Predicting Unplanned Transfers to the Intensive Care Unit: A Machine Learning Approach Leveraging Diverse Clinical Elements.

BACKGROUND: Early warning scores aid in the detection of pediatric clinical deteriorations but include limited data inputs, rarely include data trends over time, and have limited validation. OBJECTIVE: Machine learning methods that make use of large numbers of predictor variables are now commonplace. This work examines how different types of predictor variables derived from the electronic health record affect the performance of predicting unplanned transfers to the intensive care unit (ICU) at three large children's hospitals. METHODS: We trained separate models with data from three different institutions from 2011 through 2013 and evaluated models with 2014 data. Cases consisted of patients who transferred from the floor to the ICU and met one or more of 5 different priori defined criteria for suspected unplanned transfers. Controls were patients who were never transferred to the ICU. Predictor variables for the models were derived from vitals, labs, acuity scores, and nursing assessments. Classification models consisted of L1 and L2 regularized logistic regression and neural network models. We evaluated model performance over prediction horizons ranging from 1 to 16 hours. RESULTS: Across the three institutions, the c-statistic values for our best models were 0.892 (95% CI 0.875-0.904), 0.902 (95% CI 0.880-0.923), and 0.899 (95% CI 0.879-0.919) for the task of identifying unplanned ICU transfer 6 hours before its occurrence and achieved 0.871 (95% CI 0.855-0.888), 0.872 (95% CI 0.850-0.895), and 0.850 (95% CI 0.825-0.875) for a prediction horizon of 16 hours. For our first model at 80% sensitivity, this resulted in a specificity of 80.5% (95% CI 77.4-83.7) and a positive predictive value of 5.2% (95% CI 4.5-6.2). CONCLUSIONS: Feature-rich models with many predictor variables allow for patient deterioration to be predicted accurately, even up to 16 hours in advance.

The cognitive demands of standardized patients: understanding limitations in attention and working memory with the decoding of nonverbal behavior during improvisations.

INTRODUCTION: This study was designed to look at the challenges of standardized patients while in role and to use the findings to enhance training methods. The study investigated the effect of improvisations and multiple-task performance on the ability of standardized patients to observe and evaluate another's communication behaviors and its associated mental workload. METHOD: Twenty standardized patients participated in a 2 types of interview (with and without improvisations)-by-2 types of observation (passive and active) within-groups design. RESULTS: The results indicated that both active observations and improvisations had a negative effect on the standardized patients' ability to observe the learner, missing more than 75% of nonverbal behaviors during active improvisational encounters. Moreover, standardized patients experienced the highest mental demand during active improvisational encounters. CONCLUSIONS: The findings suggest that the need to simultaneously portray a character and assess a learner may negatively affect the ability of standardized patients to provide accurate evaluations of a learner, particularly when they are required to improvise responses, underscoring the need for specific and targeted training.