Abstract. Objective: To develop a prediction equation for the number of patients seeking urgent care. Methods: In the first phase, daily patient volume from February 1998 to January 1999 was matched with calendar and weather variables, and stepwise linear regression analysis was performed. This model was used to match staffing to patient volume. The effects were measured through patient complaint and ''left without being seen'' rates. The second phase was undertaken to develop a model to account for the continual yearly increase in patient volume. The model predicted the patient volume in the validation set within Ϯ11%. When the first-phase model was used to predict patient volume and thus staffing, the percentage of patients who left without being seen decreased by 18.5% and the number of patient complaints dropped by 30%. Conclusions: Use of a prediction equation allowed for improved accuracy in staffing patterns with associated improvement in measures of patient satisfaction.

Background: We experienced a high incidence of pulmonary barotrauma among patients with coronavirus disease-2019 (COVID-19) associated acute respiratory distress syndrome (ARDS) at our institution. In current study, we sought to estimate the incidence, clinical outcomes, and characteristics of barotrauma among COVID-19 patients receiving invasive and non-invasive positive pressure ventilation. Methodology: We conducted this retrospective cohort study of adult patients diagnosed with COVID-19 pneumonia and requiring oxygen support or positive airway pressure for ARDS who presented to our tertiary care center from March through November, 2020. Results: A total of 353 patients met our inclusion criteria, of which 232patients who required heated high-flow nasal cannula, continuous or bilevel positive airway pressure were assigned to non-invasive group. The remaining 121 patients required invasive mechanical ventilation and were assigned to invasive group. Of the 353 patients, 32 patients (65.6% males) with a mean age of 63 ± 11 years developed barotrauma in the form of either subcutaneous emphysema, pneumothorax, or pneumomediastinum. The incidence of barotrauma was 4.74% (11/232) and 17.35% (21/121) in non-invasive group and invasive group, respectively. The median length of hospital stay was 22 (15.7 −33.0) days with an overall mortality of 62.5% (n = 20). Conclusions: Patients with COVID-19 ARDS have a high incidence rate of barotrauma. Pulmonary barotrauma should be considered in patients with COVID-19 pneumonia who exhibit worsening of their respiratory disease as it is likely associated with a high mortality risk. Utilizing lung-protective ventilation strategies may reduce the risk of barotrauma.

The value of the electrocardiogram in assessing infarct size was studied using serial estimates of the MB isomer of creatine kinase (CK MB) in plasma, serial 35 lead praecordial maps in 28 patients with anterior myocardial infarction, and serial 12 lead electrocardiograms in 17 patients with inferior myocardial infarction. In patients with anterior infarcts, sigma ST, sigma R, sigma Q, sigma R/(Q+S), and the number of sites with ST elevation more than 2 mm or with QS waves, were obtained from each map. Correlation between both maximum sigma Q and maximum sigma ST with cumulative CK MB was highly significant. There was also a significant correlation between sigma R and sigma R/(Q+S) with cumulative CK MB. There was no significant correlation between maximum number of sites with ST elevation or with Q or QS waves and cumulative CK MB. Maximum sigma ST and number of sites with ST elevation predicted maximum sigma Q and number of sites with QS or Q waves at a time when infarction was not complete. In patients with inferior infarcts, there was a significant correlation between maximum sigma Q and maximum sigma ST in leads II, III, and a VF, and cumulative CK MB. This study shows that all the waves in the electrocardiogram are useful in assessing infarct size. The fact that maximum sigma ST predicts final sigma Q may be used to assess the efficacy of interventions designed to salvage ischaemic myocardium.

Conventional algorithms for modeling clinical events focus on characterizing the differences between patients with varying outcomes in historical data sets used for the model derivation. For many clinical conditions with low prevalence and where small data sets are available, this approach to developing models is challenging due to the limited number of positive (that is, event) examples available for model training. Here, we investigate how the approach of developing clinical models might be improved across three distinct patient populations (patients with acute coronary syndrome enrolled in the DISPERSE2-TIMI33 and MERLIN-TIMI36 trials, patients undergoing inpatient surgery in the National Surgical Quality Improvement Program registry, and patients undergoing percutaneous coronary intervention in the Blue Cross Blue Shield of Michigan Cardiovascular Consortium registry). For each of these cases, we supplement an incomplete characterization of patient outcomes in the derivation data set (uncensored view of the data) with an additional characterization of the extent to which patients differ from the statistical support of their clinical characteristics (censored view of the data). Our approach exploits the same training data within the derivation cohort in multiple ways to improve the accuracy of prediction. We position this approach within the context of traditional supervised (2-class) and unsupervised (1-class) learning methods and present a 1.5-class approach for clinical decision-making. We describe a 1.5-class support vector machine (SVM) classification algorithm that implements this approach, and report on its performance relative to logistic regression and 2-class SVM classification with cost-sensitive weighting and oversampling. The 1.5-class SVM algorithm improved prediction accuracy relative to other approaches and may have value in predicting clinical events both at the bedside and for risk-adjusted quality of care assessment.

No abstract