Benchmarking Inpatient Mortality Using Electronic Medical Record Data: A Retrospective, Multicenter Analytical Observational Study.

OBJECTIVES: To develop a model to benchmark mortality in hospitalized patients using accessible electronic medical record data. DESIGN: Univariate analysis and multivariable logistic regression were used to identify variables collected during the first 24 hours following admission to test for risk factors associated with the end point of hospital mortality. Models were built using specific diagnosis (International Classification of Diseases, 9th Edition or International Classification of Diseases, 10th Edition) captured at discharge, rather than admission diagnosis, which may be discordant. Variables were selected based, in part, on prior the Acute Physiology and Chronic Health Evaluation methodology and included primary diagnosis information plus three aggregated indices (physiology, comorbidity, and support). A Physiology Index was created using parsimonious nonlinear modeling of heart rate, mean arterial pressure, temperature, respiratory rate, hematocrit, platelet counts, and serum sodium. A Comorbidity Index incorporates new or ongoing diagnoses captured by the electronic medical record during the preceding year. A Support Index considered 10 interventions such as mechanical ventilation, selected IV drugs, and hemodialysis. Accuracy was determined using area under the receiver operating curve for discrimination, calibration curves, and modified Brier score for calibration. SETTING AND PATIENTS: We used deidentified electronic medical record data from 74,434 adult inpatients (ICU and ward) at 15 hospitals from 2010 to 2013 to develop the mortality model and validated using data for additional 49,752 patients from the same 15 hospitals. A second revalidation was accomplished using data on 83,684 patients receiving care at six hospitals between 2014 and 2016. The model was also validated on a subset of patients with an ICU stay on day 1. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: This model uses physiology, comorbidity, and support indices, primary diagnosis, age, lowest Glasgow Coma Score, and elapsed time since hospital admission to predict hospital mortality. In the initial validation cohort, observed mortality was 4.04% versus predicted mortality 4.12% (Student t test, p = 0.37). In the revalidation using a different set of hospitals, predicted and observed mortality were 2.66% and 2.99%, respectively. Area under the receiver operating curve were 0.902 (0.895-0.909) and 0.884 (0.877-0.891), respectively, and calibration curves show a close relationship of observed and predicted mortalities. In the evaluation of the subset of ICU patients on day1, the area under the receiver operating curve was 0.87, with an observed mortality of 8.78% versus predicted mortality of 8.93% (Student t test, p = 0.52) and a standardized mortality ratio of 0.98 (0.932-1.034). CONCLUSIONS: Variables considered by traditional ICU prognostic models accurately benchmark patient mortality for patients receiving care in multiple hospital locations, not only the ICU. Unlike Acute Physiology and Chronic Health Evaluation, this model relies on electronic medical record data alone and does not require personnel to collect the independent predictor variables. Assessing the model's utility for benchmarking hospital performance will require prospective testing in a larger representative sample of hospitals.

Coronavirus Disease 2019 ICU Patients Have Higher-Than-Expected Acute Physiology and Chronic Health Evaluation-Adjusted Mortality and Length of Stay Than Viral Pneumonia ICU Patients.

OBJECTIVES: To compare Acute Physiology and Chronic Health Evaluation-IV-adjusted mortality and length of stay outcomes of adult ICU patients who tested positive for coronavirus disease 2019 with patients admitted to ICU with other viral pneumonias including a subgroup with viral pneumonia and concurrent acute respiratory distress syndrome (viral pneumonia-acute respiratory distress syndrome). DESIGN: Retrospective review of Acute Physiology and Chronic Health Evaluation data collected from routine clinical care. SETTING: Forty-three hospitals contributing coronavirus disease 2019 patient data between March 14, and June 17, 2020, and 132 hospitals in the United States contributing data on viral pneumonia patients to the Acute Physiology and Chronic Health Evaluation database between January 1, 2014, and December 31, 2019. PATIENTS AND MEASUREMENTS: One thousand four hundred ninety-one patients with diagnosis of coronavirus disease 2019 infection and 4,200 patients with a primary (n = 2,544) or secondary (n = 1,656) admitting diagnosis of noncoronavirus disease viral pneumonia receiving ICU care. A subset of 202 viral pneumonia patients with concurrent acute respiratory distress syndrome was examined separately. INTERVENTIONS: None. MAIN RESULTS: Mean age was 63.4 for coronavirus disease (p = 0.064) versus 64.1 for viral pneumonia. Acute Physiology and Chronic Health Evaluation-IV scores were similar at 56.7 and 55.0, respectively (p = 0.060), but gender and ethnic distributions differed, as did Pao2 to Fio2 ratio and WBC count at admission. The hospital standardized mortality ratio (95% CI) was 1.52 (1.35-1.68) for coronavirus disease patients and 0.82 (0.75-0.90) for viral pneumonia patients. In the coronavirus disease group, ICU and hospital length of stay were 3.1 and 3.0 days longer than in viral pneumonia patients. Standardized ICU and hospital length of stay ratios were 1.13 and 1.46 in the coronavirus disease group versus 0.95 and 0.94 in viral pneumonia patients. Forty-seven percent of coronavirus disease patients received invasive or noninvasive ventilatory support on their first ICU day versus 65% with viral pneumonia. Ventilator days in survivors were longer in coronavirus disease (10.4 d) than in viral pneumonia (4.3 d) patients, except in the viral pneumonia-acute respiratory distress syndrome subgroup (10.2 d). CONCLUSIONS: Severity-adjusted mortality and length of stay are higher for coronavirus disease 2019 patients than for viral pneumonia patients admitted to ICU. Coronavirus disease patients also have longer time on ventilator and ICU length of stay, comparable with the subset of viral pneumonia patients with concurrent acute respiratory distress syndrome. Mortality and length of stay increase with age and higher scores in both populations, but observed to predicted mortality and length of stay are higher than expected with coronavirus disease patients across all severity of illness levels. These findings have implications for benchmarking ICU outcomes during the coronavirus disease 2019 pandemic.