Dominik Aronsky

Automatic Detection of Acute Bacterial Pneumonia from Chest X-ray Reports

OBJECTIVE To evaluate the performance of a natural language processing system in extracting pneumonia-related concepts from chest x-ray reports. METHODS DESIGN Four physicians, three lay persons, a natural language processing system, and two keyword searches (designated AAKS and KS) detected the presence or absence of three pneumonia-related concepts and inferred the presence or absence of acute bacterial pneumonia from 292 chest x-ray reports. Gold standard: Majority vote of three independent physicians. Reliability of the gold standard was measured. OUTCOME MEASURES Recall, precision, specificity, and agreement (using Finns R: statistic) with respect to the gold standard. Differences between the physicians and the other subjects were tested using the McNemar test for each pneumonia concept and for the disease inference of acute bacterial pneumonia. RESULTS Reliability of the reference standard ranged from 0.86 to 0.96. Recall, precision, specificity, and agreement (Finn R:) for the inference on acute bacterial pneumonia were, respectively, 0.94, 0.87, 0.91, and 0.84 for physicians; 0.95, 0.78, 0.85, and 0.75 for natural language processing system; 0.46, 0.89, 0.95, and 0.54 for lay persons; 0.79, 0.63, 0.71, and 0.49 for AAKS; and 0.87, 0.70, 0.77, and 0.62 for KS. The McNemar pairwise comparisons showed differences between one physician and the natural language processing system for the infiltrate concept and between another physician and the natural language processing system for the inference on acute bacterial pneumonia. The comparisons also showed that most physicians were significantly different from the other subjects in all pneumonia concepts and the disease inference. CONCLUSION In extracting pneumonia related concepts from chest x-ray reports, the performance of the natural language processing system was similar to that of physicians and better than that of lay persons and keyword searches. The encoded pneumonia information has the potential to support several pneumonia-related applications used in our institution. The applications include a decision support system called the antibiotic assistant, a computerized clinical protocol for pneumonia, and a quality assurance application in the radiology department.

Forecasting Emergency Department Crowding: A Discrete Event Simulation

STUDY OBJECTIVE To develop a discrete event simulation of emergency department (ED) patient flow for the purpose of forecasting near-future operating conditions and to validate the forecasts with several measures of ED crowding. METHODS We developed a discrete event simulation of patient flow with evidence from the literature. Development was purely theoretical, whereas validation involved patient data from an academic ED. The model inputs and outputs, respectively, are 6-variable descriptions of every present and future patient in the ED. We validated the model by using a sliding-window design, ensuring separation of fitting and validation data in time series. We sampled consecutive 10-minute observations during 2006 (n=52,560). The outcome measures--all forecast 2, 4, 6, and 8 hours into the future from each observation--were the waiting count, waiting time, occupancy level, length of stay, boarding count, boarding time, and ambulance diversion. Forecasting performance was assessed with Pearsons correlation, residual summary statistics, and area under the receiver operating characteristic curve. RESULTS The correlations between crowding forecasts and actual outcomes started high and decreased gradually up to 8 hours into the future (lowest Pearsons r for waiting count=0.56; waiting time=0.49; occupancy level=0.78; length of stay=0.86; boarding count=0.79; boarding time=0.80). The residual means were unbiased for all outcomes except the boarding time. The discriminatory power for ambulance diversion remained consistently high up to 8 hours into the future (lowest area under the receiver operating characteristic curve=0.86). CONCLUSION By modeling patient flow, rather than operational summary variables, our simulation forecasts several measures of near-future ED crowding, with various degrees of good performance.

Accuracy of administrative data for identifying patients with pneumonia.

The goal of this study was to determine the accuracy and the impact of 5 different claims-based pneumonia definitions. Three International Classification of Diseases, Version 9, (ICD-9), and 2 diagnosis-related group (DRG)-based case identification algorithms were compared against an independent, clinical pneumonia reference standard. Among 10748 patients, 272 (2.5%) had pneumonia verified by the reference standard. The sensitivity of claims-based algorithms ranged from 47.8% to 66.2%. The positive predictive values ranged from 72.6% to 80.8%. Patient-related variables were not significantly different from the reference standard among the 3 ICD-9-based algorithms. DRG-based algorithms had significantly lower hospital admission rates (57% and 65% vs 73.2%), lower 30-day mortality (5.0% and 5.8% vs 10.7%), shorter length of stay (3.9 and 4.1 days vs 5.6 days), and lower costs (US

Emergency physicians’ behaviors and workload in the presence of an electronic whiteboard

4543 and US

Prompting clinicians about preventive care measures: a systematic review of randomized controlled trials

5159 vs US

Supporting patient care in the emergency department with a computerized whiteboard system.

8585). Claims-based identification algorithms for defining pneumonia in administrative databases are imprecise. ICD-9-based algorithms did not influence patient variables in our population. Identifying pneumonia patients with DRG codes is significantly less precise.

Decreasing Lab Turnaround Time Improves Emergency Department Throughput and Decreases Emergency Medical Services Diversion: A Simulation Model

BACKGROUND As the demands on the emergency medicine (EM) system continue to increase, improvements in the organization of work and the access to timely clinical and system information will be required for providers to manage their workload in a safe and efficient manner. Information technology (IT) solutions are beginning to find their place in the emergency department (ED) and it is time to begin understanding how these systems are effecting physician behavior, communication and workload. METHODS The study used a time-in-motion, primary task analyses to study faculty and resident physician behavior in the presence of an electronic whiteboard. The NASA-Task Load Index (TLX) was used to measure subjective workload and the underlying dimensions of workload at the end of each physician observation. Work, communication and workload were characterized using descriptive statistics and compared using Mann-Whitney U-tests. RESULTS Physicians in our study performed more tasks and were interrupted less than physicians studied previously in conventional EDs. Interruptions interrupted direct patient care tasks less than other clinical activities. Temporary interruptions appear to be a major source of inefficiency in the ED, and likely a major threat to patient safety. Face-to-face interruptions persist even in the presence of advanced IT systems, such as the electronic whiteboard. Faculty physicians exhibited lower workload scores than resident physicians. Frustration was a significant contributing factor to workload in resident physicians. All physicians ranked temporal demands and mental demands as major contributing factors to workload. CONCLUSION The results indicate that the electronic whiteboard improves the efficiency of work and communication in the ED. IT solutions may have great utility in improving provider situational awareness and distributing workload among ED providers. The results also demonstrate that IT solutions alone will not solve all problems in the ED. IT solutions will probably be most effective in improving efficiency and safety outcomes when paired with human-based interventions, such as crew resource management. Future studies must investigate team interaction, workload and situational awareness, and the association of these factors to patient and provider outcomes.

The Effect of Physician Triage on Emergency Department Length of Stay

Preventive care measures remain underutilized despite recommendations to increase their use. The objective of this review was to examine the characteristics, types, and effects of paper- and computer-based interventions for preventive care measures. The study provides an update to a previous systematic review. We included randomized controlled trials that implemented a physician reminder and measured the effects on the frequency of providing preventive care. Of the 1,535 articles identified, 28 met inclusion criteria and were combined with the 33 studies from the previous review. The studies involved 264 preventive care interventions, 4,638 clinicians and 144,605 patients. Implementation strategies included combined paper-based with computer generated reminders in 34 studies (56%), paper-based reminders in 19 studies (31%), and fully computerized reminders in 8 studies (13%). The average increase for the three strategies in delivering preventive care measures ranged between 12% and 14%. Cardiac care and smoking cessation reminders were most effective. Computer-generated prompts were the most commonly implemented reminders. Clinician reminders are a successful approach for increasing the rates of delivering preventive care; however, their effectiveness remains modest. Despite increased implementation of electronic health records, randomized controlled trials evaluating computerized reminder systems are infrequent.

The Challenge of Predicting Demand for Emergency Department Services

Efficient information management and communication within the emergency department (ED) is essential to providing timely and high-quality patient care. The ED whiteboard (census board) usually serves as an EDs central access point for operational and patient-related information. This article describes the design, functionality, and experiences with a computerized ED whiteboard, which has the ability to display relevant operational and patient-related information in real time. Embedded functionality, additional whiteboard views, and the integration with ED and institutional information system components, such as the computerized patient record or the provider order entry system, provide rapid access to more detailed information. As an information center, the computerized whiteboard supports our ED environment not only for providing patient care, but also for operational, educational, and research activities.

Assessing the Quality of Clinical Data in a Computer-based Record for Calculating the Pneumonia Severity Index

BACKGROUND The effect of decreasing lab turnaround times on emergency department (ED) efficiency can be estimated through system-level simulation models and help identify important outcome measures to study prospectively. Furthermore, such models may suggest the advantage of bedside or point-of-care testing and how they might affect efficiency measures. OBJECTIVES The authors used a sophisticated simulation model in place at an adult urban ED with an annual census of 55,000 patient visits. The effect of decreasing turnaround times on emergency medical services (EMS) diversion, ED patient throughput, and total ED length of stay (LOS) was determined. METHODS Data were generated by using system dynamics analytic modeling and simulation approach on 90 separate days from December 2, 2007, through February 29, 2008. The model was a continuous simulation of ED flow, driven by real-time actual patient data, and had intrinsic error checking to assume reasonable goodness-of-fit. A return of complete laboratory results incrementally at 120, 100, 80, 60, 40, 20, and 10 minutes was compared. Diversion calculation assumed EMS closure when more than 10 patients were in the waiting room and 100% ED bed occupancy had been reached for longer than 30 minutes, as per local practice. LOS was generated from data insertion into the patient flow stream and calculation of time to specific predefined gates. The average accuracy of four separate measurement channels (waiting room volume, ED census, inpatient admit stream, and ED discharge stream), all across 24 hours, was measured by comparing the area under the simulated curve against the area under the measured curve. Each channels accuracy was summed and averaged for an overall accuracy rating. RESULTS As lab turnaround time decreased from 120 to 10 minutes, the total number of diversion days (maximum 57 at 120 minutes, minimum 29 at 10 minutes), average diversion hours per day (10.8 hours vs. 6.0 hours), percentage of days with diversion (63% vs. 32%), and average ED LOS (2.77 hours vs. 2.17 hours) incrementally decreased, while average daily throughput (104 patients vs. 120 patients) increased. All runs were at least 85% accurate. CONCLUSIONS This simulation model suggests compelling improvement in ED efficiency with decreasing lab turnaround time. Outcomes such as time on EMS diversion, ED LOS, and ED throughput represent important but understudied areas that should be evaluated prospectively. EDs should consider processes that will improve turnaround time, such as point-of-care testing, to obtain these goals.