Prospective Multi-Site Validation of AI to Detect Tuberculosis and Chest X-Ray Abnormalities.

Background: Using artificial intelligence (AI) to interpret chest X-rays (CXRs) could support accessible triage tests for active pulmonary tuberculosis (TB) in resource-constrained settings.

Methods: The performance of two cloud-based CXR AI systems - one to detect TB and the other to detect CXR abnormalities - in a population with a high TB and human immunodeficiency virus (HIV) burden was evaluated. We recruited 1978 adults who had TB symptoms, were close contacts of known TB patients, or were newly diagnosed with HIV at three clinical sites.

A multiplexed high throughput screening assay using flow cytometry identifies glycolytic molecular probes in bloodstream form Trypanosoma brucei.

Kinetoplastid organisms, including Trypanosoma brucei, are a significant health burden in many tropical and semitropical countries. Much of their metabolism is poorly understood. To better study kinetoplastid metabolism, chemical probes that inhibit kinetoplastid enzymes are needed.

Assistive AI in Lung Cancer Screening: A Retrospective Multinational Study in the United States and Japan.

Purpose To evaluate the impact of an artificial intelligence (AI) assistant for lung cancer screening on multinational clinical workflows. Materials and Methods An AI assistant for lung cancer screening was evaluated on two retrospective randomized multireader multicase studies where 627 (141 cancer-positive cases) low-dose chest CT cases were each read twice (with and without AI assistance) by experienced thoracic radiologists (six U.S.

An intentional approach to managing bias in general purpose embedding models.

Advances in machine learning for health care have brought concerns about bias from the research community; specifically, the introduction, perpetuation, or exacerbation of care disparities. Reinforcing these concerns is the finding that medical images often reveal signals about sensitive attributes in ways that are hard to pinpoint by both algorithms and people. This finding raises a question about how to best design general purpose pretrained embeddings (GPPEs, defined as embeddings meant to support a broad array of use cases) for building downstream models that are free from particular types of bias.

Beyond the Four Walls: The American College of Emergency Physicians 2022 New Practice Models Task Force Report.

Emergency physicians are highly trained to deliver acute unscheduled care. The emergency physician core skillset gained during emergency medicine residency can be applied to many other roles that benefit patients and extend and diversify emergency physician careers. In 2022, the American College of Emergency Physicians (ACEP) convened the New Practice Models Task Force to describe new care models and emergency physician opportunities outside the 4 walls of the emergency department.

Health outcomes of penicillin allergy testing in children: a systematic review.

Background: Penicillin allergy labels are commonly acquired in childhood and lead to avoidance of first-line penicillin antibiotics. Understanding the health outcomes of penicillin allergy testing (PAT) can strengthen its place in antimicrobial stewardship efforts.

Objectives: To identify and summarize the health outcomes of PAT in children.

Development of a Machine Learning Model for Sonographic Assessment of Gestational Age.

Importance: Fetal ultrasonography is essential for confirmation of gestational age (GA), and accurate GA assessment is important for providing appropriate care throughout pregnancy and for identifying complications, including fetal growth disorders. Derivation of GA from manual fetal biometry measurements (ie, head, abdomen, and femur) is operator dependent and time-consuming.

Objective: To develop artificial intelligence (AI) models to estimate GA with higher accuracy and reliability, leveraging standard biometry images and fly-to ultrasonography videos.

A mobile-optimized artificial intelligence system for gestational age and fetal malpresentation assessment.

Background: Fetal ultrasound is an important component of antenatal care, but shortage of adequately trained healthcare workers has limited its adoption in low-to-middle-income countries. This study investigated the use of artificial intelligence for fetal ultrasound in under-resourced settings.

Methods: Blind sweep ultrasounds, consisting of six freehand ultrasound sweeps, were collected by sonographers in the USA and Zambia, and novice operators in Zambia.

Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists.

Background The World Health Organization (WHO) recommends chest radiography to facilitate tuberculosis (TB) screening. However, chest radiograph interpretation expertise remains limited in many regions. Purpose To develop a deep learning system (DLS) to detect active pulmonary TB on chest radiographs and compare its performance to that of radiologists.

Deep learning for distinguishing normal versus abnormal chest radiographs and generalization to two unseen diseases tuberculosis and COVID-19.

Chest radiography (CXR) is the most widely-used thoracic clinical imaging modality and is crucial for guiding the management of cardiothoracic conditions. The detection of specific CXR findings has been the main focus of several artificial intelligence (AI) systems. However, the wide range of possible CXR abnormalities makes it impractical to detect every possible condition by building multiple separate systems, each of which detects one or more pre-specified conditions.

A Cross-Sectional Analysis of High-Acuity Professional Services Performed by Urban and Rural Emergency Care Physicians Across the United States.

Study Objective: We seek to examine differences in the provision of high-acuity professional services between rural and urban physicians receiving reimbursement for emergency care evaluation and management services from Medicare fee-for-service Part B.

Methods: Using the 2017 Medicare Public Use Files, we performed a cross-sectional analysis and defined the primary outcome, the proportion of high-acuity charts (PHAC), at the physician level as the proportion of services provided as 99285 and 99291 emergency care evaluation and management service codes relative to all such codes. After accounting for unique clinician-level characteristics, we categorized individual physicians by PHAC quintiles and conducted ordered logistic regression analyses reporting adjusted marginal probabilities to examine associations with rurality.

The Three-Year Effect of Medicaid Expansion on Emergency Department Visits and Admissions.

Study Objective: We examine the effect of the Medicaid expansion in 2014 under in the Patient Protection and Affordable Care Act on emergency department (ED) utilization and ED admission rates (fraction of ED visits that lead to hospital admission) during the first 3 postexpansion years (2014 to 2016).

Methods: We compared ED utilization and ED admission rates in 151 EDs in 14 expansion states with those in 376 EDs in 14 nonexpansion states, using difference-in-differences methods with data from 3 national emergency medicine groups from 2013 to 2016.

Results: In expansion states, the volume of Medicaid-paid ED visits increased 49% (95% confidence interval 34% to 65%), and the volume of uninsured visits decreased 44% (95% confidence interval -52% to -34%) relative to that of nonexpansion states.

Managing and Measuring Emergency Department Care: Results of the Fourth Emergency Department Benchmarking Definitions Summit.

Background: A shared language and vocabulary are essential for managing emergency department (ED) operations. This Fourth Emergency Department Benchmarking Alliance (EDBA) Summit brought together experts in the field to review, update, and add to key definitions and metrics of ED operations.

Objective: Summit objectives were to review and revise existing definitions, define and characterize new practices related to ED operations, and introduce financial and regulatory definitions affecting ED reimbursement.

Choosing wisely in emergency medicine: Early results and insights from the ACEP emergency quality network (E-QUAL).

Purpose: To characterize performance among ED sites participating in the Emergency Quality Network (E-QUAL) Avoidable Imaging Initiative for clinical targets on the American College of Emergency Physicians Choosing Wisely list.

Methods: This was an observational study of quality improvement (QI) data collected from hospital-based ED sites in 2017-2018. Participating EDs reported imaging utilization rates (UR) and common QI practices for three Choosing Wisely targets: Atraumatic Low Back Pain, Syncope, or Minor Head Injury.

Medicaid Expansion In 2014 Did Not Increase Emergency Department Use But Did Change Insurance Payer Mix.

In 2014 twenty-eight states and the District of Columbia had expanded Medicaid eligibility while federal and state-based Marketplaces in every state made subsidized private health insurance available to qualified individuals. As a result, about seventeen million previously uninsured Americans gained health insurance in 2014. Many policy makers had predicted that Medicaid expansion would lead to greatly increased use of hospital emergency departments (EDs).

The Affordable Care Act and emergency care.

The Affordable Care Act (ACA) will have far-reaching effects on the way health care is designed and delivered. Several elements of the ACA will directly affect both demand for ED care and expectations for its role in providing coordinated care. Hospitals will need to employ strategies to reduce ED crowding as the ACA expands insurance coverage.

The effect of electronic health record implementation on community emergency department operational measures of performance.

Study Objective: We study the effect of an emergency department (ED) electronic health record implementation on the operational metrics of a diverse group of community EDs.

Methods: We performed a retrospective before/after analysis of 23 EDs from a single management group that experienced ED electronic health record implementation (with the majority of electronic health records optimized specifically for ED use). We obtained electronic data for 4 length of stay measures (arrival to provider, admitted, discharged, and overall length of stay) and 4 measures of operational characteristics (left before treatment complete, significant returns, overall patient satisfaction, and provider efficiency).

Strategies for integrating cost-consciousness into acute care should focus on rewarding high-value care.

The acute care system reflects the best and worst in American medicine. The system, which includes urgent care and retail clinics, emergency departments, hospitals, and doctors' offices, delivers 24/7 care for life-threatening conditions and is a key part of the safety net for the under- and uninsured. At the same time, it is fragmented, disconnected, and costly.

Interventions to improve the timeliness of emergency care.

With a persistent trend of increasing emergency department (ED) volumes every year, services are intensifying. Thus, improving the timeliness of delivering emergency care should be a primary focus, both from an operational and from a research perspective. Much has been published on factors associated with delays in emergency care, and the next phase in this area of research will focus on exploring interventions to improve the timeliness of care.

Practical implications of implementing emergency department crowding interventions: summary of a moderated panel.

Emergency department (ED) crowding continues to be a major public health problem in the United States and around the world. In June 2011, the Academic Emergency Medicine consensus conference focused on exploring interventions to alleviate ED crowding and to generate a series of research agendas on the topic. As part of the conference, a panel of leaders in the emergency care community shared their perspectives on emergency care, crowding, and some of the fundamental issues facing emergency care today.

Episodes of care: is emergency medicine ready?

Optimizing resource use, eliminating waste, aligning provider incentives, reducing overall costs, and coordinating the delivery of quality care while improving outcomes have been major themes of health care reform initiatives. Recent legislation contains several provisions designed to move away from the current fee-for-service payment mechanism toward a model that reimburses providers for caring for a population of patients over time while shifting more financial risk to providers. In this article, we review current approaches to episode of care development and reimbursement.

Administrative challenges to regionalization.

The ideal emergency care system delivers the right care to the right patient at the right time and yields appropriate patient outcomes at a sustainable overall cost. Transforming the current system of emergency care into the Institute of Medicine's vision of a coordinated, regionalized, and accountable emergency care system requires careful consideration of administrative challenges and barriers. Left unaddressed, certain processes, systems, and structures may prevent integration efforts or threaten long-term viability.

Research priorities for administrative challenges of integrated networks of care.

In 2006, the Institute of Medicine (IOM) advanced the concept of "coordinated, regionalized, and accountable emergency care systems" to address significant problems with the delivery of emergency medical care in the United States. Achieving this vision requires the thoughtful implementation of well-aligned, system-level structures and processes that enhance access to emergency care and improve patient outcomes at a sustainable cost. Currently, the delivery of emergency medical care is supported by numerous administrative systems, including economic; reimbursement; legal and regulatory structures; licensure, credentialing, and accreditation processes; medicolegal systems; and quality reporting mechanisms.