Unsupervised SoftOtsuNet Augmentation for Clinical Dermatology Image Classifiers

Data Augmentation is a crucial tool in the Machine Learning (ML) toolbox because it can extract novel, useful training images from an existing dataset, thereby improving accuracy and reducing overfitting in a Deep Neural Network (DNNs). However, clinical dermatology images often contain irrelevant background information,such as furniture and objects in the frame. DNNs make use of that information when optimizing the loss function. Data augmentation methods that preserve this information risk creating biases in the DNN's understanding (for example, that objects in a particular doctor's office are a clue that the patient has cutaneous T-cell lymphoma). Creating a supervised foreground/background segmentation algorithm for clinical dermatology images that removes this irrelevant information would be prohibitively expensive due to labeling costs. To that end, we propose a novel unsupervised DNN that dynamically masks out image information based on a combination of a differentiable adaptation of Otsu's Method and CutOut augmentation. SoftOtsuNet augmentation outperforms all other evaluated augmentation methods on the Fitzpatrick17k dataset (0.75% improvement), Diverse Dermatology Images dataset (1.76% improvement), and our proprietary dataset (0.92% improvement). SoftOtsuNet is only required at training time, meaning inference costs are unchanged from the baseline. This further suggests that even large data-driven models can still benefit from human-engineered unsupervised loss functions.

Structure and Funding of Clinical Informatics Fellowships: A National Survey of Program Directors

BACKGROUND

In 2011, the American Board of Medical Specialties established clinical informatics (CI) as a subspecialty in medicine, jointly administered by the American Board of Pathology and the American Board of Preventive Medicine. Subsequently, many institutions created CI fellowship training programs to meet the growing need for informaticists. Although many programs share similar features, there is considerable variation in program funding and administrative structures.

OBJECTIVES

The aim of our study was to characterize CI fellowship program features, including governance structures, funding sources, and expenses.

METHODS

We created a cross-sectional online REDCap survey with 44 items requesting information on program administration, fellows, administrative support, funding sources, and expenses. We surveyed program directors of programs accredited by the Accreditation Council for Graduate Medical Education between 2014 and 2021.

RESULTS

We invited 54 program directors, of which 41 (76%) completed the survey. The average administrative support received was $27,732/year. Most programs (85.4%) were accredited to have two or more fellows per year. Programs were administratively housed under six departments: Internal Medicine (17; 41.5%), Pediatrics (7; 17.1%), Pathology (6; 14.6%), Family Medicine (6; 14.6%), Emergency Medicine (4; 9.8%), and Anesthesiology (1; 2.4%). Funding sources for CI fellowship program directors included: hospital or health systems (28.3%), clinical departments (28.3%), graduate medical education office (13.2%), biomedical informatics department (9.4%), hospital information technology (9.4%), research and grants (7.5%), and other sources (3.8%) that included philanthropy and external entities.

CONCLUSION

CI fellowships have been established in leading academic and community health care systems across the country. Due to their unique training requirements, these programs require significant resources for education, administration, and recruitment. There continues to be considerable heterogeneity in funding models between programs. Our survey findings reinforce the need for reformed federal funding models for informatics practice and training.

Measles: Contemporary considerations for the emergency physician

Measles, or rubeola, is a highly contagious acute febrile viral illness. Despite the availability of an effective vaccine since 1963, measles outbreaks continue worldwide. This article seeks to provide emergency physicians with the contemporary knowledge required to rapidly diagnose potential measles cases and bolster public health measures to reduce ongoing transmission.

Clinical Policy: Critical Issues in the Management of Adult Patients Presenting to the Emergency Department With Mild Traumatic Brain Injury: Approved by ACEP Board of Directors, February 1, 2023 Clinical Policy Endorsed by the Emergency Nurses Association (April 5, 2023)

This 2023 Clinical Policy from the American College of Emergency Physicians is an update of the 2008 “Clinical Policy: Neuroimaging and Decisionmaking in Adult Mild Traumatic Brain Injury in the Acute Setting.” A writing subcommittee conducted a systematic review of the literature to derive evidence-based recommendations to answer the following questions: 1) In the adult emergency department patient presenting with minor head injury, are there clinical decision tools to identify patients who do not require a head computed tomography? 2) In the adult emergency department patient presenting with minor head injury, a normal baseline neurologic examination, and taking an anticoagulant or antiplatelet medication, is discharge safe after a single head computed tomography? and 3) In the adult emergency department patient diagnosed with mild traumatic brain injury or concussion, are there clinical decision tools or factors to identify patients requiring follow-up care for postconcussive syndrome or to identify patients with delayed sequelae after emergency department discharge? Evidence was graded and recommendations were made based on the strength of the available data. Widespread and consistent implementation of evidence-based clinical recommendations is warranted to improve patient care.

Overcoming barriers to promotion for women and underrepresented in medicine faculty in academic emergency medicine

Equity in the promotion of women and underrepresented minorities (URiM) is essential for the advancement of academic emergency medicine and the specialty as a whole. Forward-thinking healthcare organizations can best position themselves to optimally care for an increasingly diverse patient population and mentor trainees by championing increased diversity in senior faculty ranks, leadership, and governance roles. This article explores several potential solutions to addressing inequities that hinder the advancement of women and URiM faculty. It is intended to complement the recently approved American College of Emergency Physicians (ACEP) policy statement aimed at overcoming barriers to promotion of women and URiM faculty in academic emergency medicine. This policy statement was jointly released and supported by the Society for Academic Emergency Medicine (SAEM), American Academy of Emergency Medicine (AAEM), and the Association of Academic Chairs of Emergency Medicine (AACEM).

Trends in user-initiated health information exchange in the inpatient, outpatient, and emergency settings

Prior research on health information exchange (HIE) typically measured provider usage through surveys or they summarized the availability of HIE services in a healthcare organization. Few studies utilized user log files. Using HIE access log files, we measured HIE use in real-world clinical settings over a 7-year period (2011-2017). Use of HIE increased in inpatient, outpatient, and emergency department (ED) settings. Further, while extant literature has generally viewed the ED as the most relevant setting for HIE, the greatest change in HIE use was observed in the inpatient setting, followed by the ED setting and then the outpatient setting. Our findings suggest that in addition to federal incentives, the implementation of features that address barriers to access (eg, Single Sign On), as well as value-added services (eg, interoperability with external data sources), may be related to the growth in user-initiated HIE.

Does academic practice protect emergency physicians against burnout?

Burnout is a complex syndrome thought to result from long-term exposure to career-related stressors. Physicians are at higher risk for burnout than the general United States (US) working population, and emergency medicine has some of the highest burnout rates of any medical specialty. Burnout impacts physicians' quality of life, but it can also increase medical errors and negatively affect patient safety. Several studies have reported lower burnout rates and higher job satisfaction in academic medicine as compared with private practice. However, researchers have only begun to explore the factors that underlie this protective effect. This paper aims to review existing literature to identify specific aspects of academic practice in emergency medicine that may be associated with lower physician burnout rates and greater career satisfaction. Broadly, it appears that spending time in the area of emergency medicine one finds most meaningful has been associated with reduced physician burnout. Certain non-clinical academic work, including involvement in research, leadership, teaching, and mentorship, have been identified as specific activities that may protect against burnout and contribute to higher job satisfaction. Given the epidemic of physician burnout, hospitals and practice groups have a responsibility to address burnout, both by prevention and by early recognition and support. We discuss methods by which organizations can actively foster physician well-being and provide examples of 2 leading academic institutions that have developed comprehensive programs to promote physician wellness and prevent burnout.

Electric Scooters (e-scooters): Assessing the Threat to Public Health and Safety in Setting Policies: Assessing e-scooter policies

Objective: To determine self-reported incidences of health and safety hazards among persons who ride rentable electric scooters (e-scooters), knowledge of e-scooter laws, and attitudes and perceptions of the health and safety of e-scooter usage. Methods: A cross-sectional survey of n= 561 e-scooter riders and non-riders was conducted during June of 2019. Results: Almost half of respondents (44%) report that e-scooters pose a threat to the health and safety of riders. Riders and non-riders disagree regarding the hazards that e-scooters pose to pedestrians. Among riders, 15% report crashing or falling off an e-scooter. Only 2.5% of e-scooter riders self-report that they always wear a helmet while riding. Conclusions: E-scooter riders report substantial rates of harmful behavior and injuries. Knowledge of e-scooter laws is limited, and e-scooters introduce threats to the health and safety of riders, pedestrians on sidewalks, and automobile drivers. Enhanced public health interventions are needed to educate about potential health risks and laws associated with e-scooter use and to ensure health in all policies. Additionally, greater consideration should be given to public health, safety, and injury prevention when passing relevant state and local e-scooter laws.  

Changes to the ACGME Common Program Requirements and Their Potential Impact on Emergency Medicine Core Faculty Protected Time

The Accreditation Council for Graduate Medical Education (ACGME), which regulates residency and fellowship training in the United States, recently revised the minimum standards for all training programs. These standards are codified and published as the Common Program Requirements. Recent specific revisions, particularly removing the requirement ensuring protected time for core faculty, are poised to have a substantial impact on emergency medicine training programs. A group of representatives and relevant stakeholders from national emergency medicine (EM) organizations was convened to assess the potential effects of these changes on core faculty and the training of emergency physicians. We reviewed the literature and results of surveys conducted by EM organizations to examine the role of core faculty protected time. Faculty nonclinical activities contribute greatly to the academic missions of EM training programs. Protected time and reduced clinical hours allow core faculty to engage in education and research, which are two of the three core pillars of academic EM. Loss of core faculty protected time is expected to have detrimental impacts on training programs and on EM generally. We provide consensus recommendations regarding EM core faculty clinical work hour limitations to maintain protected time for educational activities and scholarship and preserve the quality of academic EM.

Preliminary evaluation of the Chest Pain Dashboard, a FHIR-based approach for integrating health information exchange information directly into the clinical workflow

Despite efforts aimed at improving the integration of clinical data from health information exchanges (HIE) and electronic health records (EHR), interoperability remains limited. Barriers due to inefficiencies and workflow interruptions make using HIE data during care delivery difficult. Capitalizing on the development of the Fast Healthcare Interoperability Resource (FHIR) specification, we designed and developed a Chest Pain Dashboard that integrates HIE data into EHRs. This Dashboard was implemented in one emergency department (ED) of Indiana University Health in Indiana. In this paper, we present the preliminary findings from a mixed-methods evaluation of the Dashboard. A difference-in-difference analysis suggests that the ED with the Dashboard implementation resulted in a significant increase in HIE use compared to EDs without. This finding was supported by qualitative interviews. While these results are encouraging, we also identified areas for improvement. FHIR-based solutions may offer promising approaches to encourage greater accessibility and use of HIE data.

Characteristics of the National Applicant Pool for Clinical Informatics Fellowships (2016-2017)

We conducted a national study to assess the numbers and diversity of applicants for 2016 and 2017 clinical informatics fellowship positions. In each year, we collected data on the number of applications that programs received from candidates who were ultimately successful vs. unsuccessful. In 2017, we also conducted an anonymous applicant survey. Successful candidates applied to an average of 4.2 and 5.5 programs for 2016 and 2017, respectively. In the survey, unsuccessful candidates reported applying to fewer programs. Assuming unsuccessful candidates submitted between 2-5 applications each, the total applicant pool numbered 42-69 for 2016 (competing for 24 positions) and 52-85 for 2017 (competing for 30 positions). Among survey respondents (n=33), 24% were female, 1 was black and none were Hispanic. We conclude that greater efforts are needed to enhance interest in clinical informatics among medical students and residents, particularly among women and members of underrepresented minority groups.

Early experiences of accredited clinical informatics fellowships

Since the launch of the clinical informatics subspecialty for physicians in 2013, over 1100 physicians have used the practice and education pathways to become board-certified in clinical informatics. Starting in 2018, only physicians who have completed a 2-year clinical informatics fellowship program accredited by the Accreditation Council on Graduate Medical Education will be eligible to take the board exam. The purpose of this viewpoint piece is to describe the collective experience of the first four programs accredited by the Accreditation Council on Graduate Medical Education and to share lessons learned in developing new fellowship programs in this novel medical subspecialty.

Developing new pathways into the biomedical informatics field: the AMIA High School Scholars Program

Increasing access to biomedical informatics experiences is a significant need as the field continues to face workforce challenges. Looking beyond traditional medical school and graduate school pathways into the field is crucial for expanding the number of individuals and increasing diversity in the field. This case report provides an overview of the development and initial implementation of the American Medical Informatics Association (AMIA) High School Scholars Program. Initiated in 2014, the program's primary goal was to provide dissemination opportunities for high school students engaged in biomedical informatics research. We discuss success factors including strong cross-institutional, cross-organizational collaboration and the high quality of high school student submissions to the program. The challenges encountered, especially around working with minors and communicating program expectations clearly, are also discussed. Finally, we present the path forward for the continued evolution of the AMIA High School Scholars Program.

A practical method for predicting frequent use of emergency department care using routinely available electronic registration data

Background

Accurately predicting future frequent emergency department (ED) utilization can support a case management approach and ultimately reduce health care costs. This study assesses the feasibility of using routinely collected registration data to predict future frequent ED visits.

Method

Using routinely collected registration data in the state of Indiana, U.S.A., from 2008, we developed multivariable logistic regression models to predict frequent ED visits in the subsequent two years. We assessed the model’s accuracy using Receiver Operating Characteristic (ROC) curves, sensitivity, and positive predictive value (PPV).

Results

Strong predictors of frequent ED visits included age between 25 and 44 years, female gender, close proximity to the ED (less than 5 miles traveling distance), total visits in the baseline year, and respiratory and dental chief complaint syndromes. The area under ROC curve (AUC) ranged from 0.83 to 0.92 for models predicting patients with 8 or more visits to 16 or more visits in the subsequent two years, suggesting acceptable discrimination. With 25 % sensitivity, the model predicting frequent ED use as defined as 16 or more visits in 2009 and 2010 had a PPV of 59.5 % and specificity of 99.9 %. The “adjusted” PPV of this model, which includes patients having 8 or more visits, is 81.9 %.

Conclusion

We demonstrate a strong association between predictor variables present in registration data and frequent ED use. The algorithm’s performance characteristics suggest that it is technically feasible to use routinely collected registration data to predict future frequent ED use.

Clinical Informatics Fellowship Programs: In Search of a Viable Financial Model: An open letter to the Centers for Medicare and Medicaid Services

In the US, the new subspecialty of Clinical Informatics focuses on systems-level improvements in care delivery through the use of health information technology (HIT), data analytics, clinical decision support, data visualization and related tools. Clinical informatics is one of the first subspecialties in medicine open to physicians trained in any primary specialty. Clinical Informatics benefits patients and payers such as Medicare and Medicaid through its potential to reduce errors, increase safety, reduce costs, and improve care coordination and efficiency. Even though Clinical Informatics benefits patients and payers, because GME funding from the Centers for Medicare and Medicaid Services (CMS) has not grown at the same rate as training programs, the majority of the cost of training new Clinical Informaticians is currently paid by academic health science centers, which is unsustainable. To maintain the value of HIT investments by the government and health care organizations, we must train sufficient leaders in Clinical Informatics. In the best interest of patients, payers, and the US society, it is therefore critical to find viable financial models for Clinical Informatics fellowship programs. To support the development of adequate training programs in Clinical Informatics, we request that the Centers for Medicare and Medicaid Services (CMS) issue clarifying guidance that would allow accredited ACGME institutions to bill for clinical services delivered by fellows at the fellowship program site within their primary specialty.

Evaluating congruence between laboratory LOINC value sets for quality measures, public health reporting, and mapping common tests

Laboratory test results are important for secondary data uses like quality measures and public health reporting, but mapping local laboratory codes to LOINC is a challenge. We evaluated the congruence between laboratory LOINC value sets for quality measures, public health reporting, and mapping common tests. We found a modest proportion of the LOINC codes from the Value Set Authority Center (VSAC) were present in the LOINC Top 2000 Results (16%) and the Reportable Condition Mapping Table (52%), and only 25 terms (3%) were shared with the Notifiable Condition Detector Top 129. More than a third of the VSAC Quality LOINCs were unique to that value set. A relatively small proportion of the VSAC Quality LOINCs were used by our hospital laboratories. Our results illustrate how mapping based only on test frequency might hinder these secondary uses of laboratory test results.

An evaluation of the rates of repeat notifiable disease reporting and patient crossover using a health information exchange-based automated electronic laboratory reporting system

Patients move across healthcare organizations and utilize services with great frequency and variety. This fact impacts both health information technology policy and patient care. To understand the challenges faced when developing strategies for effective health information exchange, it is important to understand patterns of patient movement and utilization for many healthcare contexts, including managing public-health notifiable conditions. We studied over 10 years of public-health notifiable diseases using the nation's most comprehensive operational automatic electronic laboratory reporting system to characterize patient utilization patterns. Our cohort included 412,699 patients and 833,710 reportable cases. 11.3% of patients had multiple notifiable case reports, and 19.5% had notifiable disease data distributed across 2 or more institutions. This evidence adds to the growing body of evidence that patient data resides in many organizations and suggests that to fully realize the value of HIT in public health, cross-organizational data sharing must be meaningfully incentivized.

Emergency department physician internet use during clinical encounters

OBJECTIVE

This study explored the Internet log files from emergency department workstations to determine search patterns, compared them to discharge diagnoses, and the emergency medicine curriculum as a way to quantify physician search behaviors.

METHODS

The log files from the computers from January 2006 to March 2010 were mapped to the EM curriculum and compared to discharge diagnoses to explore search terms and website usage by physicians and students.

RESULTS

Physicians in the ED averaged 1.35 searches per patient encounter using Google.com and UpToDate.com 83.9% of the time. The most common searches were for drug information (23.1%) by all provider types. The majority of the websites utilized were in the third tier evidence level for evidence-based medicine (EBM).

CONCLUSION

We have shown a need for a readily accessible drug knowledge base within the EMR for decision support as well as easier access to first and second tier EBM evidence.

Indianapolis emergency medical service and the Indiana Network for Patient Care: evaluating the patient match algorithm

In 2009, Indianapolis launched an electronic medical record system within their ambulances1 and started to exchange patient data with the Indiana Network for Patient Care (INPC) This unique system allows EMS personnel to get important information prior to the patient's arrival to the hospital. In this descriptive study, we found EMS personnel requested patient data on 14% of all transports, with a "success" match rate of 46%, and a match "failure" rate of 17%. The three major factors for causing match "failure" were ZIP code 55%, Patient Name 22%, and Birth date 12%. We conclude that the ZIP code matching process needs to be improved by applying a limitation of 5 digits in ZIP code instead of using ZIP+4 code. Non-ZIP code identifiers may be a better choice due to inaccuracies and changes of the ZIP code in a patient's record.

Variability in drug formularies and implications in decision support

Formularies are highly variable, which limits physicians ability to prescribe cost effective medications for their patients. In this study we explore the composition of 3,346 formularies in terms of outpatient prescription coverage, medication class coverage, and cost implications. Our analysis revealed that 42% of formularies are duplicative and that the unique formularies contain variability for medications that contribute little in terms of cost or overall use. These results lead us to believe the number and complexities of formularies can be dramatically reduced leading to more intuitive decision support for physicians when writing prescriptions.

All health care is not local: an evaluation of the distribution of Emergency Department care delivered in Indiana

The Emergency Department (ED) delivers a major portion of health care - often with incomplete knowledge about the patient. As such, EDs are particularly likely to benefit from a health information exchange (HIE). The Indiana Public Health Emergency Surveillance System (PHESS) sends real-time registration information for emergency department encounters. Over the three-year study period, we found 2.8 million patients generated 7.4 million ED visits. The average number of visits was 2.6 visits/patient (range 1-385). We found more than 40% of ED visits during the study period were for patients having data at multiple institutions. When examining the network density, we found nearly all EDs share patients with more than 80 other EDs. Our results help clarify future health care policy decisions regarding optimal NHIN architecture and discount the notion that 'all healthcare is local'.

Emergency medical services: the frontier in health information exchange

Emergency medical service (EMS) providers routinely lack even basic access to pre-existing patient information when delivering patient care in the field. Improving access to pre-existing patient information could improve the quality, safety and efficiency of care that they can deliver. EMS providers in Indianapolis use an electronic record to document their care. In order to provide access to pre-existing patient information, we integrated the EMS electronic record into the Indiana Network for Patient Care (INPC) --an operational statewide health information exchange (HIE). Over a six month study period, there were 28,986 911 calls to EMS, with 4,332 (16%) requests for patient data. Of the 58 medics surveyed, a substantial majority felt the information delivered was an important tool for delivering quality patient care.

Delphi consensus on the feasibility of translating the ACEP clinical policies into computerized clinical decision support

Clinical practice guidelines are developed to reduce variations in clinical practice, with the goal of improving health care quality and cost. However, evidence-based practice guidelines face barriers to dissemination, implementation, usability, integration into practice, and use. The American College of Emergency Physicians (ACEP) clinical policies have been shown to be safe and effective and are even cited by other specialties. In spite of the benefits of the ACEP clinical policies, implementation of these clinical practice guidelines into physician practice continues to be a challenge. Translation of the ACEP clinical policies into real-time computerized clinical decision support systems could help address these barriers and improve clinician decision making at the point of care. The investigators convened an emergency medicine informatics expert panel and used a Delphi consensus process to assess the feasibility of translating the current ACEP clinical policies into clinical decision support content. This resulting consensus document will serve to identify limitations to implementation of the existing ACEP Clinical Policies so that future clinical practice guideline development will consider implementation into clinical decision support at all stages of guideline development.

Changes in patient mortality based on increased patient load in the emergency department

Being able to better understand the effects of emergency department overcrowding can improve patient outcome. We propose to evaluate various predictors of mortality based on our ability to identify at what point an ED becomes too busy causing decreased quality of care. The study aims to utilize information from hospital records and statewide death records to find significant increases in mortality associated with presenting to the ED during a busy period of time.

A rationale for parsimonious laboratory term mapping by frequency

Mapping local observation codes to a standard vocabulary provides a bridge across the many islands of data that reside in isolated systems, but mapping is resource intensive. To help prioritize the mapping effort, we analyzed laboratory results reported over a thirteen month period from five institutions in the Indiana Network for Patient Care. Overall, more than 4,000 laboratory observation codes accounted for almost 49 million results. Of the observations reported in the thirteen months, 80 codes (2%) accounted for 80% of the total volume from all institutions and 784 codes (19%) accounted for 99% of the volume from all institutions. The 244 to 517 observation codes that represented 99% of the volume at each institution also captured all results for more than 99% of the patients at that institution. Our findings suggest that focusing the mapping effort on this modest set of high-yield codes can reduce the barriers to interoperability.

In support of emergency department health information technology

Emergency department visits represent a significant portion of medical care. Emergency physicians require immediate access to clinical information in order to provide quality care. Increased medical errors result when access to the complete medical record is limited. Clinicians' access to clinical information is limited to the greatest extent when care occurs over short time intervals, and between separate healthcare systems. Over the four-year period, the majority (85%) of all patients, stay within the same system; however, of patients with more than one visit, this percentage decreases to 66%. Of patients who return within 24 hours, 75% return to the same hospital or healthcare system. This patient population represents a unique cohort with special healthcare needs. Not only do they represent a disproportionate share of visits compared to those remaining within a single system but they also represent additional, and often underestimated, opportunities to provide quality care.

A calibrated paper clip is a reliable measure of two-point discrimination

OBJECTIVES

The primary objective of this study was to compare two different instruments for assessing digital nerve function; a secondary aim was to determine interobserver agreement among emergency physicians by using static two-point testing of digital nerve function.

METHODS

This was a prospective, blinded, observational study of static two-point discrimination involving healthy volunteers aged 18-59 years. The authors compared two instruments (paper clip set or Disk-Criminator) to assess two-point discrimination of the index and long fingers of the dominant hand. For each subject, the initial investigator and initial testing instrument were randomized. Two-point testing was conducted at 4, 5, and 6 mm by using six randomly selected stimuli (1 or 2 points) for each distal phalanx tested. The study was designed to detect a 25% difference in mean two-point distance with a power of 80%.

RESULTS

Seventy-five subjects were entered into the study, of which two were excluded. Interinstrument agreement for a given investigator ranged from 77% to 84% for absolute agreement and 98% to 100% within 2 mm. Weighted kappa values for interobserver differences of 2 mm or less was 0.79 to 1.00. There was no statistically significant difference between instruments.

CONCLUSIONS

Using a clinically relevant threshold of 2 mm, the authors found that a properly calibrated set of paper clips performed as well as the Disk-Criminator.

Community clinical data exchange for emergency medicine patients

Little is known about the opportunities for a community clinical data exchange network to influence patient care. Rates of patient "cross-over" among different institutions can provide one estimate of the additional value such systems have over unconnected, independent institutional electronic medical records. The Indiana Network for Patient Care (INPC) represents such a system, involving a collaboration of central Indiana hospitals to improve patient care. During a one year study period, 288,696 patients made 471,640 Emergency Department (ED) visits within the INPC collaboration -- accounting for 92% of all Indianapolis ED visits. Overall 25% of the patients with more than one visit also visited one of the other five hospital systems, accounting for 19% of all visits. Our results help clarify the expected frequency within one large metropolitan area that ED patients could obtain direct benefit from a community clinical data exchange network.