ABSTRACT
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.
ABSTRACT
PURPOSE: Since the SARS-CoV-2 pandemic, countries are overwhelmed by critically ill Coronavirus disease 2019 (COVID-19) patients. As ICU capacity becomes limited we characterized critically ill COVID-19 patients in the Netherlands. METHODS: In this case series, COVID-19 patients admitted to the ICU of the Jeroen Bosch Hospital were included from March 9 to April 7, 2020. COVID-19 was confirmed by a positive result by a RT-PCR of a specimen collected by nasopharyngeal swab. Clinical data were extracted from medical records. RESULTS: The mean age of the 50 consecutively included critically ill COVID-19 patients was 65 ± 10 years, the mean BMI was 29 ± 4.7 and 66% were men. Seventy-eight percent of patients had ≥1 comorbidity, 34% had hypertension. Ninety-six percent of patients required mechanical ventilation and 80% were ventilated in prone position. Venous thromboembolism was recognized in 36% of patients. Seventy-four percent of patients survived and were successfully discharged from the ICU, the remaining 26% died (median follow up 86 days). The length of invasive ventilation in survivors was 15 days (IQR 12-31). CONCLUSIONS: The survival rate of COVID-19 critically ill patients in our population is considerably better than previously reported. Thrombotic complications are commonly found and merit clinical attention. TRIAL REGISTRATION NUMBER: NL2020.07.04.01.