Deploying unsupervised clustering analysis to derive clinical phenotypes and risk factors associated with mortality risk in 2,022 critically ill patients with COVID-19 in Spain (preprint)

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 Intensive Care Units(ICU) 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 2,022 patients (mean age 64[IQR5-71] years, 1423(70.4%) male, median APACHE II score (13[IQR10-17]) and SOFA score (5[IQR3-7]) 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 .

Deploying Machine Learning to Validate Clinical Phenotypes and Factors Associated with Mortality Risk in 2,022 Critically Ill Patients with COVID-19 in Spain (preprint)

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. The objective was to analyze patient’s factors associated with mortality risk and utilize a Machine Learning(ML) to derive clinical COVID-19 phenotypes.Methods: Prospective, multicenter, observational study of critically ill patients with confirmed COVID-19 disease and acute respiratory failure admitted from 63 Intensive Care Units(ICU) in Spain. Patient features including demographics and clinical data at ICU admission were analyzed. Generalized linear models were used to determine ICU morality risk factors. An unsupervised clustering analysis was applied to determine presence of phenotypes. The prognostic models were validated and their performance was measured using accuracy test, sensitivity, specificity and ROC curves.Findings: The database included a total of 2,022 patients (mean age 64[IQR5-71] years, 1423(70·4%) male, median APACHE II score (13[IQR10-17]) and SOFA score (5[IQR3-7]) points. The ICU mortality rate was 32·6%. Of the 3 derived phenotypes, 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. The A(mild) phenotype (537;26·7%) included older age (>65 years), fewer abnormal laboratory values and less development of complications and B (moderate) phenotype (623,30·8%) had similar characteristics of A phenotype but were more likely to present shock. Crude ICU mortality was 45·4%, 25·0% and 20·3% for the C, B and A phenotype respectively. The ICU mortality risk factors and model performance differed between whole population and phenotype classifications.Interpretation: The presented ML 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.Funding Statement: This study was supported by the Spanish Intensive Care Society(SEMICYUC) and Ricardo Barri Casanovas Foundation.Declaration of Interests: All authors declare that they have no conflicts of interest.Ethics Approval Statement: The study was approved by the reference institutional review board at Joan XXIII University Hospital (IRB# CEIM/066/2020) and each participating site with a waiver of informed consent. All data values were anonymized prior to the phenotyping which consisted of clustering clinical variables on their association with COVID-19 mortality.

Prevalence and risk factors for mortality related to COVID-19 in a severely affected area of Madrid, Spain (preprint)

BACKGROUND: The coronavius disease 2019 (COVID-9) caused by the severe acute respiratory syndrome coronavirus 2 reached Spain by 31 January 2020, in April 2020, the Comunidad de Madrid suffered one of the world's highest crude mortality rate ratios. This study aimed to detect risk factors for mortality in patients with COVID-19. METHODS: Our cohort were all consecutive adult patients with laboratory-confirmed COVID-19 at a secondary hospital in Madrid, March 3-16, 2020. Clinical and laboratory data came from electronic clinical records and were compared between survivors and non-survivors, with outcomes followed up until April 4. Univariable and multivariable logistic regression methods allowed us to explore risk factors associated with in-hospital death. FINDINGS: The cohort comprised 562 patients with COVID-19. Clinical records were available for evaluation for 392 patients attended at the emergency department of our hospital, of whom 199 were discharged, 85 remained hospitalized and 108 died during hospitalization. Among 311 of the hospitalized patients, 34.7% died. Of the 392 patients with records, the median age was 71.5 years (50.6-80.7); 52.6% were men. 252 (64.3%) patients had a comorbidity, hypertension being the most common: 175 (44.6%), followed by other cardiovascular disease: 102 (26.0%) and diabetes: 97 (24.7%). Multivariable regression showed increasing odds of in-hospital death associated with age over 65 (odds ratio 8.32, 95% CI 3.01-22.96; p<0.001), coronary heart disease (2.76, 1.44-5.30; 0.002), and both lower lymphocyte count (0.34, 0.17-0.68; 0.002) and higher LDH (1.25, 1.05-1.50; 0.012) per 1-unit increase and per 100 units respectively. INTERPRETATION: COVID-19 was associated in our hospital at the peak of the pandemic with a crude mortality ratio of 19.2% and a mortality ratio of 34.7% in admitted patients, considerably above most of the ratios described in the Chinese series. These results leave open the question as to which factors, epidemiological or intrinsically viral, apart from age and comorbidities, can explain this difference in excess mortality. FUNDING: None.