Background The complex medical terminology of radiology reports may cause confusion or anxiety for patients, especially given increased access to electronic health records. Large language models (LLMs) can potentially simplify radiology report readability. Purpose To compare the performance of four publicly available LLMs (ChatGPT-3.5 and ChatGPT-4, Bard [now known as Gemini], and Bing) in producing simplified radiology report impressions. Materials and Methods In this retrospective comparative analysis of the four LLMs (accessed July 23 to July 26, 2023), the Medical Information Mart for Intensive Care (MIMIC)-IV database was used to gather 750 anonymized radiology report impressions covering a range of imaging modalities (MRI, CT, US, radiography, mammography) and anatomic regions. Three distinct prompts were employed to assess the LLMs' ability to simplify report impressions. The first prompt (prompt 1) was "Simplify this radiology report." The second prompt (prompt 2) was "I am a patient. Simplify this radiology report." The last prompt (prompt 3) was "Simplify this radiology report at the 7th grade level." Each prompt was followed by the radiology report impression and was queried once. The primary outcome was simplification as assessed by readability score. Readability was assessed using the average of four established readability indexes. The nonparametric Wilcoxon signed-rank test was applied to compare reading grade levels across LLM output. Results All four LLMs simplified radiology report impressions across all prompts tested (P < .001). Within prompts, differences were found between LLMs. Providing the context of being a patient or requesting simplification at the seventh-grade level reduced the reading grade level of output for all models and prompts (except prompt 1 to prompt 2 for ChatGPT-4) (P < .001). Conclusion Although the success of each LLM varied depending on the specific prompt wording, all four models simplified radiology report impressions across all modalities and prompts tested. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Rahsepar in this issue.

The COVID-19 pandemic will have a profound impact on Radiology practices across the country. Policy measures adopted to slow the transmission of disease are decreasing the demand for imaging indepe...

Identifying reasons for the low proportion of female and underrepresented minority radiology residency applicants, despite a highly diverse pool of medical students, would be key to increasing thei... Background There have been growing efforts nationally and institutionally toward diversity in radiology. Purpose To analyze sex and racial and ethnic diversity over time (2010–2019) for the various...

Purpose Managerial sciences are playing an increasingly prominent role in the organization and delivery of health care. Despite popular media reports that a rising number of physicians are acquiring a background in this discipline through MD/MBA (medical and master of business administration) programs, no recent study has verified this. This study measured changes in the number and nature of the affiliations between management and medicine in the form of MD/MBA programs in the United States. Method Surveys of admission officers of 125 U.S. allopathic medical schools and of the overseers of each joint MD/MBA degree program were administered in May–October 2001. Main outcome measures included program growth, curriculum and degree requirements, application and admission requirements, and program leadership and organization. Results The number of MD/MBA programs grew from six to 33 between 1993 and 2001, and 17 more medical schools were considering establishing the joint-degree program. Ten, 15, and 20 programs produced 27, 42, and 61 graduates in 1999, 2000, and 2001, respectively, and over 100 students were expected to graduate per year when all 33 programs matured. Program structures and oversight indicate a spectrum of philosophies regarding the appropriate level of integration of the two degrees. MD/MBA programs apparently attempt to complement medical education with management education rather than the converse. Conclusions The growth in the numbers of MD/MBA programs and participants indicates rising cooperation between medical and business schools and increasing interest in management education early in the careers of graduating physicians.

Follicular lymphoma (FL) is traditionally considered treatable but incurable. In March 2021, the US Food and Drug Administration approved the use of chimeric antigen receptor (CAR) T-cell therapy in patients with relapsed or refractory (R/R) FL after ≥2 lines of therapy. Priced at $373 000, CAR T-cell therapy is potentially curative, and its cost-effectiveness compared with other modern R/R FL treatment strategies is unknown. We developed a Markov model to assess the cost-effectiveness of third-line CAR T-cell vs standard of care (SOC) therapies in adults with R/R FL. We estimated progression rates for patients receiving CAR T-cell and SOC therapies from the ZUMA-5 trial and the LEO CReWE study, respectively. We calculated costs, discounted life years, quality-adjusted life years (QALYs), and the incremental cost-effectiveness ratio (ICER) of CAR T-cell vs SOC therapies with a willingness-to-pay threshold of $150 000 per QALY. Our analysis was conducted from a US payer’s perspective over a lifetime horizon. In our base-case model, the cost of the CAR T-cell strategy was $731 682 compared with $458 490 for SOC therapies. However, CAR T-cell therapy was associated with incremental clinical benefit of 1.50 QALYs, resulting in an ICER of $182 127 per QALY. Our model was most sensitive to the utilities associated with CAR T-cell therapy remission and third-line SOC therapies and to the total upfront CAR T-cell therapy cost. Under current pricing, CAR T-cell therapy is unlikely to be cost-effective in unselected patients with FL in the third-line setting. Both randomized clinical trials and longer term clinical follow-up can help clarify the benefits of CAR T-cell therapy and optimal sequencing in patients with FL.