Faculty Bibliography

Introduction/UNASSIGNED:Emergency department (ED) patient care often hinges on the result of a diagnostic test. Frequently there is a lag time between a test result becoming available for review and physician decision-making or disposition based on that result. We implemented a system that electronically alerts ED providers when test results are available for review via a smartphone- and smartwatch-push notification. We hypothesized this would reduce the time from result to clinical decision-making. Methods/UNASSIGNED:We retrospectively assessed the impact of the implementation of a push notification system at three EDs on time-to-disposition or time-to-follow-up order in six clinical scenarios of interest: chest radiograph (CXR) to disposition, basic metabolic panel (BMP) to disposition, urinalysis (UA) to disposition, respiratory pathogen panel (RPP) to disposition, hemoglobin (Hb) to blood transfusion order, and abnormal D-dimer to computed tomography pulmonary angiography (CTPA) order. All ED patients during a one-year period of push-notification availability were included in the study. The primary outcome was median time in each scenario from result availability to either disposition order or defined follow-up order. The secondary outcome was the overall usage rate of the opt-in push notification system by providers. Results/UNASSIGNED:During the study period there were 6115 push notifications from 4183 ED encounters (2.7% of all encounters). Of the six clinical scenarios examined in this study, five were associated with a decrease in median time from test result availability to patient disposition or follow-up order when push notifications were employed: CXR to disposition, 80 minutes (interquartile range [IQR] 32-162 minutes) vs 56 minutes (IQR 18-141 minutes), difference 24 minutes (p<0.01); BMP to disposition, 128 minutes (IQR 62-225 minutes) vs 116 minutes (IQR 33-226 minutes), difference 12 minutes (p<0.01); UA to disposition, 105 minutes (IQR 43-200 minutes) vs 55 minutes (IQR 16-144 minutes), difference 50 minutes (p<0.01); RPP to disposition, 80 minutes (IQR 28-181 minutes) vs 37 minutes (IQR 10-116 minutes), difference 43 minutes (p<0.01); and D-dimer to CTPA, 14 minutes (IQR 6-30 minutes) vs 6 minutes (IQR 2.5-17.5 minutes), difference 8 minutes (p<0.01). The sixth scenario, Hb to blood transfusion (difference 19 minutes, p=0.73), did not meet statistical significance. Conclusion/UNASSIGNED:Implementation of a push notification system for test result availability in the ED was associated with a decrease in lag time between test result and physician decision-making in the examined clinical scenarios. Push notifications were used in only a minority of ED patient encounters.

Background: Emergency department (ED) care decisions often hinge on the result of a diagnostic test. Frequently there is a lag time between a test result becoming available for review, and physician decision-making based on that result. Push notifications to physician smartphones have demonstrated improvement in this lag time in chest pain patients, but have not been studied in other ED patients. We implemented a system by which ED providers can subscribe to electronic alerts when test results are available for review via a smartphone or smartwatch push notification, and hypothesized that this would reduce the time to make clinical decisions. Method(s): This was a retrospective, multicenter, observational study in three emergency departments of an urban health system. We assessed push notification impact on time to disposition or time to follow-up order in six clinical scenarios of interest: chest x-ray (CXR) to disposition, basic metabolic panel (BMP) to disposition, urinalysis (UA) to disposition, respiratory pathogen panel (RPP) to disposition, hemoglobin (Hb) to blood transfusion order, and D-dimer to computed tomography pulmonary angiography (CTPA) order. All adult ED patients during a one-year period of push notification availability were included in the study. The primary outcome was median time from result availability to disposition order or defined follow-up order. Median times with interquartile ranges were determined in each scenario and the Mann Whitney (Wilcoxon) test for unpaired data was used to determine statistical significance. Result(s): During the study period there were 6,115 push notifications from 4,183 eligible ED encounters (2.7% of all ED encounters). All six scenarios studied were associated with a decrease in median time from test result availability to patient disposition, or from test result availability to follow-up order, when push notifications were employed: CXR to disposition (24 minutes, p<0.01), BMP to disposition (12 minutes, p<0.01), UA to disposition (50 minutes, p<0.01), RPP to disposition (43 minutes, p<0.01), D-dimer to CTPA (8 minutes, p<0.01), Hb to blood transfusion (19 minutes, p=0.73). Conclusion(s): Implementation of a push notification system for test result availability in the ED was associated with a decrease in lag time between test result availability and physician decision-making

BACKGROUND:The assessment of clinical guideline adherence for the evaluation of pulmonary embolism (PE) via computed tomography pulmonary angiography (CTPA) currently requires either labor-intensive, retrospective chart review or prospective collection of PE risk scores at the time of CTPA order. The recording of clinical data in a structured manner in the electronic health record (EHR) may make it possible to automate the calculation of a patient's PE risk classification and determine whether the CTPA order was guideline concordant. OBJECTIVES/OBJECTIVE:The objective of this study was to measure the performance of automated, structured-data-only versions of the Wells and revised Geneva risk scores in emergency department encounters during which a CTPA was ordered. The hypothesis was that such an automated method would classify a patient's PE risk with high accuracy compared to manual chart review. METHODS:We developed automated, structured-data-only versions of the Wells and revised Geneva risk scores to classify 212 emergency department (ED) encounters during which a CTPA was performed as "PE Likely" or "PE Unlikely." We then combined these classifications with D-dimer ordering data to assess each encounter as guideline concordant or discordant. The accuracy of these automated classifications and assessments of guideline concordance were determined by comparing them to classifications and concordance based on the complete Wells and revised Geneva scores derived via abstractor manual chart review. RESULTS:The automatically derived Wells and revised Geneva risk classifications were 91.5% and 92% accurate compared to the manually determined classifications, respectively. There was no statistically significant difference between guideline adherence calculated by the automated scores as compared to manual chart review (Wells: 70.8 vs. 75%, p = 0.33 | Revised Geneva: 65.6 vs. 66%, p = 0.92). CONCLUSION/CONCLUSIONS:The Wells and revised Geneva score risk classifications can be approximated with high accuracy using automated extraction of structured EHR data elements in patients who received a CTPA. Combining these automated scores with D-dimer ordering data allows for the automated assessment of clinical guideline adherence for CTPA ordering in the emergency department, without the burden of manual chart review.

Given the inequalities in the distribution of disease burden, geographically detailed methods of disease surveillance are needed to identify local hot spots of chronic disease. However, few data sources include the patient-level addresses needed to perform these studies. Given that individual hospitals would have access to this geographically granular data, this study assessed the reliability of estimating chronic disease prevalence using emergency department surveillance at specific hospitals. Neighborhood-level diabetes, hypertension, and asthma prevalence were estimated using emergency claims data from each individual hospital in New York City from 2009-2012. Estimates were compared to prevalence obtained from a traditional health survey. A multivariable analysis also was performed to identify which individual hospitals were more accurate at estimating citywide disease prevalence. Among 52 hospitals, variation was found in the accuracy of disease prevalence estimates using emergency department surveillance. Estimates at some hospitals, such as NYU Langone Medical Center, had strong correlations for all diseases studied (diabetes: 0.81, hypertension: 0.84, and asthma: 0.84). Hospitals with patient populations geographically distributed throughout New York City had better accuracy in estimating citywide disease prevalence. For diabetes and hypertension, hospitals with racial/ethnic patient distributions similar to Census estimates and higher fidelity of diagnosis coding also had more accurate prevalence estimates. This study demonstrated how citywide chronic disease surveillance can be performed using emergency data from specific sentinel hospitals. The findings may provide an alternative means of mapping chronic disease burden by using existing data, which may be critical in regions without resources for geographically detailed health surveillance.

BACKGROUND: Testing for venous thromboembolism (VTE) is associated with cost and risk to patients (e.g. radiation). To assess the appropriateness of imaging utilization at the provider level, it is important to know that provider's diagnostic yield (percentage of tests positive for the diagnostic entity of interest). However, determining diagnostic yield typically requires either time-consuming, manual review of radiology reports or the use of complex and/or proprietary natural language processing software. OBJECTIVES: The objectives of this study were twofold: 1) to develop and implement a simple, user-configurable, and open-source natural language processing tool to classify radiology reports with high accuracy and 2) to use the results of the tool to design a provider-specific VTE imaging dashboard, consisting of both utilization rate and diagnostic yield. METHODS: Two physicians reviewed a training set of 400 lower extremity ultrasound (UTZ) and computed tomography pulmonary angiogram (CTPA) reports to understand the language used in VTE-positive and VTE-negative reports. The insights from this review informed the arguments to the five modifiable parameters of the NLP tool. A validation set of 2,000 studies was then independently classified by the reviewers and by the tool; the classifications were compared and the performance of the tool was calculated. RESULTS: The tool was highly accurate in classifying the presence and absence of VTE for both the UTZ (sensitivity 95.7%; 95% CI 91.5-99.8, specificity 100%; 95% CI 100-100) and CTPA reports (sensitivity 97.1%; 95% CI 94.3-99.9, specificity 98.6%; 95% CI 97.8-99.4). The diagnostic yield was then calculated at the individual provider level and the imaging dashboard was created. CONCLUSIONS: We have created a novel NLP tool designed for users without a background in computer programming, which has been used to classify venous thromboembolism reports with a high degree of accuracy. The tool is open-source and available for download at http://iturrate.com/simpleNLP. Results obtained using this tool can be applied to enhance quality by presenting information about utilization and yield to providers via an imaging dashboard.

Background: Multiple models have been developed to predict hospital admission for patients presenting to the ED. However, these tools suffer from multiple limitations including reliance on manual data entry (e.g. ED arrival mechanism), multiple types of data, and data that are not completely generalizable across institutions (e.g. triage score). An ideal solution would produce a disposition score that requires no data entry, employs variables already captured by all EDs, and provides a score far enough in advance to expedite admission processes. Objectives: Evaluate the discriminatory power of machine learning algorithms for predicting hospital admission at two hours of ED arrival through the sole use of the medication administration record (MAR). Methods: Our dataset included 27,757 encounters (26% admitted) from January 2013 to September 2014 and 2,109 medications encoded to RxNorm CUI numbers using MedEx. We included all medications in the MAR, including those given during prior ED visits. We employed classic and state[[Unsupported Character - Codename]]of [[Unsupported Character - Codename]]the[[Unsupported Character - Codename]]art classifiers including logistic regression, naive bayes, regularized logistic regression, classification and regression trees (CART), and linear support vector machine (SVM) with penalty parameter C. In all cases, we split the dataset into a training, validation, and test set. We used the validation set to optimize any parameters of the learning algorithm and used the test set to calculate performances. We employed 5[[Unsupported Character - Codename]]fold cross validation and reported AUC performances averaged across 5 folds. Results: The models performed with AUCs of 0.85 for linear SVM with penalty parameter C (95%CI 0.84-0.86), 0.83 for CART (95%CI 0.82-0.84), 0.79 for regularized logistic regression (95%CI 0.78-0.80), 0.70 for Naive Bayes (95%CI 0.69-0.72), and 0.68 for logistic regression (95%CI 0.67-0.69). Conclusion: MAR data is sufficient to reliably predict hospital admission two hours into the ED stay. Our models perform similarly to those from prior studies, but with the advantages of only requiring a single type of data and being highly generalizable to other institutions; MAR data is objective, does not require manual data entry, and is universally available across EDs