Sea‐surface temperature and salinity (SST/S) in the Arctic Ocean (AO) are largely governed by sea‐ice and continental runoff rather than evaporation and precipitation as in lower latitude oceans, and global satellite analyses and models which incorporate remotely observed SST/S may be inaccurate in the AO due to lack of direct measurements for calibrating satellite data. For this reason, we are motivated to validate several satellite sea‐surface temperature (SST) data products and SST/S models by comparing gridded data in the AO with oceanographic records from 2006 to 2013. Statistical analysis of product‐minus‐observation differences reveals that the satellite SST products considered have a temperature bias magnitude of less than 0.5 °C compared to ship‐based CTD measurements, and most of these biases are negative in sign. SST/S models also show an overall negative temperature bias, but no common sign or magnitude of salinity bias against CTD data. Ice tethered profiler (ITP) near‐surface data span the seasons of several years, and these measurements reflect a sea‐ice dominated region where the ocean surface cannot be remotely observed. Against this data, many of the considered models and products show large errors with detectable seasonal differences in SST bias. Possible sources of these errors are discussed, and two adjustments of product SST on the basis of sea‐ice concentration are suggested for reducing bias to within less than 0.01 °C of ITP near‐surface temperatures.

Objective To rapidly develop, validate, and implement a novel real-time mortality score for the COVID-19 pandemic that improves upon SOFA for decision support for a Crisis Standards of Care team. Materials and Methods We developed, verified, and deployed a stacked generalization model to predict mortality using data available in the EHR by combining five previously validated scores and additional novel variables reported to be associated with COVID-19-specific mortality. We verified the model with prospectively collected data from 12 hospitals in Colorado between March 2020 and July 2020. We compared the area under the receiver operator curve (AUROC) for the new model to the SOFA score and the Charlson Comorbidity Index. Results The prospective cohort included 27,296 encounters, of which 1,358 (5.0%) were positive for SARS-CoV-2, 4,494 (16.5%) required intensive care unit care, 1,480 (5.4%) required mechanical ventilation, and 717 (2.6%) ended in death. The Charlson Comorbidity Index and SOFA scores predicted mortality with an AUROC of 0.72 and 0.90, respectively. Our novel score predicted mortality with AUROC 0.94. In the subset of patients with COVID-19, the stacked model predicted mortality with AUROC 0.90, whereas SOFA had AUROC of 0.85. Discussion Stacked regression allows a flexible, updatable, live-implementable, ethically defensible predictive analytics tool for decision support that begins with validated models and includes only novel information that improves prediction. Conclusion We developed and validated an accurate in-hospital mortality prediction score in a live EHR for automatic and continuous calculation using a novel model that improved upon SOFA.

BackgroundThe SARS-CoV-2 virus has infected millions of people, overwhelming critical care resources in some regions. Many plans for rationing critical care resources during crises are based on the Sequential Organ Failure Assessment (SOFA) score. The COVID-19 pandemic created an emergent need to develop and validate a novel electronic health record (EHR)-computable tool to predict mortality.Research QuestionsTo rapidly develop, validate, and implement a novel real-time mortality score for the COVID-19 pandemic that improves upon SOFA.Study Design and MethodsWe conducted a prospective cohort study of a regional health system with 12 hospitals in Colorado between March 2020 and July 2020. All patients >14 years old hospitalized during the study period without a do not resuscitate order were included. Patients were stratified by the diagnosis of COVID-19. From this cohort, we developed and validated a model using stacked generalization to predict mortality using data widely available in the EHR by combining five previously validated scores and additional novel variables reported to be associated with COVID-19-specific mortality. We compared the area under the receiver operator curve (AUROC) for the new model to the SOFA score and the Charlson Comorbidity Index.ResultsWe prospectively analyzed 27,296 encounters, of which 1,358 (5.0%) were positive for SARS-CoV-2, 4,494 (16.5%) included intensive care unit (ICU)-level care, 1,480 (5.4%) included invasive mechanical ventilation, and 717 (2.6%) ended in death. The Charlson Comorbidity Index and SOFA scores predicted overall mortality with an AUROC of 0.72 and 0.90, respectively. Our novel score predicted overall mortality with AUROC 0.94. In the subset of patients with COVID-19, we predicted mortality with AUROC 0.90, whereas SOFA had AUROC of 0.85.InterpretationWe developed and validated an accurate, in-hospital mortality prediction score in a live EHR for automatic and continuous calculation using a novel model, that improved upon SOFA.Take Home PointsStudy QuestionCan we improve upon the SOFA score for real-time mortality prediction during the COVID-19 pandemic by leveraging electronic health record (EHR) data?ResultsWe rapidly developed and implemented a novel yet SOFA-anchored mortality model across 12 hospitals and conducted a prospective cohort study of 27,296 adult hospitalizations, 1,358 (5.0%) of which were positive for SARS-CoV-2. The Charlson Comorbidity Index and SOFA scores predicted all-cause mortality with AUROCs of 0.72 and 0.90, respectively. Our novel score predicted mortality with AUROC 0.94.InterpretationA novel EHR-based mortality score can be rapidly implemented to better predict patient outcomes during an evolving pandemic.