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
Background : Critically ill patients with COVID-19 are at high risk of thromboembolic events, despite thromboprophylaxis with lowmolecular weight heparins (LWMH), while increased-intensity thromboprophylaxis in this patient population is associated with bleeding. This raises the question whether pharmacokinetic (PK) effects of LMWHs are predictable in these patients. Aims : To investigate whether a dosing algorithm for dalteparin administration could be designed based on clinical parameters, using PK modeling with anti-Xa levels as readout. Methods : In this explorative, observational study, we prospectively included 15 adult COVID-19 patients admitted to the intensive care unit receiving dalteparin in prophylactic-intensity (5000 IU dalteparin once daily (OD) for those <100 kg, 5000 IU dalteparin bidaily (BD) for those ≥100 kg) and therapeutic-intensity (100 IU/kg BD). A minimum of 4 anti-Xa samples per day were collected on regular timepoints over 1-3 days. PK analysis of dalteparin was performed by nonlinear mixed-effect modeling (NONMEM v7.4). The final model was used to perform Monte Carlo simulations to predict anti-Xa levels with different dalteparin regimens. The study was approved by the local medical ethics committee. Results : The data were well-fitted to a linear one compartment model. Wide interindividual variation in the parameters absorption (78%) and clearance (34%) of dalteparin was observed, not explained by clinical covariates such as creatinine clearance for elimination rate. Simulations show that prophylactic dosing in individuals <100 kg result in anti-Xa levels within generally used prophylactic targets, while increased-prophylactic dosing in those ≥100 kg result in supraprophylactic levels in 40% of patients. With therapeuticintensity dosing in secondary thromboprophylaxis, 22% of patients would be subtherapeutically, and 19% patients supratherapeutically dosed. Conclusions : Anti-Xa levels during dalteparin treatment in the critically ill COVID-19 patient are difficult to predict and often off-target. Until data from randomized clinical trials conclude on the best dosing, this suggests that anti-Xa measurements are needed to guide high-intensity dosing in the individual patient.