Use of ChatGPT to Assign BI-RADS Assessment Categories to Breast Imaging Reports.

The large language model GPT-4 showed limited utility in generating BI-RADS assessment categories for factitious breast imaging reports containing findings and impression sections, with frequent incorrect BI-RADS category assignments and poor reproducibility in assigned BI-RADS categories across independent tests for the same report using the same prompt.

Evaluating the Use of ChatGPT to Accurately Simplify Patient-centered Information about Breast Cancer Prevention and Screening.

Purpose To evaluate the use of ChatGPT as a tool to simplify answers to common questions about breast cancer prevention and screening. Materials and Methods In this retrospective, exploratory study, ChatGPT was requested to simplify responses to 25 questions about breast cancer to a sixth-grade reading level in March and August 2023. Simplified responses were evaluated for clinical appropriateness. All original and simplified responses were assessed for reading ease on the Flesch Reading Ease Index and for readability on five scales: Flesch-Kincaid Grade Level, Gunning Fog Index, Coleman-Liau Index, Automated Readability Index, and the Simple Measure of Gobbledygook (ie, SMOG) Index. Mean reading ease, readability, and word count were compared between original and simplified responses using paired t tests. McNemar test was used to compare the proportion of responses with adequate reading ease (score of 60 or greater) and readability (sixth-grade level). Results ChatGPT improved mean reading ease (original responses, 46 vs simplified responses, 70; P < .001) and readability (original, grade 13 vs simplified, grade 8.9; P < .001) and decreased word count (original, 193 vs simplified, 173; P < .001). Ninety-two percent (23 of 25) of simplified responses were considered clinically appropriate. All 25 (100%) simplified responses met criteria for adequate reading ease, compared with only two of 25 original responses (P < .001). Two of the 25 simplified responses (8%) met criteria for adequate readability. Conclusion ChatGPT simplified answers to common breast cancer screening and prevention questions by improving the readability by four grade levels, though the potential to produce incorrect information necessitates physician oversight when using this tool. Keywords: Mammography, Screening, Informatics, Breast, Education, Health Policy and Practice, Oncology, Technology Assessment Supplemental material is available for this article. © RSNA, 2023.

Assessment of coronary inflammation in antiretroviral treated people with HIV infection and active HIV/hepatitis C virus co-infection.

OBJECTIVE: People with HIV (PWH) and co-infected with hepatitis C virus (PWH + HCV) have increased risk of cardiovascular disease (CVD). Peri-coronary inflammation, measured by fat attenuation index (FAI) on coronary computed tomography angiography (CCTA), independently predicts cardiovascular risk in the general population but has not been studied in the PWH + HCV population. We tested whether peri-coronary inflammation is increased in PWH or PWH + HCV, and whether inflammation changes over time. DESIGN: Cross-sectional analysis to determine FAI differences among groups. Longitudinal analysis in PWH to assess changes in inflammation over time. METHODS: Age-matched and sex-matched seropositive groups (PWH and PWH + HCV) virologically suppressed on antiretroviral therapy, HCV viremic, and without prior CVD and matched controls underwent CCTA. Peri-coronary FAI was measured around the proximal right coronary artery (RCA) and left anterior descending artery (LAD). Follow-up CCTA was performed in 22 PWH after 20.6-27.4 months. RESULTS: A total of 101 participants (48 women) were studied (60 PWH, 19 PWH + HCV and 22 controls). In adjusted analyses, peri-coronary FAI did not differ between seropositive groups and controls. Low attenuation coronary plaque was significantly less common in seropositive groups compared with controls (LAD, P = 0.035; and RCA, P = 0.017, respectively). Peri-coronary FAI values significantly progressed between baseline and follow-up in PWH (RCA: P = 0.001, LAD: P = <0.001). CONCLUSION: PWH and PWH + HCV without history of CVD do not have significantly worse peri-coronary inflammation, assessed by FAI, compared with matched controls. However, peri-coronary inflammation in mono-infected PWH significantly increased over approximately 22 months. FAI measures may be an important imaging biomarker for tracking asymptomatic CVD progression in PWH.

Assessment of Myocarditis: Cardiac MR, PET/CT, or PET/MR?

PURPOSE OF REVIEW: Diagnosis of myocarditis is challenging given its variable clinical manifestations and non-specific laboratory findings. Cardiac magnetic resonance (MR) is currently the preferred imaging modality for the diagnosis of myocarditis. 18F-fluoro-deoxy-glucose (FDG) positron emission tomography/computed tomography (PET/CT), as a functional imaging tool, has a potential role in the assessment of myocarditis by detecting the underlying myocardial inflammatory activity. Data are accumulating that simultaneous cardiac PET/MR may have complementary and incremental values for the evaluation of myocarditis compared to PET/CT or cardiac MR alone. The article aims to summarize the findings in the literature and discuss future directions of cardiac PET/MR for myocarditis. RECENT FINDINGS: The Lake Louis Criteria (CLL) of cardiac MR is widely used for the diagnosis of myocarditis. It has an overall acceptable sensitivity of 67% and specificity of 91% for acute myocarditis but does not have the same accuracy for chronic myocarditis. FDG PET/CT is capable of assessing myocarditis by providing metabolic information of inflammation as increased myocardial FDG uptake. In addition to reduced radiation exposure, FDG PET performed on a hybrid PET/MR may detect more myocarditis than FDG PET/CT, because of the delayed PET acquisition time on PET/MR. Case-based observations and small clinical studies of FDG PET/MR have shown that FDG PET findings as abnormally increased myocardial uptake correlate well with the cardiac MR biomarkers. FDG PET findings may add complementary and incremental values to cardiac MR by improving the sensitivity of cardiac MR for mild or borderline myocarditis, and increasing specificity for chronic myocarditis. Preliminary data from retrospective and case-based observational studies have suggested the complementary and incremental values of simultaneous cardiac FDG PET/MR for evaluation of myocarditis, compared to PET/CT or MR alone. Well-designed studies are needed to confirm the findings and to assess the value of cardiac PET/MR for clinical management and more importantly patient's outcome in both acute and chronic myocarditis.

Quarterly Reporting of Computed Tomography Ordering History Reduces the Use of Imaging in an Emergency Department.

BACKGROUND: Computed tomography (CT) is a useful and necessary part of many emergency department (ED) assessments. However, the costs of imaging and the health risks associated with radiation exposure have sparked national efforts to reduce CT ordering in EDs. STUDY OBJECTIVE: We analyzed CT ordering habits prior to and following implementation of a feedback tool at a community hospital. METHODS: In this intervention study, we identified the CT-ordering habits of physicians and mid-level care providers (physician assistants and nurse practitioners) at baseline and after implementation of a system that sent quarterly feedback reports comparing their ordering habits with those of their peers. Variability in ordering and subgroup analyses by body region were included in these reports. RESULTS: We examined the records of 104,454 patients seen between October 1, 2013 and December 31, 2014. There were 5552 or 21.0% of patients seen during the baseline period that underwent CT imaging. We observed an absolute reduction in imaging of 2.3% (95% confidence interval 1.7-2.8%) after implementation, avoiding approximately $400,000 in costs, 22 days of scanning time, and radiation exposure equivalent to 33,000 chest films annually. These changes occurred across physicians and mid-level providers, regardless of the number years of practice or board certification. CONCLUSIONS: Implementation of a feedback mechanism reduced CT use by emergency medicine practitioners, with concomitant reductions in cost and radiation exposure. The change was similar across levels of medical care. Future studies will examine the effect of the feedback reporting system at other institutions in our hospital network.

Differences in quantitative assessment of myocardial scar and gray zone by LGE-CMR imaging using established gray zone protocols.

Late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) imaging is the gold standard for myocardial scar evaluation. Heterogeneous areas of scar ('gray zone'), may serve as arrhythmogenic substrate. Various gray zone protocols have been correlated to clinical outcomes and ventricular tachycardia channels. This study assessed the quantitative differences in gray zone and scar core sizes as defined by previously validated signal intensity (SI) threshold algorithms. High quality LGE-CMR images performed in 41 cardiomyopathy patients [ischemic (33) or non-ischemic (8)] were analyzed using previously validated SI threshold methods [Full Width at Half Maximum (FWHM), n-standard deviation (NSD) and modified-FWHM]. Myocardial scar was defined as scar core and gray zone using SI thresholds based on these methods. Scar core, gray zone and total scar sizes were then computed and compared among these models. The median gray zone mass was 2-3 times larger with FWHM (15 g, IQR: 8-26 g) compared to NSD or modified-FWHM (5 g, IQR: 3-9 g; and 8 g. IQR: 6-12 g respectively, p < 0.001). Conversely, infarct core mass was 2.3 times larger with NSD (30 g, IQR: 17-53 g) versus FWHM and modified-FWHM (13 g, IQR: 7-23 g, p < 0.001). The gray zone extent (percentage of total scar that was gray zone) also varied significantly among the three methods, 51 % (IQR: 42-61 %), 17 % (IQR: 11-21 %) versus 38 % (IQR: 33-43 %) for FWHM, NSD and modified-FWHM respectively (p < 0.001). Considerable variability exists among the current methods for MRI defined gray zone and scar core. Infarct core and total myocardial scar mass also differ using these methods. Further evaluation of the most accurate quantification method is needed.

Safety of computed tomography in patients with cardiac rhythm management devices: assessment of the U.S. Food and Drug Administration advisory in clinical practice.

OBJECTIVES: To assess the safety of computed tomography (CT) imaging in patients with cardiac rhythm management (CRM) devices, which was subject to an advisory from the U.S. Food and Drug Administration (FDA) in 2008. BACKGROUND: The FDA warned about potential interference of CT imaging with CRM devices and made recommendations for clinical practice despite only limited evidence. METHODS: All 516 CT scans that involved direct radiation exposure of CRM devices (332 defibrillators, 184 pacemakers) at 2 large-volume centers between July 2000 and May 2010 were included. The primary outcome was a composite endpoint of death, bradycardia or tachycardia requiring termination of the scan or an immediate intervention, unplanned hospital admission, reprogramming of the device, inappropriate defibrillator shocks, or device replacement/revision thought to be due to CT imaging. Significant changes in device parameters were sought as a secondary outcome (control group 4:1 ratio). RESULTS: The main finding was that none of the CTs were associated with the primary outcome. With serial device interrogations, there were no differences in changes in battery voltage or lead parameters between devices exposed to radiation and their controls. Potentially significant changes in device parameters were observed in a small group of devices (both the CT group and control group), but no definitive link to CT was confirmed, and there were no associated clinical consequences. CONCLUSIONS: The findings suggest that the presence of CRM devices should not delay or result in cancellation of clinically indicated CT imaging procedures, and provide evidence that would be helpful when the FDA advisory is re-evaluated.

Quantitative assessment of percentage of lung parenchyma visualized on cardiac computed tomographic angiography.

RATIONALE AND OBJECTIVES: The purpose of the study was to quantitatively assess the percentage of total lung parenchyma visualized on cardiac computed tomographic angiography (CTA) using standard and tight-coned fields of view (FOVs). MATERIALS AND METHODS: The authors evaluated lung volumes in 43 electrocardiogram-gated cardiac CTAs performed as part of triple rule-out/chest pain protocol CTAs over a 9-month period. Using a commercially available software package, a quantitative tissue differentiation analysis was performed using a threshold of -750 Hounsfield units to segment air in the lungs. Using each triple rule-out data set as a starting point, measurements of lung volume were performed with 2 cardiac CTA FOV scenarios, obtained by excluding the periphery of the triple rule-out volume: (1) standard cardiac CTA FOV typically used and recommended by the manufacturer and (2) tight cardiac CTA FOV maximally coned to the heart. For each scenario, the volume of the lung within the restricted FOV was compared with the overall volume of the lungs derived from the triple rule-out study, expressed as a percentage. RESULTS: On the standard cardiac CTA FOV typically used at our institution, a mean of 58% of the lung parenchyma is included with wide variability (range, 26%-86%). On the severely limited FOV, a mean of 14% (range, 7.5%-22%) of the lung parenchyma is included. CONCLUSIONS: The percentage of lung parenchyma included in a standard FOV is considerable, although this can be mitigated by using a tight FOV, with potential exclusion of part of the cardiac anatomy. Interpreters of cardiac CTA images should have adequate training and skill in evaluating structures outside the heart.

Computed tomography assessment of valvular morphology, function, and disease.

Recent advancement in computed tomography angiography (CTA) has enabled the noninvasive delineation of cardiac valves using this method. Although echocardiography is the current standard, CTA is a valuable complementary imaging method to evaluate valvular morphology and function. In addition, CTA may contribute to the assessment of both congenital and acquired valvular heart disease, infectious endocarditis, and postsurgical complications of valve replacement.