Identifying Patient Groups in SARS-CoV-2 Pneumonia
Author Information
Author(s): García-García Fernando, Lee Dae-Jin, Nieves-Ermecheo Mónica, Bronte Olaia, España Pedro Pablo, Quintana José María, Menéndez Rosario, Torres Antoni, Ruiz Iturriaga Luis Alberto, Urrutia Isabel
Primary Institution: Basque Center for Applied Mathematics (BCAM), Bilbao, Basque Country Spain
Hypothesis
Can distinct clinical phenotypes among hospitalized patients with SARS-CoV-2 pneumonia be identified and associated with clinical outcomes?
Conclusion
Three distinct patient phenotypes were identified, each showing strong associations with clinical severity and mortality in SARS-CoV-2 pneumonia.
Supporting Evidence
- Phenotype A was associated with lower severity and mortality.
- Phenotype B showed moderate risk for severity and mortality.
- Phenotype C had the highest risk for severe outcomes.
Takeaway
Doctors found three different types of patients with COVID-19 pneumonia, and each type had different chances of getting worse or dying.
Methodology
Multicentric observational, prospective, longitudinal cohort study using machine learning clustering to identify phenotypes.
Potential Biases
Potential inclusion bias due to hospital admission policies during the pandemic.
Limitations
The study's observational design may introduce bias, and it only includes baseline data without considering disease dynamics or treatment responses.
Participant Demographics
Adult patients (≥ 18 years old) admitted for SARS-CoV-2 pneumonia.
Statistical Information
P-Value
p<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website