - Medicine (Q1)
Factor impacto SCIMAGO: 3.218 - Critical Care and Intensive Care Medicine (Q1)
Tipo y forma: Article (Published version)
Área (Departamento): Area Medicina (Dpto. Medicina, Psiqu. y Derm.)
You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. Exportado de SIDERAL (2025-10-17-14:18:10)
Permalink:
Visitas y descargas
Este artículo se encuentra en las siguientes colecciones:
Articles > Artículos por área > Medicina
Record created 2025-03-10, last modified 2025-10-17