Interpretable physiological forecasting in the ICU using constrained data assimilation and electronic health record data.

OBJECTIVE: Prediction of physiological mechanics are important in medical practice because interventions are guided by predicted impacts of interventions. But prediction is difficult in medicine because medicine is complex and difficult to understand from data alone, and the data are sparse relative to the complexity of the generating processes. Computational methods can increase prediction accuracy, but prediction with clinical data is difficult because the data are sparse, noisy and nonstationary. This paper focuses on predicting physiological processes given sparse, non-stationary, electronic health record data in the intensive care unit using data assimilation (DA), a broad collection of methods that pair mechanistic models with inference methods. METHODS: A methodological pipeline embedding a glucose-insulin model into a new DA framework, the constrained ensemble Kalman filter (CEnKF) to forecast blood glucose was developed. The data include tube-fed patients whose nutrition, blood glucose, administered insulins and medications were extracted by hand due to their complexity and to ensure accuracy. The model was estimated using an individual's data as if they arrived in real-time, and the estimated model was run forward producing a forecast. Both constrained and unconstrained ensemble Kalman filters were estimated to compare the impact of constraints. Constraint boundaries, model parameter sets estimated, and data used to estimate the models were varied to investigate their influence on forecasting accuracy. Forecasting accuracy was evaluated according to mean squared error between the model-forecasted glucose and the measurements and by comparing distributions of measured glucose and forecast ensemble means. RESULTS: The novel CEnKF produced substantial gains in robustness and accuracy while minimizing the data requirements compared to the unconstrained ensemble Kalman filters. Administered insulin and tube-nutrition were important for accurate forecasting, but including glucose in IV medication delivery did not increase forecast accuracy. Model flexibility, controlled by constraint boundaries and estimated parameters, did influence forecasting accuracy. CONCLUSION: Accurate and robust physiological forecasting with sparse clinical data is possible with DA. Introducing constrained inference, particularly on unmeasured states and parameters, reduced forecast error and data requirements. The results are not particularly sensitive to model flexibility such as constraint boundaries, but over or under constraining increased forecasting errors.

COVID-19 and Thrombotic or Thromboembolic Disease: Implications for Prevention, Antithrombotic Therapy, and Follow-Up: JACC State-of-the-Art Review.

Coronavirus disease-2019 (COVID-19), a viral respiratory illness caused by the severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2), may predispose patients to thrombotic disease, both in the venous and arterial circulations, because of excessive inflammation, platelet activation, endothelial dysfunction, and stasis. In addition, many patients receiving antithrombotic therapy for thrombotic disease may develop COVID-19, which can have implications for choice, dosing, and laboratory monitoring of antithrombotic therapy. Moreover, during a time with much focus on COVID-19, it is critical to consider how to optimize the available technology to care for patients without COVID-19 who have thrombotic disease. Herein, the authors review the current understanding of the pathogenesis, epidemiology, management, and outcomes of patients with COVID-19 who develop venous or arterial thrombosis, of those with pre-existing thrombotic disease who develop COVID-19, or those who need prevention or care for their thrombotic disease during the COVID-19 pandemic.

Effect of Extracorporeal Membrane Oxygenation Use on Sedative Requirements in Patients with Severe Acute Respiratory Distress Syndrome.

STUDY OBJECTIVES: To compare sedative dose requirements during the 6-hour period when they are greatest in patients with severe acute respiratory distress syndrome (ARDS), as well as the time from severe ARDS onset to reach this maximum sedation exposure, between patients with severe ARDS who were managed either with or without extracorporeal membrane oxygenation (ECMO). Also, to explore factors other than ECMO use that may influence sedation requirements during this period of maximum sedation. DESIGN: Retrospective comparative cohort analysis. DATA SOURCES: Two academic centers, one with an adult ECMO program and one without. PATIENTS: Consecutive adults with severe ARDS who were receiving continuous-infusion sedative therapy for at least 48 hours from the time of severe ARDS diagnosis and who were managed with ECMO (34 patients) or without ECMO (60 patients) between 2009 and 2013. MEASUREMENTS AND MAIN RESULTS: Among patients managed with ECMO, the maximum median (interquartile range [IQR]) 6-hr sedative exposure (in midazolam equivalents) was nearly twice as high (118 [IQR 48-225] mg vs 60 [37-99] mg, p=0.004) and was reached, on average, 3 days later (4 [IQR 1-8] vs 1 [IQR 0.5-6] days, p=0.003) than patients not managed with ECMO. Patients managed with ECMO were younger, had a higher Sequential Organ Failure Assessment score, and, in the 24 hours prior to the period of maximum sedative exposure, had a higher ratio of partial pressure of oxygen in arterial blood to fraction of inspired oxygen and were more likely to receive renal replacement and high-dose fentanyl (2000 µg or more/24 hrs) therapy. An adjusted multivariable linear regression model using the natural logarithmic value of the maximum sedative exposure in a 6-hour period revealed that patient age (p=0.04) and administration of high-dose fentanyl in the 24 hours prior to the 6-hour period of maximum sedative use (p<0.0001) were each independently associated with the maximum 6-hour sedative requirement reached, but the use of ECMO was not (p=0.52). CONCLUSION: Although the application of ECMO during severe ARDS resulted in a period of maximum sedation exposure that was both greater and took longer to reach, factors other than ECMO, particularly high-dose opioid administration, appeared more likely to account for this maximum sedation use. Further research surrounding sedative requirements, clearance, and patient response during ECMO is required.