000151455 001__ 151455 000151455 005__ 20251017144613.0 000151455 0247_ $$2doi$$a10.1186/s13054-021-03487-8 000151455 0248_ $$2sideral$$a143124 000151455 037__ $$aART-2021-143124 000151455 041__ $$aeng 000151455 100__ $$aRodríguez, Alejandro 000151455 245__ $$aDeploying unsupervised clustering analysis to derive clinical phenotypes and risk factors associated with mortality risk in 2022 critically ill patients with COVID-19 in Spain 000151455 260__ $$c2021 000151455 5060_ $$aAccess copy available to the general public$$fUnrestricted 000151455 5203_ $$aBackground 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. 000151455 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es 000151455 590__ $$a19.344$$b2021 000151455 591__ $$aCRITICAL CARE MEDICINE$$b4 / 35 = 0.114$$c2021$$dQ1$$eT1 000151455 592__ $$a3.218$$b2021 000151455 593__ $$aCritical Care and Intensive Care Medicine$$c2021$$dQ1 000151455 594__ $$a14.2$$b2021 000151455 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000151455 700__ $$aRuiz-Botella, Manuel 000151455 700__ $$aMartín-Loeches, Ignacio 000151455 700__ $$aJimenez Herrera, María 000151455 700__ $$aSolé-Violan, Jordi 000151455 700__ $$aGómez, Josep 000151455 700__ $$aBodí, María 000151455 700__ $$aTrefler, Sandra 000151455 700__ $$aPapiol, Elisabeth 000151455 700__ $$aDíaz, Emili 000151455 700__ $$aSuberviola, Borja 000151455 700__ $$aVallverdu, Montserrat 000151455 700__ $$aMayor-Vázquez, Eric 000151455 700__ $$aAlbaya Moreno, Antonio 000151455 700__ $$aCanabal Berlanga, Alfonso 000151455 700__ $$aSánchez, Miguel 000151455 700__ $$adel Valle Ortíz, María 000151455 700__ $$aBallesteros, Juan Carlos 000151455 700__ $$aMartín Iglesias, Lorena 000151455 700__ $$aMarín-Corral, Judith 000151455 700__ $$aLópez Ramos, Esther 000151455 700__ $$aHidalgo Valverde, Virginia 000151455 700__ $$aVidaur Tello, Loreto Vidaur 000151455 700__ $$aSancho Chinesta, Susana 000151455 700__ $$aGonzáles de Molina, Francisco Javier 000151455 700__ $$aHerrero García, Sandra 000151455 700__ $$aSena Pérez, Carmen Carolina 000151455 700__ $$aPozo Laderas, Juan Carlos 000151455 700__ $$aRodríguez García, Raquel 000151455 700__ $$aEstella, Angel 000151455 700__ $$aFerrer, Ricard 000151455 700__ $$aLoza, Ana 000151455 700__ $$aMatallana Zapata, Diego 000151455 700__ $$aDíaz Torres, Isabel 000151455 700__ $$aIbañez Cuadros, Sonia 000151455 700__ $$aRecuerda Nuñez, María 000151455 700__ $$aCarmona Pérez, Maria Luz 000151455 700__ $$aGómez Ramos, Jorge 000151455 700__ $$aVillares Casas, Alba 000151455 700__ $$aCantón, María Luisa 000151455 700__ $$aGonzález Contreras, José Javier 000151455 700__ $$aPérez Chomón, Helena 000151455 700__ $$aAlvarez Chicote, Nerissa 000151455 700__ $$aSousa González, Alberto 000151455 700__ $$aDe Alba Aparicio, María 000151455 700__ $$aMoreno Cano, Sara 000151455 700__ $$aJorge García, Ruth 000151455 700__ $$aSánchez Montori, Laura 000151455 700__ $$aAbanses Moreno, Paula 000151455 700__ $$aMayordomo García, Carlos 000151455 700__ $$aMallor Bonet, Tomás 000151455 700__ $$aOmedas Bonafonte, Paula 000151455 700__ $$aFranquesa Gonzalez, Enric 000151455 700__ $$aBueno Vidales, Nestor 000151455 700__ $$aOcabo Buil, Paula 000151455 700__ $$0(orcid)0000-0002-8068-5016$$aSerón Arbeloa, Carlos$$uUniversidad de Zaragoza 000151455 7102_ $$11007$$2610$$aUniversidad de Zaragoza$$bDpto. Medicina, Psiqu. y Derm.$$cArea Medicina 000151455 773__ $$g25 (2021), 63 [15 pp.]$$pCrit. care$$tCritical care$$x1364-8535 000151455 8564_ $$s2285946$$uhttps://zaguan.unizar.es/record/151455/files/texto_completo.pdf$$yVersión publicada 000151455 8564_ $$s2407849$$uhttps://zaguan.unizar.es/record/151455/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000151455 909CO $$ooai:zaguan.unizar.es:151455$$particulos$$pdriver 000151455 951__ $$a2025-10-17-14:18:10 000151455 980__ $$aARTICLE