Research and Publications.

As a result of the 21st Century Cures Act, radiology reports are immediately released to patients. We determine if readers of radiology reports, via electronic health records (EHRs), and radiology report complexity have changed post the implementation of the 21st Century Cures Act.

Dr Melissa Davis is an assistant professor of radiology and vice chair for imaging informatics in the Department of Radiology and Biomedical Imaging at Yale School of Medicine. She is known for her work at the intersection of imaging, innovation, technology, and organizational change.

Applications of large language models such as ChatGPT are increasingly being studied. Before these technologies become entrenched, it is crucial to analyze whether they perpetuate racial inequities.

As a result of the 21st Century Cures Act, radiology reports are immediately released to patients. However, these reports are often too complex for the lay patient, potentially leading to stress and anxiety. While solutions such as patient portals or providing radiologist contact information have been proposed in the past, new generative artificial intelligence technologies like ChatGPT and Google Gemini may provide the most accessible and scalable method of simplifying radiology reports for patients. Here, we gather the opinions of radiologists regarding this possibility.

Generative artificial intelligence (AI) and large language models (LLMs) are increasingly being recognized as tools with the potential to transform many industries, including health care. Implementation and use of these tools among radiologists is likely variable, driven by radiology practice and institutional factors. Radiologists from various practices were asked about their perspectives on generative AI and LLMs in radiology.

Appropriate governance can help identify, screen, assess, deploy, and maintain AI tools in a clinically impactful way.

This study [1] examines private equity (PE) market penetration in 10 specialties by linking PE acquisitions to national-level physician data. Acquisitions were concentrated in the U.S. South and in specialties such as dermatology, ophthalmology, and gastroenterology. The market share held by PE-backed practices was greater than 30.0% in one-third of metropolitan sampled areas (MSAs) and greater than 50.0% in one-sixth of MSAs. In one-quarter of MSAs, one PE-backed practice accounted for greater than 30.0% of the market share, and in one-eighth of MSAs, greater than 50.0% of the market share. In diagnostic radiology, local markets saw a greater PE presence. Although the number of MSAs where PE-backed practices dominated was lower in diagnostic radiology than in some other specialties, the mean market share held by PE-backed diagnostic radiology practices was 48.0%. In MSAs where the PE market share was greater than 50.0%, the mean market share held by PE-backed diagnostic radiology practices was 70.6%, the second highest market share held by PE among all specialties.

Artificial intelligence (AI) holds promise for helping patients access new and individualized health care pathways while increasing efficiencies for health care practitioners. Radiology has been at the forefront of this technology in medicine; many radiology practices are implementing and trialing AI-focused products. AI also holds great promise for reducing health disparities and promoting health equity. Radiology is ideally positioned to help reduce disparities given its central and critical role in patient care. The purposes of this article are to discuss the potential benefits and pitfalls of deploying AI algorithms in radiology, specifically highlighting the impact of AI on health equity; to explore ways to mitigate drivers of inequity; and to enhance pathways for creating better health care for all individuals, centering on a practical framework that helps radiologists address health equity during deployment of new tools.

Digital health change management projects have a high rate of failure which limits the realization of their potential benefits. While there are many change management models, there is limited evidence of one model being effective in all circumstances. We propose a framework for building on an organizations preferred change management model and adapting it based on the change desired and the organization. We use three change management scenarios (small, large, and rapid) from radiology to explore the application of the framework. Radiology was chosen to illustrate the framework because it has been digital longer than many medical specialties. Given the high number of upgrades and new digital platforms in Radiology, it could also serve as a testing ground for such a framework.

More than 70% of FDA-approved artificial intelligence (AI) tools are centered within radiology [1]. In 2008, one AI-enabled device application was approved by the FDA for clinical use, with the number increasing to 79 in 2022. This trajectory ensures the continual growth of AI tools in radiology practice and throughout the marketplace. Therefore, radiology groups must understand the economics of implementing and using these tools in robust ways.

The timely reporting of critical results in radiology is paramount to improved patient outcomes. Artificial intelligence has the ability to improve quality by optimizing clinical radiology workflows. We sought to determine the impact of a United States Food and Drug Administration-approved machine learning (ML) algorithm, meant to mark computed tomography (CT) head examinations pending interpretation as higher probability for intracranial hemorrhage (ICH), on metrics across our healthcare system. We hypothesized that ML is associated with a reduction in report turnaround time (RTAT) and length of stay (LOS) in emergency department (ED) and inpatient populations.

We characterized the core elements of a clinical redesign program (CRDP) to represent both a team and a methodology to rapidly improve outcomes important to patients and hospitals (e.g., length of stay, unnecessary care, and cost). Unique features of our CRDP included a clinician lead, engagement from senior leadership, formal project management, and rapid cycle implementation. We aimed to examine the effectiveness of this strategy across three different project examples.

Social determinants of health, including race and insurance status, contribute to patient outcomes. In academic health systems, care is provided by a mix of trainees and faculty members. The optimal staffing ratio of trainees to faculty members (T/F) in radiology is unknown but may be related to the complexity of patients requiring care. Hospital characteristics, patient demographics, and radiology report findings may serve as markers of risk for poor outcomes because of patient complexity.

Chest radiographs (CXR) are frequently used as a screening tool for patients with suspected COVID-19 infection pending reverse transcriptase polymerase chain reaction (RT-PCR) results, despite recommendations against this. We evaluated radiologist performance for COVID-19 diagnosis on CXR at the time of patient presentation in the Emergency Department (ED).

Radiology procedure workflow is a summation of individual workflows for scheduling, precertification, preprocedure clinic visits, and day of procedure, representing a complex total process with many opportunities for inefficiencies and waste. At the authors’ institution, a lack of standard work and communication gaps in a pre- and postprocedure care area (PPCA) workflow were identified as factors in bottlenecks, waits and delays, and staff and patient frustrations. Using “lean” process improvement tools, these workflows were targeted in a rapid improvement event (RIE). A cross-functional team was formed to work on the PPCA workflow RIE. Using lean management principles, process gaps were identified and changes were instituted to improve patient and information flow. Three projects were implemented over a course of 4 months. These included a 5S, a lean methodology of workplace organization to optimize supply cabinets; standardization of nursing preprocedure documentation and process; and standard work confirmation in daily management system huddles. At baseline, 45% of patients were prepared within 60 minutes of their arrival in the PPCA. After the RIE and instituting the changes from the RIE, 80% of patients were prepared within 60 minutes of their arrival in the PPCA. Implementing lean management strategies, such as daily management systems and huddles, and establishing standard work confirmation help to eliminate waste and create systems and teams that sustain and improve complex workflows.

Radiology is not alone in grappling with these issues. Across healthcare specialties, coverage models have evolved to meet patient care demands. Many studies in the nursing and ED literature have analyzed the effects of shift coverage on patient care, productivity, and well-being.8-10 Although radiology’s needs may differ, this literature holds valuable lessons for the field. This review examines how 24-hour staffing has evolved and how it may be leveraged within the specialty. It also offers recommendations on potential future models of imaging coverage.

In this opinion article, we argue that to reduce race-based inequities in radiology, we must change leaders’ behaviors and the standard management practices of our organizations. Change agents must promote efforts to reduce racial inequities throughout our practices and hospitals. We close by discussing concrete ways to successfully implement change management practices and exploring how radiology leadership can contribute to these efforts through sustainable practice management.

Misdiagnosis of intracranial hemorrhage (ICH) can adversely impact patient outcomes. The increasing workload on the radiologists may increase the chance of error and compromise the quality of care provided by the radiologists.

In 2011, the Centers for Medicare & Medicaid Services (CMS) initiated public reporting of outpatient imaging efficiency measures to reduce potentially inappropriate imaging and unnecessary exposure to ionizing radiation performed in hospital outpatient departments. Three CMS quality measures were designed to reduce duplicative CT in the Medicare population: OP-10, which CMS lists as “Abdomen Computed Tomography—Use of Contrast Material”; OP-11, which CMS lists as “Thorax CT—Use of Contrast Material”; and OP-14, which CMS lists as “Simultaneous Use of Brain CT and Sinus CT.” We describe trends in hospital performance on these national hospital outpatient imaging efficiency measures since the inception of their public reporting.

The University of North Carolina at Chapel Hill (UNC) established a chapter of RAD-AID International in 2012. The group was founded by the UNC Division of Radiologic Science, and its membership draws from the Department of Allied Health Sciences and the Department of Radiology. To date, there are 45 members of the UNC RAD-AID chapter, including 7 radiologists, 17 technologists, 3 nurses, 1 radiation therapist, 1 biomedical engineer, 1 radiologist assistant, 6 technologist faculty members, and 9 students from these two departments. The mission of the chapter is to increase radiology’s contribution to sustainable global health initiatives and to develop long-term educational relationships with international partner organizations. The purpose of this communication is to discuss the interprofessional activities of the UNC RAD-AID chapter with colleagues in Malawi.