The impact of pre-existing chronic heart failure on the intensive care treatment and outcome of old intensive care patients suffering from COVID-19

Background: Patients suffering from COVID-19 with pre-existing chronic heart failure (CHF) are considered to have a significant risk regarding morbidity and mortality. Similarly, older patients on the intensive care unit (ICU) constitute another vulnerable subgroup. This study investigated the association between pre-existing CHF and clinical practice in critically ill older ICU patients with COVID-19. Method(s): Patients with severe COVID-19 and who were >=70 years old were recruited from this prospective multicenter international study. Patients' treatment, follow-up, and pre-existing heart failure data were collected during ICU stay. Univariate and multivariate logistic regression analyses examined the association between pre-existing heart failure and the primary endpoint of 30-day mortality. Result(s): The study included 3,917 patients, with 407 patients (17%) evidencing pre-existing CHF. These patients were older (77+/-5 versus 76+/-5, p<0.001) and more frail (Clinical Frailty Scale 4+/-2 versus 3+/-2, p<0.0001). The other comorbidities were also significantly more common in CHF patients. Before hospital admission, CHF patients suffered fewer days from symptoms (5 days (3-8) versus 7 days (4-10), p<0.001), but there was no difference in the days in the hospital before ICU admission (2 days (1-5) versus 2 (1-5) days, p=0.21). At ICU admission, disease severity assessed by SOFA scores was significantly higher in CHF patients (7+/-3 versus 5+/-3). During ICU-stay, intubation, mechanical ventilation, and tracheostomy occurred significantly more often in patients without CHF (63% versus 69%, p=0.017;and 13% versus 18%, p=0.002, respectively). In contrast, there was no difference regarding non-invasive ventilation (28% versus 27%, p=0.20), and the need for vasoactive drugs (66% versus 64, p=0.30). Regarding the limitation of life-sustaining therapy, therapy was significantly more often withheld (32% versus 25%, p=0.001) but not withdrawn (18% versus 17%, p=0.21) in CHF patients. Length of ICU stay was significantly shorter in CHF patients (166 (72-336) hours versus 260 hours (120-528), p<0.001). CHF patients had significantly higher ICU-(52% versus 46%, p=0.007), 30-day mortality (60% vs. 48%, p<0.001;OR 1.87, 95% CI 1.5- 2.3) and 3-month mortality (69% vs. 56%, p<0.001). In the univariate regression analysis, having pre-existing CHF was significantly associated with 30-day mortality (OR 1.89, 95% CI 1.5-2.3;p<0.001), but after adjusting for confounders (SOFA, age, gender, frailty), heart failure was not independently associated any more (aOR 1.2, 95% CI 0.5-1.5;p=0.137). Conclusion(s): In critically ill old COVID-19 patients, pre-existing chronic heart failure is associated with significantly increased short-and long-term mortality, but heart failure is not independently associated with increased 30-day mortality when adjusted for confounders.

Can we reliably automate clinical prognostic modelling? A retrospective cohort study for ICU triage prediction of in-hospital mortality of COVID-19 patients in the Netherlands.

BACKGROUND: Building Machine Learning (ML) models in healthcare may suffer from time-consuming and potentially biased pre-selection of predictors by hand that can result in limited or trivial selection of suitable models. We aimed to assess the predictive performance of automating the process of building ML models (AutoML) in-hospital mortality prediction modelling of triage COVID-19 patients at ICU admission versus expert-based predictor pre-selection followed by logistic regression. METHODS: We conducted an observational study of all COVID-19 patients admitted to Dutch ICUs between February and July 2020. We included 2,690 COVID-19 patients from 70 ICUs participating in the Dutch National Intensive Care Evaluation (NICE) registry. The main outcome measure was in-hospital mortality. We asessed model performance (at admission and after 24h, respectively) of AutoML compared to the more traditional approach of predictor pre-selection and logistic regression. FINDINGS: Predictive performance of the autoML models with variables available at admission shows fair discrimination (average AUROC = 0·75-0·76 (sdev = 0·03), PPV = 0·70-0·76 (sdev = 0·1) at cut-off = 0·3 (the observed mortality rate), and good calibration. This performance is on par with a logistic regression model with selection of patient variables by three experts (average AUROC = 0·78 (sdev = 0·03) and PPV = 0·79 (sdev = 0·2)). Extending the models with variables that are available at 24h after admission resulted in models with higher predictive performance (average AUROC = 0·77-0·79 (sdev = 0·03) and PPV = 0·79-0·80 (sdev = 0·10-0·17)). CONCLUSIONS: AutoML delivers prediction models with fair discriminatory performance, and good calibration and accuracy, which is as good as regression models with expert-based predictor pre-selection. In the context of the restricted availability of data in an ICU quality registry, extending the models with variables that are available at 24h after admission showed small (but significantly) performance increase.

Comparison of outcome and characteristics between 6343 COVID-19 patients and 2256 other community-acquired viral pneumonia patients admitted to Dutch ICUs.

PURPOSE: Describe the differences in characteristics and outcomes between COVID-19 and other viral pneumonia patients admitted to Dutch ICUs. MATERIALS AND METHODS: Data from the National-Intensive-Care-Evaluation-registry of COVID-19 patients admitted between February 15th and January 1th 2021 and other viral pneumonia patients admitted between January 1st 2017 and January 1st 2020 were used. Patients' characteristics, the unadjusted, and adjusted in-hospital mortality were compared. RESULTS: 6343 COVID-19 and 2256 other viral pneumonia patients from 79 ICUs were included. The COVID-19 patients included more male (71.3 vs 49.8%), had a higher Body-Mass-Index (28.1 vs 25.5), less comorbidities (42.2 vs 72.7%), and a prolonged hospital length of stay (19 vs 9 days). The COVID-19 patients had a significantly higher crude in-hospital mortality rate (Odds ratio (OR) = 1.80), after adjustment for patient characteristics and ICU occupancy rate the OR was respectively 3.62 and 3.58. CONCLUSION: Higher mortality among COVID-19 patients could not be explained by patient characteristics and higher ICU occupancy rates, indicating that COVID-19 is more severe compared to other viral pneumonia. Our findings confirm earlier warnings of a high need of ICU capacity and high mortality rates among relatively healthy COVID-19 patients as this may lead to a higher mental workload for the staff.