TY - JOUR
T1 - Clustering COVID-19 ARDS patients through the first days of ICU admission. An analysis of the CIBERESUCICOVID Cohort
AU - Ceccato, Adrian
AU - Forne, Carles
AU - Bos, Lieuwe D.
AU - Camprubí-Rimblas, Marta
AU - Areny-Balagueró, Aina
AU - Campaña-Duel, Elena
AU - Quero, Sara
AU - Diaz, Emili
AU - Roca, Oriol
AU - de Gonzalo-Calvo, David
AU - Fernández-Barat, Laia
AU - Motos, Anna
AU - Ferrer, Ricard
AU - Riera, Jordi
AU - Lorente, Jose A.
AU - Peñuelas, Oscar
AU - Menendez, Rosario
AU - Amaya-Villar, Rosario
AU - Añón, José M.
AU - Balan-Mariño, Ana
AU - Barberà, Carme
AU - Barberán, José
AU - Blandino-Ortiz, Aaron
AU - Boado, Maria Victoria
AU - Bustamante-Munguira, Elena
AU - Caballero, Jesús
AU - Carbajales, Cristina
AU - Carbonell, Nieves
AU - Catalán-González, Mercedes
AU - Franco, Nieves
AU - Galbán, Cristóbal
AU - Gumucio-Sanguino, V. ctor D.
AU - de la Torre, Maria del Carmen
AU - Estella, Ángel
AU - Gallego, Elena
AU - García-Garmendia, José Luis
AU - Garnacho-Montero, José
AU - Gómez, José M.
AU - Huerta, Arturo
AU - Jorge-García, Ruth Noemí
AU - Loza-Vázquez, Ana
AU - Marin-Corral, Judith
AU - Martínez de la Gándara, Amalia
AU - Martin-Delgado, María Cruz
AU - Martínez-Varela, Ignacio
AU - Messa, Juan Lopez
AU - Muñiz-Albaiceta, Guillermo
AU - Nieto, María Teresa
AU - Novo, Mariana Andrea
AU - Peñasco, Yhivian
AU - Pozo-Laderas, Juan Carlos
AU - Pérez-García, Felipe
AU - Ricart, Pilar
AU - Roche-Campo, Ferran
AU - Rodríguez, Alejandro
AU - Sagredo, Victor
AU - Sánchez-Miralles, Angel
AU - Sancho-Chinesta, Susana
AU - Socias, Lorenzo
AU - Solé-Violan, Jordi
AU - Suarez-Sipmann, Fernando
AU - Tamayo-Lomas, Luis
AU - Trenado, José
AU - Úbeda, Alejandro
AU - Valdivia, Luis Jorge
AU - Vidal, Pablo
AU - Bermejo, Jesus
AU - Gonzalez, Jesica
AU - Barbe, Ferran
AU - Calfee, Carolyn S.
AU - Artigas, Antonio
AU - Torres, Antoni
N1 - Publisher Copyright: © The Author(s) 2024.
PY - 2024/12/1
Y1 - 2024/12/1
N2 - Background: Acute respiratory distress syndrome (ARDS) can be classified into sub-phenotypes according to different inflammatory/clinical status. Prognostic enrichment was achieved by grouping patients into hypoinflammatory or hyperinflammatory sub-phenotypes, even though the time of analysis may change the classification according to treatment response or disease evolution. We aimed to evaluate when patients can be clustered in more than 1 group, and how they may change the clustering of patients using data of baseline or day 3, and the prognosis of patients according to their evolution by changing or not the cluster. Methods: Multicenter, observational prospective, and retrospective study of patients admitted due to ARDS related to COVID-19 infection in Spain. Patients were grouped according to a clustering mixed-type data algorithm (k-prototypes) using continuous and categorical readily available variables at baseline and day 3. Results: Of 6205 patients, 3743 (60%) were included in the study. According to silhouette analysis, patients were grouped in two clusters. At baseline, 1402 (37%) patients were included in cluster 1 and 2341(63%) in cluster 2. On day 3, 1557(42%) patients were included in cluster 1 and 2086 (57%) in cluster 2. The patients included in cluster 2 were older and more frequently hypertensive and had a higher prevalence of shock, organ dysfunction, inflammatory biomarkers, and worst respiratory indexes at both time points. The 90-day mortality was higher in cluster 2 at both clustering processes (43.8% [n = 1025] versus 27.3% [n = 383] at baseline, and 49% [n = 1023] versus 20.6% [n = 321] on day 3). Four hundred and fifty-eight (33%) patients clustered in the first group were clustered in the second group on day 3. In contrast, 638 (27%) patients clustered in the second group were clustered in the first group on day 3. Conclusions: During the first days, patients can be clustered into two groups and the process of clustering patients may change as they continue to evolve. This means that despite a vast majority of patients remaining in the same cluster, a minority reaching 33% of patients analyzed may be re-categorized into different clusters based on their progress. Such changes can significantly impact their prognosis.
AB - Background: Acute respiratory distress syndrome (ARDS) can be classified into sub-phenotypes according to different inflammatory/clinical status. Prognostic enrichment was achieved by grouping patients into hypoinflammatory or hyperinflammatory sub-phenotypes, even though the time of analysis may change the classification according to treatment response or disease evolution. We aimed to evaluate when patients can be clustered in more than 1 group, and how they may change the clustering of patients using data of baseline or day 3, and the prognosis of patients according to their evolution by changing or not the cluster. Methods: Multicenter, observational prospective, and retrospective study of patients admitted due to ARDS related to COVID-19 infection in Spain. Patients were grouped according to a clustering mixed-type data algorithm (k-prototypes) using continuous and categorical readily available variables at baseline and day 3. Results: Of 6205 patients, 3743 (60%) were included in the study. According to silhouette analysis, patients were grouped in two clusters. At baseline, 1402 (37%) patients were included in cluster 1 and 2341(63%) in cluster 2. On day 3, 1557(42%) patients were included in cluster 1 and 2086 (57%) in cluster 2. The patients included in cluster 2 were older and more frequently hypertensive and had a higher prevalence of shock, organ dysfunction, inflammatory biomarkers, and worst respiratory indexes at both time points. The 90-day mortality was higher in cluster 2 at both clustering processes (43.8% [n = 1025] versus 27.3% [n = 383] at baseline, and 49% [n = 1023] versus 20.6% [n = 321] on day 3). Four hundred and fifty-eight (33%) patients clustered in the first group were clustered in the second group on day 3. In contrast, 638 (27%) patients clustered in the second group were clustered in the first group on day 3. Conclusions: During the first days, patients can be clustered into two groups and the process of clustering patients may change as they continue to evolve. This means that despite a vast majority of patients remaining in the same cluster, a minority reaching 33% of patients analyzed may be re-categorized into different clusters based on their progress. Such changes can significantly impact their prognosis.
KW - ARDS
KW - Clustering
KW - Mortality
KW - Precision medicine
UR - http://www.scopus.com/inward/record.url?scp=85188329150&partnerID=8YFLogxK
U2 - 10.1186/s13054-024-04876-5
DO - 10.1186/s13054-024-04876-5
M3 - Article
C2 - 38515193
SN - 1364-8535
VL - 28
JO - Critical Care
JF - Critical Care
IS - 1
M1 - 91
ER -