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.

Use of ChatGPT, GPT-4, and Bard to Improve Readability of ChatGPT's Answers to Common Questions About Lung Cancer and Lung Cancer Screening.

ChatGPT's responses to questions about lung cancer and LCS, although deemed clinically appropriate by cardiothoracic radiologists, were difficult to read. Simplified responses from three LLMs (ChatGPT, GPT-4, and Bard) had improved reading ease and readability (in terms of U.S. grade levels). However, some simplified responses were no longer clinically appropriate.

Global Radiology Training Prevalence Among Radiology Residency Programs.

OBJECTIVE: Global Radiology aims to enhance access to medical imaging services and education, worldwide. To date, few reports have evaluated Global Radiology Training (GRT) in radiology residency programs. Here, we examined how radiology residency programs perceive and incorporate GRT into their curriculum, and how this information is promoted online. METHODS: Two methods were used to examine the current state of GRT. First, radiology residency program directors (identified via the Association of Program Directors in Radiology) were surveyed on topics including: Electives, institutional partnerships, resident and faculty involvement, inquiry by prospective residents, and barriers to implementation. Second, radiology residency program websites (n = 193) were examined for existing GRT on the programs' publicly available webpages. RESULTS: There were 62 survey responses (response rate of 19%). Thirty-eight percent (24/62) of residency programs offered a Global Radiology elective to their residents within the past academic year and 27% (17/62) of programs have active affiliations with medical institutions outside of the United States. Eighty-four percent of program directors (52/62) received questions from residency applicants regarding opportunities to participate in Global Radiology. Furthermore, only 13% (26/193) of all radiology residency programs listed at least one GRT elective on their webpage. DISCUSSION: GRT in radiology residency is more widely available than previously reported and has been underrepresented on residency program websites. In the present survey, the majority of radiology residency program directors reported that radiology is an important component of Global Health, one-third of whom have already incorporated the subject into their curriculum. However, most common barriers to GRT include, perceived lack of time in the curriculum and lack of faculty interest. The high prevalence of inquiry from residency program applicants about GRT suggests that it may be a notable factor for applicants during the ranking process. Programs build up GRT may choose to share related information seeking to may choose to emphasize work in Global Radiology on their program webpages.

Mutations in genes for the F420 biosynthetic pathway and a nitroreductase enzyme are the primary resistance determinants in spontaneous in vitro-selected PA-824-resistant mutants of Mycobacterium tuberculosis.

Alleviating the burden of tuberculosis (TB) requires an understanding of the genetic basis that determines the emergence of drug-resistant mutants. PA-824 (pretomanid) is a bicyclic nitroimidazole class compound presently undergoing the phase III STAND clinical trial, despite lacking identifiable genetic markers for drug-specific resistant Mycobacterium tuberculosis. In the present study, we aimed to characterize the genetic polymorphisms of spontaneously generated PA-824-resistant mutant strains by surveying drug metabolism genes for potential mutations. Of the 183 independently selected PA-824-resistant M. tuberculosis mutants, 83% harbored a single mutation in one of five nonessential genes associated with either PA-824 prodrug activation (ddn, 29%; fgd1, 7%) or the tangential F420 biosynthetic pathway (fbiA, 19%; fbiB, 2%; fbiC, 26%). Crystal structure analysis indicated that identified mutations were specifically located within the protein catalytic domain that would hinder the activity of the enzymes required for prodrug activation. This systematic analysis conducted of genotypes resistant to PA-824 may contribute to future efforts in monitoring clinical strain susceptibility with this new drug therapy.