Joseph R. Pare

Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach.

OBJECTIVES Predictive analytics in emergency care has mostly been limited to the use of clinical decision rules (CDRs) in the form of simple heuristics and scoring systems. In the development of CDRs, limitations in analytic methods and concerns with usability have generally constrained models to a preselected small set of variables judged to be clinically relevant and to rules that are easily calculated. Furthermore, CDRs frequently suffer from questions of generalizability, take years to develop, and lack the ability to be updated as new information becomes available. Newer analytic and machine learning techniques capable of harnessing the large number of variables that are already available through electronic health records (EHRs) may better predict patient outcomes and facilitate automation and deployment within clinical decision support systems. In this proof-of-concept study, a local, big data-driven, machine learning approach is compared to existing CDRs and traditional analytic methods using the prediction of sepsis in-hospital mortality as the use case. METHODS This was a retrospective study of adult ED visits admitted to the hospital meeting criteria for sepsis from October 2013 to October 2014. Sepsis was defined as meeting criteria for systemic inflammatory response syndrome with an infectious admitting diagnosis in the ED. ED visits were randomly partitioned into an 80%/20% split for training and validation. A random forest model (machine learning approach) was constructed using over 500 clinical variables from data available within the EHRs of four hospitals to predict in-hospital mortality. The machine learning prediction model was then compared to a classification and regression tree (CART) model, logistic regression model, and previously developed prediction tools on the validation data set using area under the receiver operating characteristic curve (AUC) and chi-square statistics. RESULTS There were 5,278 visits among 4,676 unique patients who met criteria for sepsis. Of the 4,222 patients in the training group, 210 (5.0%) died during hospitalization, and of the 1,056 patients in the validation group, 50 (4.7%) died during hospitalization. The AUCs with 95% confidence intervals (CIs) for the different models were as follows: random forest model, 0.86 (95% CI = 0.82 to 0.90); CART model, 0.69 (95% CI = 0.62 to 0.77); logistic regression model, 0.76 (95% CI = 0.69 to 0.82); CURB-65, 0.73 (95% CI = 0.67 to 0.80); MEDS, 0.71 (95% CI = 0.63 to 0.77); and mREMS, 0.72 (95% CI = 0.65 to 0.79). The random forest model AUC was statistically different from all other models (p ≤ 0.003 for all comparisons). CONCLUSIONS In this proof-of-concept study, a local big data-driven, machine learning approach outperformed existing CDRs as well as traditional analytic techniques for predicting in-hospital mortality of ED patients with sepsis. Future research should prospectively evaluate the effectiveness of this approach and whether it translates into improved clinical outcomes for high-risk sepsis patients. The methods developed serve as an example of a new model for predictive analytics in emergency care that can be automated, applied to other clinical outcomes of interest, and deployed in EHRs to enable locally relevant clinical predictions.

Emergency physician focused cardiac ultrasound improves diagnosis of ascending aortic dissection

STUDY OBJECTIVE Ascending aortic dissection (AAD) is an uncommon, time-sensitive, and deadly diagnosis with a nonspecific presentation. Ascending aortic dissection is associated with aortic dilation, which can be determined by emergency physician focused cardiac ultrasound (EP FOCUS). We seek to determine if patients who receive EP FOCUS have reduced time to diagnosis for AAD. METHODS We performed a retrospective review of patients treated at 1 of 3 affiliated emergency departments, March 1, 2013, to May 1, 2015, diagnosed as having AAD. All autopsies were reviewed for missed cases. Primary outcome measure was time to diagnosis. Secondary outcomes were time to disposition, misdiagnosis rate, and mortality. RESULTS Of 386547 ED visits, targeted review of 123 medical records and 194 autopsy reports identified 32 patients for inclusion. Sixteen patients received EP FOCUS and 16 did not. Median time to diagnosis in the EP FOCUS group was 80 (interquartile range [IQR], 46-157) minutes vs 226 (IQR, 109-1449) minutes in the non-EP FOCUS group (P = .023). Misdiagnosis was 0% (0/16) in the EP FOCUS group vs 43.8% (7/16) in the non-EP FOCUS group (P = .028). Mortality, adjusted for do-not-resuscitate status, for EP FOCUS vs non-EP FOCUS was 15.4% vs 37.5% (P = .24). Median rooming time to disposition was 134 (IQR, 101-195) minutes for EP FOCUS vs 205 (IQR, 114-342) minutes for non-EP FOCUS (P = .27). CONCLUSIONS Patients who receive EP FOCUS are diagnosed faster and misdiagnosed less compared with patients who do not receive EP FOCUS. We recommend assessment of the thoracic aorta be performed routinely during cardiac ultrasound in the emergency department.

Emergency physician performed tricuspid annular plane systolic excursion in the evaluation of suspected pulmonary embolism

Objectives: The primary objectives were to describe the diagnostic characteristics tricuspid annular plane systolic excursion (TAPSE) for pulmonary embolism (PE) and to optimize the measurement cutoff of TAPSE for the diagnosis of PE. Secondary objectives included assessment of interrater reliability and the quantitative visual estimation of TAPSE. Methods: This is a prospective observational cohort study involving a convenience sample of patients at an urban academic emergency department. Patients underwent focused right heart echocardiogram (FOCUS) before computed tomographic angiography (CTA) for suspected PE. Results: A total of 150 patients were enrolled, 32 of whom (21.3%) were diagnosed as having a PE. A receiver operating characteristic curve analysis yielded 2.0 cm as the optimal cutoff for TAPSE in the diagnosis of PE, with a sensitivity of 72% (95% confidence interval [CI], 53‐86), a specificity of 66% (95% CI, 57‐75), and an area under the curve of 0.73 (95% CI, 0.65‐0.83). In patients with tachycardia or hypotension, post hoc analysis demonstrated that FOCUS is 100% (95% CI, 80‐100) sensitive for PE, whereas TAPSE is 94% (95% CI, 71‐99) sensitive for PE. The intraclass correlation coefficient was 0.87 (95% CI, 0.79‐0.93). Emergency physicians with training in echocardiography accurately visually estimated TAPSE, with a &kgr; statistic of 0.94 (95% CI, 0.87‐0.98). Conclusions: Emergency physicians with training in echocardiography can reliably measure TAPSE and are able to accurately visually estimate TAPSE as either normal or abnormal. When using an abnormal cutoff of less than 2.0 cm, TAPSE has moderate diagnostic value in patients with suspected PE. On post hoc analysis, TAPSE and FOCUS appear to be highly sensitive for PE in patients with tachycardia or hypotension.

Basic neuroanatomy and stroke syndromes.

Stroke should not solely be considered a disease of the elderly, and racial disparities are most evident among young adults. Acute stroke can present at any age and it is important to be familiar with the evaluation and treatment of stroke to provide timely care. The National Institute of Health Stroke Scale helps physicians objectively evaluate stroke patients. This article presents an overview of basic information on neuroanatomy, pathophysiology, and stroke syndromes.

Revival of the use of ultrasound in screening for appendicitis in young adult men.

Our primary aim was to evaluate the use of ultrasound (US) as an initial screening test for diagnosing appendicitis in young adult men. Secondary exploratory analyses included the effects of using US for initial screening in these patients, compared with the use of CT, on radiation exposure, length of stay (LOS), and cost of imaging.

Corrected flow time: a noninvasive ultrasound measure to detect preload reduction by nitroglycerin

OBJECTIVE Monitoring of patients intravascular volume status without invasive measures remains challenging and unreliable. Our objective was to determine if corrected flow time (FTc) measurement could detect preload reduction with administration of nitroglycerin (NTG) as a surrogate for volume loss. METHODS Post hoc FTc analysis was performed for a prospective cohort study of pulsed wave spectral Doppler measurements before and after administration of NTG. Patients enrolled were eligible for inclusion if they were admitted to a chest pain center for cardiac evaluation. Descriptive statistics, t tests, bivariate regression, and intraclass correlation coefficient were performed as appropriate. RESULTS Fifty-four patients had Doppler measurements available for review. Mean FTc decreased from 339 milliseconds (95% confidence interval, 332-346) to 325 milliseconds (95% confidence interval, 318-331) with administration of 0.3 mg of sublingual NTG (P=.0001). Mean heart rate increased 5 beats/min with administration of NTG (P<.0001); however, there was no significant change in systolic or diastolic blood pressure. CONCLUSION Corrected flow time was able to detect a significant difference in preload reduction with 0.3 mg of NTG. The FTc may be an early reliable noninvasive measure to detect changes in intravascular volume status.

Clinical Pathologic Conference: A 65-year-old Male With Left-Sided Chest Pain. A Case of an Unexpected Occupational Hazard

The authors present a case of a 65-year-old male who presented four times to the emergency department (ED) with left-sided chest pain. On the first three visits, the patient was admitted with a different diagnosis related to his chest pain. On the final visit, an abnormality on an imaging study performed in the ED led to the ultimate diagnostic test revealing the cause of the patients symptoms. The patients clinical presentation and ultimate clinical course are summarized, and a discussion of the differential diagnoses of his condition is presented.

Ultrasound vs. Computed Tomography for Severity of Hydronephrosis and Its Importance in Renal Colic

Introduction Supporting an “ultrasound-first” approach to evaluating renal colic in the emergency department (ED) remains important for improving patient care and decreasing healthcare costs. Our primary objective was to compare emergency physician (EP) ultrasound to computed tomography (CT) detection of hydronephrosis severity in patients with suspected renal colic. We calculated test characteristics of hydronephrosis on EP-performed ultrasound for detecting ureteral stones or ureteral stone size >5mm. We then analyzed the association of hydronephrosis on EP-performed ultrasound, stone size >5mm, and proximal stone location with 30-day events. Methods This was a prospective observational study of ED patients with suspected renal colic undergoing CT. Subjects had an EP-performed ultrasound evaluating for the severity of hydronephrosis. A chart review and follow-up phone call was performed. Results We enrolled 302 subjects who had an EP-performed ultrasound. CT and EP ultrasound results were comparable in detecting severity of hydronephrosis (x2=51.7, p<0.001). Hydronephrosis on EP-performed ultrasound was predictive of a ureteral stone on CT (PPV 88%; LR+ 2.91), but lack of hydronephrosis did not rule it out (NPV 65%). Lack of hydronephrosis on EP-performed ultrasound makes larger stone size >5mm less likely (NPV 89%; LR− 0.39). Larger stone size > 5mm was associated with 30-day events (OR 2.30, p=0.03). Conclusion Using an ultrasound-first approach to detect hydronephrosis may help physicians identify patients with renal colic. The lack of hydronephrosis on ultrasound makes the presence of a larger ureteral stone less likely. Stone size >5mm may be a useful predictor of 30-day events.

Does the location of a narrative comment section affect feedback on a lecture evaluation form

Although the structure and composition of graduate medical education (GME) is evolving with medical and technological advances, didactic lecture format instruction remains a critical component in many training environments internationally. In the US, the Accreditation Council for Graduate Medical Education (ACGME) publishes program requirements outlining educational guidelines for 133 specialties and subspecialties.1 These requirements mandate Emergency Medicine (EM) residency programs must have an average of at least five hours of dedicated instruction per week with 50% of these hours given by faculty members. Trainees therefore often lead a significant portion of didactic sessions. Developing presentation skills is a critical talent to learn, as junior physicians become educators. Additionally, US accreditation bodies require evaluations to measure participation and educational effectiveness of these didactic presentations. Learner evaluations are one mechanism used to meet this requirement. Formative assessment and feedback have been shown to change trainees’ behavior.2-5 Recent literature also supports the notion that trainees do not benefit from feedback in the form of numerical marks but rather from narrative, specific feedback that explicitly states the areas that require improvement.2,3,6 Despite this evidence, there is little data about the components of an effective evaluation tool. One common example, a numerical Likert scale has been shown to be less helpful than narrative or verbal feedback.7 To our knowledge, there is no validated or recommended tool to measure educational effectiveness while also providing meaningful feedback to resident lecturers. The authors sought to test the hypothesis that by relocating a blank space for written comments from the bottom of a lecture evaluation form to the top, it would convey the importance of narrative feedback to the evaluator, motivate the evaluator to provide feedback more frequently, and increase the quality of feedback provided to our resident lecturers. The purpose of this study was to determine if moving the narrative feedback section on a lecture evaluation form from the bottom to the top of the form increases the presence and the quality of written narrative feedback.

Defining Fluid Responsiveness by the Velocity-Time Integral Alone?

To the Editor: In the recently published article “Rapid Ultrasound in Shock (RUSH) Velocity-Time Integral: A Proposal to Expand the RUSH Protocol,” Blanco et al1 recommend the addition of velocity-time integral (VTI) measurements to the RUSH protocol to assess fluid responsiveness. We agree that an accurate assessment of cardiac function and fluid responsiveness may be important in managing hemodynamically unstable patients; however, we are concerned that adding VTI alone to a RUSH protocol may not be prudent at this point. Blanco et al cited one article supporting the capability of emergency physicians (EPs) to perform VTI measurements, in which it was reported that EP providers could perform “optimal” VTI measurements in 78.4% of patients.2 In that case, an optimal measurement was determined by expert cardiology review; however, that process does not support the reproducibly of the measurement, particularly by different EP sonographers. On review of the article by Dinh et al,2 the percent difference reported within 1 SD between experienced cardiac sonographerand EPmeasured VTIs was 8% ± 7% (κ = 0.4). The large standard deviation could have been due to the low number of study participants; however, the low κ and variability do not suggest that the VTI alone in serial measurements should be used to detect a recommended 15% to 20% change. Additionally the percent differences between EPand cardiology sonographer-obtained cardiac indices and stroke volume indices were 12.4% ± 10.1% and 11.1% ± 8.8%, which also indicated a substantial overlap in the variability of the measurement within the desired range to detect fluid responsiveness at a 15% change. Our own experience is that the VTI may be difficult to reliably measure by using transthoracic echocardiography in the emergency department. In addition to concerns about the reliability and reproducibility of VTI measurements, we think that the VTI without incorporation of the heart rate may be misleading. A previous Journal of Ultrasound in Medicine publication on fluid responsiveness by Evans et al3 was based on assessment of cardiac output rather than stroke volume, which is dependent on the heart rate. Although the authors did note a range of normal VTIs based on heart rates between 55 and 95 beats per minute, even a small deviation in the heart rate when calculating the percent change in cardiac output can drastically alter measurements of fluid responsiveness. It is possible that although the stroke volume and VTI may increase, if the heart rate decreases, for whatever clinical