Dynamic prediction of mortality in COVID-19 patients in the intensive care unit: A retrospective multi-center cohort study.

Background: The COVID-19 pandemic continues to overwhelm intensive care units (ICUs) worldwide, and improved prediction of mortality among COVID-19 patients could assist decision making in the ICU setting. In this work, we report on the development and validation of a dynamic mortality model specifically for critically ill COVID-19 patients and discuss its potential utility in the ICU. Methods: We collected electronic medical record (EMR) data from 3222 ICU admissions with a COVID-19 infection from 25 different ICUs in the Netherlands. We extracted daily observations of each patient and fitted both a linear (logistic regression) and non-linear (random forest) model to predict mortality within 24 h from the moment of prediction. Isotonic regression was used to re-calibrate the predictions of the fitted models. We evaluated the models in a leave-one-ICU-out (LOIO) cross-validation procedure. Results: The logistic regression and random forest model yielded an area under the receiver operating characteristic curve of 0.87 [0.85; 0.88] and 0.86 [0.84; 0.88], respectively. The recalibrated model predictions showed a calibration intercept of -0.04 [-0.12; 0.04] and slope of 0.90 [0.85; 0.95] for logistic regression model and a calibration intercept of -0.19 [-0.27; -0.10] and slope of 0.89 [0.84; 0.94] for the random forest model. Discussion: We presented a model for dynamic mortality prediction, specifically for critically ill COVID-19 patients, which predicts near-term mortality rather than in-ICU mortality. The potential clinical utility of dynamic mortality models such as benchmarking, improving resource allocation and informing family members, as well as the development of models with more causal structure, should be topics for future research.

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.

Short-term outpatient follow-up of COVID-19 patients: A multidisciplinary approach.

BACKGROUND: Short-term follow-up of COVID-19 patients reveals pulmonary dysfunction, myocardial damage and severe psychological distress. Little is known of the burden of these sequelae, and there are no clear recommendations for follow-up of COVID-19 patients.In this multi-disciplinary evaluation, cardiopulmonary function and psychological impairment after hospitalization for COVID-19 are mapped. METHODS: We evaluated patients at our outpatient clinic 6 weeks after discharge. Cardiopulmonary function was measured by echocardiography, 24-hours ECG monitoring and pulmonary function testing. Psychological adjustment was measured using questionnaires and semi-structured clinical interviews. A comparison was made between patients admitted to the general ward and Intensive care unit (ICU), and between patients with a high versus low functional status. FINDINGS: Eighty-one patients were included of whom 34 (41%) had been admitted to the ICU. New York Heart Association class II-III was present in 62% of the patients. Left ventricular function was normal in 78% of patients. ICU patients had a lower diffusion capacity (mean difference 12,5% P = 0.01), lower forced expiratory volume in one second and forced vital capacity (mean difference 14.9%; P<0.001; 15.4%; P<0.001; respectively). Risk of depression, anxiety and PTSD were 17%, 5% and 10% respectively and similar for both ICU and non-ICU patients. INTERPRETATION: Overall, most patients suffered from functional limitations. Dyspnea on exertion was most frequently reported, possibly related to decreased DLCOc. This could be caused by pulmonary fibrosis, which should be investigated in long-term follow-up. In addition, mechanical ventilation, deconditioning, or pulmonary embolism may play an important role.

Detailed immune monitoring of a pregnant woman with critical Covid-19.

A primigravid woman with Covid-19 related respiratory insufficiency was admitted into a tertiary Intensive Care Unit at 23 3/7 weeks' gestation. Highly sensitive flow cytometry of peripheral leukocytes indicated significantly suppressed naïve T- and B-cell compartments. The suppressed immune cell responses led us keep the initially started administration of corticosteroids for fetal and maternal indication at a low dose. After three weeks her B-cell response peaked, SARS-CoV-2 was cleared and clinical improvement ensued a week later. At 28 weeks' gestation, a son of 1570 g was born by cesarean section. She was extubated two days postpartum and discharged from hospital 5.5 weeks postpartum.

Confirmation of the high cumulative incidence of thrombotic complications in critically ill ICU patients with COVID-19: An updated analysis.

INTRODUCTION: We recently reported a high cumulative incidence of thrombotic complications in critically ill patients with COVID-19 admitted to the intensive care units (ICUs) of three Dutch hospitals. In answering questions raised regarding our study, we updated our database and repeated all analyses. METHODS: We re-evaluated the incidence of the composite outcome of symptomatic acute pulmonary embolism (PE), deep-vein thrombosis, ischemic stroke, myocardial infarction and/or systemic arterial embolism in all COVID-19 patients admitted to the ICUs of 2 Dutch university hospitals and 1 Dutch teaching hospital from ICU admission to death, ICU discharge or April 22nd 2020, whichever came first. RESULTS: We studied the same 184 ICU patients as reported on previously, of whom a total of 41 died (22%) and 78 were discharged alive (43%). The median follow-up duration increased from 7 to 14 days. All patients received pharmacological thromboprophylaxis. The cumulative incidence of the composite outcome, adjusted for competing risk of death, was 49% (95% confidence interval [CI] 41-57%). The majority of thrombotic events were PE (65/75; 87%). In the competing risk model, chronic anticoagulation therapy at admission was associated with a lower risk of the composite outcome (Hazard Ratio [HR] 0.29, 95%CI 0.091-0.92). Patients diagnosed with thrombotic complications were at higher risk of all-cause death (HR 5.4; 95%CI 2.4-12). Use of therapeutic anticoagulation was not associated with all-cause death (HR 0.79, 95%CI 0.35-1.8). CONCLUSION: In this updated analysis, we confirm the very high cumulative incidence of thrombotic complications in critically ill patients with COVID-19 pneumonia.

Incidence of thrombotic complications in critically ill ICU patients with COVID-19.

INTRODUCTION: COVID-19 may predispose to both venous and arterial thromboembolism due to excessive inflammation, hypoxia, immobilisation and diffuse intravascular coagulation. Reports on the incidence of thrombotic complications are however not available. METHODS: We evaluated the incidence of the composite outcome of symptomatic acute pulmonary embolism (PE), deep-vein thrombosis, ischemic stroke, myocardial infarction or systemic arterial embolism in all COVID-19 patients admitted to the ICU of 2 Dutch university hospitals and 1 Dutch teaching hospital. RESULTS: We studied 184 ICU patients with proven COVID-19 pneumonia of whom 23 died (13%), 22 were discharged alive (12%) and 139 (76%) were still on the ICU on April 5th 2020. All patients received at least standard doses thromboprophylaxis. The cumulative incidence of the composite outcome was 31% (95%CI 20-41), of which CTPA and/or ultrasonography confirmed VTE in 27% (95%CI 17-37%) and arterial thrombotic events in 3.7% (95%CI 0-8.2%). PE was the most frequent thrombotic complication (n = 25, 81%). Age (adjusted hazard ratio (aHR) 1.05/per year, 95%CI 1.004-1.01) and coagulopathy, defined as spontaneous prolongation of the prothrombin time > 3 s or activated partial thromboplastin time > 5 s (aHR 4.1, 95%CI 1.9-9.1), were independent predictors of thrombotic complications. CONCLUSION: The 31% incidence of thrombotic complications in ICU patients with COVID-19 infections is remarkably high. Our findings reinforce the recommendation to strictly apply pharmacological thrombosis prophylaxis in all COVID-19 patients admitted to the ICU, and are strongly suggestive of increasing the prophylaxis towards high-prophylactic doses, even in the absence of randomized evidence.