Environmental Sustainability and AI in Radiology: A Double-Edged Sword.

According to the World Health Organization, climate change is the single biggest health threat facing humanity. The global health care system, including medical imaging, must manage the health effects of climate change while at the same time addressing the large amount of greenhouse gas (GHG) emissions generated in the delivery of care. Data centers and computational efforts are increasingly large contributors to GHG emissions in radiology. This is due to the explosive increase in big data and artificial intelligence (AI) applications that have resulted in large energy requirements for developing and deploying AI models. However, AI also has the potential to improve environmental sustainability in medical imaging. For example, use of AI can shorten MRI scan times with accelerated acquisition times, improve the scheduling efficiency of scanners, and optimize the use of decision-support tools to reduce low-value imaging. The purpose of this Radiology in Focus article is to discuss this duality at the intersection of environmental sustainability and AI in radiology. Further discussed are strategies and opportunities to decrease AI-related emissions and to leverage AI to improve sustainability in radiology, with a focus on health equity. Co-benefits of these strategies are explored, including lower cost and improved patient outcomes. Finally, knowledge gaps and areas for future research are highlighted.

A randomized trial of mailed outreach with behavioral economic interventions to improve liver cancer surveillance.

BACKGROUND: Surveillance rates for HCC remain limited in patients with cirrhosis. We evaluated whether opt-out mailed outreach increased uptake with or without a $20 unconditional incentive. METHODS: This was a pragmatic randomized controlled trial in an urban academic health system including adult patients with cirrhosis or advanced fibrosis, at least 1 visit to a specialty practice in the past 2 years and no surveillance in the last 7 months. Patients were randomized in a 1:2:2 ratio to (1) usual care, (2) a mailed letter with a signed order for an ultrasound, or (3) a mailed letter with an order and a $20 unconditional incentive. The main outcome was the proportion with completion of ultrasound within 6 months. RESULTS: Among the 562 patients included, the mean age was 62.1 (SD 11.1); 56.8% were male, 51.1% had Medicare, and 40.6% were Black. At 6 months, 27.6% (95% CI: 19.5-35.7) completed ultrasound in the Usual care arm, 54.5% (95% CI: 47.9-61.0) in the Letter + Order arm, and 54.1% (95% CI: 47.5-60.6) in the Letter + Order + Incentive arm. There was a significant increase in the Letter + Order arm compared to Usual care (absolute difference of 26.9%; 95% CI: 16.5-37.3; p<0.001), but no significant increase in the Letter + Order + Incentive arm compared to Letter + Order (absolute difference of -0.4; 95% CI: -9.7 to 8.8; p=0.93). CONCLUSIONS: There was an increase in HCC surveillance from mailed outreach with opt-out framing and a signed order slip, but no increase in response to the financial incentive.

Imaging Informatics Fellowship Curriculum: Building Consensus on the Most Critical Topics and the Future of the Informatics Fellowship.

The existing fellowship imaging informatics curriculum, established in 2004, has not undergone formal revision since its inception and inaccurately reflects present-day radiology infrastructure. It insufficiently equips trainees for today's informatics challenges as current practices require an understanding of advanced informatics processes and more complex system integration. We sought to address this issue by surveying imaging informatics fellowship program directors across the country to determine the components and cutline for essential topics in a standardized imaging informatics curriculum, the consensus on essential versus supplementary knowledge, and the factors individual programs may use to determine if a newly developed topic is an essential topic. We further identified typical program structural elements and sought fellowship director consensus on offering official graduate trainee certification to imaging informatics fellows. Here, we aim to provide an imaging informatics fellowship director consensus on topics considered essential while still providing a framework for informatics fellowship programs to customize their individual curricula.

Economic impact of selective use of contrast for routine follow-up MRI of patients with multiple sclerosis.

BACKGROUND AND PURPOSE: Imaging and autopsy studies show intracranial gadolinium deposition in patients who have undergone serial contrast-enhanced MRIs. This observation has raised concerns when using contrast administration in patients who receive frequent MRIs. To address this, we implemented a contrast-conditional protocol wherein gadolinium is administered only for multiple sclerosis (MS) patients with imaging evidence of new disease activity on precontrast imaging. In this study, we explore the economic impact of our new MRI protocol. METHODS: We compared scanner time and Medicare reimbursement using our contrast-conditional methodology versus that of prior protocols where all patients received gadolinium. RESULTS: For 422 patients over 4 months, the contrast-conditional protocol amounted to 60% decrease in contrast injection and savings of approximately 20% of MRI scanner time. If the extra scanner time was used for performing MS follow-up MRIs in additional patients, the contrast-conditional protocol would amount to net revenue loss of $21,707 (∼3.7%). CONCLUSIONS: Implementation of a new protocol to limit contrast in MS follow-up MRIs led to a minimal decrease in revenue when controlled for scanner time utilized and is outweighed by other benefits, including substantial decreased gadolinium administration, increased patient comfort, and increased availability of scanner time, which depending on type of studies performed could result in additional financial benefit.

Patient Factor Disparities in Imaging Follow-Up Rates After Incidental Abdominal Findings.

OBJECTIVE: The effect of demographics and societal determinants on imaging follow-up rates is not clear. The purpose of this study was to compare characteristics of patients with imaging findings representing possible cancer who undergo follow-up imaging versus those who do not to better understand factors that contribute to follow-up completion. MATERIALS AND METHODS: The records of 1588 patients with indeterminate abdominal imaging findings consecutively registered between July 1, 2013, and March 20, 2014, were reviewed. Several patient characteristics, including distance between patients' home zip codes and the flagship hospital of the health system were compared between the groups who did and did not undergo follow-up imaging. Subgroup analyses based on the location of the index examination were also performed. RESULTS: Among the 1513 (36.62%) included patients, 554 did not undergo follow-up abdominal imaging within 1 year of the index examination. The same was true of 270 of 938 (28.78%) outpatients and 168 of 279 (60.21%) emergency department patients. Eighty-nine of 959 (9.28%) patients who underwent follow-up imaging were younger than 40 years, compared with 76 of 554 (13.72%) patients who did not undergo follow-up imaging (p = 0.005). Fifty-four of 959 (5.63%) patients who underwent follow-up imaging were older than 80 years, compared with 70 of 554 (12.64%) patients who did not undergo follow-up imaging (p < 0.001). More white patients (587 of 959 vs 301 of 554, p = 0.007) and fewer black patients (204 of 554 versus 270 of 959, p < 0.001) were found in the follow-up imaging group. Greater distance from the flagship hospital correlated with less follow-up in the outpatient subgroup only (p = 0.03). CONCLUSION: Emergency department patients and patients at the extremes of age are less likely to complete follow-up imaging. Insurance status and race and ethnicity may affect follow-up completion rates. The relationship between distance to hospital and follow-up completion requires further investigation.

Geographic Patterns of Radiology Referrals in the United States: A Descriptive Network Analysis.

PURPOSE: To provide a nationwide description of radiology referral patterns for Medicare beneficiaries and network-based measures that can describe and monitor shifts in referral patterns. METHODS: We linked publicly available Medicare data with the National Plan and Provider Enumeration System data set to analyze 3,925,366 encounters representing referrals from nonradiology referrers to diagnostic radiology providers in 2015. We assessed per-state referral volume as well as in-state and in-region referrals and the correlation between state referral volume and in-state referrals. Additionally, we applied the conceptual framework of networks to create two measures to evaluate referrer-radiologist connections within each state: number of referrer relationships and referral density index (RDI). RESULTS: In 2015, there was considerable variation in in-state referrals across states, and the correlation between state referral volume and in-state referrals was low (0.18). Across census regions, in-region referrals were high (84.3% in the South to 89.2% in the Midwest). Across states, the mean number of referrer relationships ranged from 7.0 in Utah to 25.0 in California, and the number of referrer relationships varied significantly within states. Radiology provider RDI also varied both within and across states, with mean radiology provider RDI spanning from 0.05 in Kansas to 0.25 in Hawaii. CONCLUSIONS: In a nationwide description of geographic patterns in radiology referrals among Medicare beneficiaries, we demonstrate wide variation in radiology referral patterns and utilized network methods to develop two measures that can be used in the future to monitor shifts in referral patterns.

Gender and Radiology Publication Productivity: An Examination of Academic Faculty From Four Health Systems in the United States.

OBJECTIVES: To compare male and female radiology faculty publication productivity metrics at four major academic centers. MATERIALS AND METHODS: All Radiology Department faculty members at four academic medical centers from January 1, 2000, to December 31, 2015, were included. Publication metrics including total number of manuscripts published; h- and m-indices; number of publications where faculty member was listed as first, last, or sole author; whether a woman was listed as one of the first five coauthors; and year of first publication were retrieved from Scopus. Publication metrics were compared between genders using the Wilcoxon signed-rank and χ2 tests. RESULTS: A total of 711 faculty members (519 male, 192 [27%] female members) were identified. Male faculty had a significantly higher number of total publications (median 54 versus 24, P < .0001), publications per year (median 2.9 versus 1.6, P < .0001), and h- (median 17 versus 10, P < .0001) and m-indices (median 0.83 versus 0.60, P < .0001) than female faculty. Male faculty had a significantly higher percentage of single author (median 1% versus 0%, P = .0014) and last author (median 16% versus 11%, P < .0001) publications than female faculty. Female faculty had a significantly higher percentage of first author publications (21% versus 17%, P = .0025) and were significantly more likely to have another woman in their first five coauthor list (70% versus 45%, P < .0001) than male faculty. CONCLUSIONS: Large differences exist between female and male faculty in total publications; h- and m-indices; publications per year; number of first, single, last author papers; and percentage of faculty that have a female coauthor in their top five coauthor lists.

PORTER: a Prototype System for Patient-Oriented Radiology Reporting.

To empower patients to participate in their medical care and decision-making, effective communication is critical. In radiology, the clinical report is the primary medium of communication. Although radiologists historically have authored reports with the referring provider as the intended reader, patients increasingly access the reports through portals to electronic health record systems. We developed a system named PORTER (Patient-Oriented Radiology Reporter) to augment radiology reports with lay-language definitions. Our IRB-approved, HIPAA-compliant study protocol analyzed 100 knee MRI reports from an academic medical center to identify the most commonly utilized terms. A glossary of 313 terms was constructed to include definitions of the terms and, where available, links to reference sources and public-domain images. Flesch-Kincaid readability scores were computed to assure that definitions were readable at or below 10th-grade reading level. The system provided an interactive web site to view outpatient knee MRI exams. After logging in with their exam ID number and date of birth, patients viewed their report annotated with definitions from the glossary. Applicable images were displayed when the user's mouse hovered over a glossary term. This patient-oriented system can help empower patients to better understand their radiology results.

The Impact of Imaging Informatics Fellowships.

Imaging informatics (II) is an area within clinical informatics that is particularly important in the field of radiology. Provider groups have begun employing dedicated radiologist-informaticists to bridge medical, information technology and administrative functions, and academic institutions are meeting this demand through formal II fellowships. However, little is known about how these programs influence graduates' careers and perceptions about professional development. We electronically surveyed 26 graduates from US II fellowships and consensus leaders in the II community-many of whom were subspecialty diagnostic radiologists (68%) employed within academic institutions (48%)-about the perceived impact of II fellowships on career development and advancement. All graduates felt that II fellowship made them more valuable to employers, with the majority of reporting ongoing II roles (78%) and continued used of competencies (61%) and skills (56%) gained during fellowship in their current jobs. Other key benefits included access to mentors, protected time for academic work, networking opportunities, and positive impacts of annual compensation. Of respondents without II fellowship training, all would recommend fellowships to current trainees given the ability to gain a "still rare" but "essential skill set" that is "critical for future leaders in radiology" and "better job opportunities." While some respondents felt that II fellowships needed further formalization and standardization, most (85%) disagreed with requiring a 2-year II fellowship in order to qualify for board certification in clinical informatics. Instead, most believed that fellowships should be integrated with clinical residency or fellowship training while preserving formal didactics and unstructured project time. More work is needed to understand existing variations in II fellowship training structure and identify the optimal format for programs targeted at radiologists.

Milestones on a Shoestring: A Cost-Effective, Semi-automated Implementation of the New ACGME Requirements for Radiology.

RATIONALE AND OBJECTIVES: The advent of the ACGME's Next Accreditation System represents a significant new challenge for residencies and fellowships, owing to its requirements for more complex and detailed information. MATERIAL AND METHODS: We developed a system of online assessment tools to provide comprehensive coverage of the twelve ACGME Milestones and digitized them using freely available cloud-based productivity tools. These tools include a combination of point-of-care procedural assessments, electronic quizzes, online modules, and other data entry forms. Using free statistical analytic tools, we also developed an automated system for management, processing, and data reporting. RESULTS: After one year of use, our Milestones project has resulted in the submission of over 20,000 individual data points. The use of automated statistical methods to generate resident-specific profiles has allowed for dynamic reports of individual residents' progress. These profiles both summarize data and also allow program directors access to more granular information as needed. CONCLUSION: Informatics-driven strategies for data assessment and processing represent feasible solutions to Milestones assessment and analysis, reducing the potential administrative burden for program directors, residents, and staff.

Assessment of follow-up completeness and notification preferences for imaging findings of possible cancer: what happens after radiologists submit their reports?

RATIONALE AND OBJECTIVES: To understand the reasons leading to potentially inappropriate management of imaging findings concerning for malignancy and identify optimal methods for communicating these findings to providers. MATERIALS AND METHODS: We identified all abdominal imaging examinations with findings of possible cancer performed on six randomly selected days in August to December 2013. Electronic medical records (EMR) of one patient group were reviewed 3 months after the index examination to determine whether management was appropriate (completed follow-up or documented reason for no follow-up) or potentially inappropriate (no follow-up or no documented reason). Providers of a second patient group were contacted 5-6 days after imaging examinations to determine notification preferences. RESULTS: Among 43 patients in the first group, five (12%) received potentially inappropriate management. Reasons included patient loss to follow-up and provider failure to review imaging results, document known imaging findings, or communicate findings to providers outside the health system. Among 16 providers caring for patients in the second group, 33% were unaware of the findings, 75% preferred to be notified of abnormal findings via e-mail or EMR, 56% wanted an embedded hyperlink enabling immediate follow-up order entry, and only 25% had a system to monitor whether patients had completed ordered testing. CONCLUSIONS: One in eight patients did not receive potentially necessary follow-up care within 3 months of imaging findings of possible cancer. Automated notification of imaging findings and follow-up monitoring not only is desired by providers but can also address many of the reasons we found for inappropriate management.