Background: The aim of this study was to describe the proficiency of ChatGPT (GPT-4) on certification style exams from the Canadian Association of Medical Radiation Technologists (CAMRT), and describe its performance across multiple exam attempts.
Methods: ChatGPT was prompted with questions from CAMRT practice exams in the disciplines of radiological technology, magnetic resonance (MRI), nuclear medicine and radiation therapy (87-98 questions each). ChatGPT attempted each exam five times. Exam performance was evaluated using descriptive statistics, stratified by discipline and question type (knowledge, application, critical thinking). Light's Kappa was used to assess agreement in answers across attempts.
Results: Using a passing grade of 65 %, ChatGPT passed the radiological technology exam only once (20 %), MRI all five times (100 %), nuclear medicine three times (60 %), and radiation therapy all five times (100 %). ChatGPT's performance was best on knowledge questions across all disciplines except radiation therapy. It performed worst on critical thinking questions. Agreement in ChatGPT's responses across attempts was substantial within the disciplines of radiological technology, MRI, and nuclear medicine, and almost perfect for radiation therapy.
Conclusion: ChatGPT (GPT-4) was able to pass certification style exams for radiation technologists and therapists, but its performance varied between disciplines. The algorithm demonstrated substantial to almost perfect agreement in the responses it provided across multiple exam attempts. Future research evaluating ChatGPT's performance on standardized tests should consider using repeated measures.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.jmir.2024.04.019 | DOI Listing |
Bone Rep
March 2025
Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, United States of America.
High resolution peripheral quantitative computed tomography (HRpQCT) offers detailed bone geometry and microarchitecture assessment, including cortical porosity, but assessing chronic kidney disease (CKD) bone images remains challenging. This proof-of-concept study merges deep learning and machine learning to 1) improve automatic segmentation, particularly in cases with severe cortical porosity and trabeculated endosteal surfaces, and 2) maximize image information using machine learning feature extraction to classify CKD-related skeletal abnormalities, surpassing conventional DXA and CT measures. We included 30 individuals (20 non-CKD, 10 stage 3 to 5D CKD) who underwent HRpQCT of the distal and diaphyseal radius and tibia and contributed data to develop and validate four different AI models for each anatomical site.
View Article and Find Full Text PDFInorg Chem
January 2025
School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, Georgia 30332-0400, United States.
While several ligand systems support uranium across a range of oxidation states, spanning more than two oxidation states in a conserved coordination geometry is uncommon among structurally authenticated complexes. Imidophosphorane ligands significantly stabilize high-valent lanthanide and actinide complexes. Here, we report a series of homoleptic uranium imidophosphorane complexes, spanning the +4, +5 and +6 oxidation states in a four-coordinate pseudotetrahedral ligand field.
View Article and Find Full Text PDFMed Phys
January 2025
Department of Chemistry, Faculty of Science, Hokkaido University, Sapporo, Hokkaido, Japan.
Background: The use of iodinated contrast-enhancing agents in computed tomography (CT) improves the visualization of relevant structures for radiotherapy treatment planning (RTP). However, it can lead to dose calculation errors by incorrectly converting a CT number to electron density.
Purpose: This study aimed to propose an algorithm for deriving virtual non-contrast (VNC) electron density from dual-energy CT (DECT) data.
Nihon Hoshasen Gijutsu Gakkai Zasshi
January 2025
Department of Risk Analysis and Biodosimetry, Institute of Radiation Emergency Medicine, Hirosaki University.
Purpose: Hereditary breast and ovarian cancers (HBOC) carry a high risk of breast cancer, and detailed screening with contrast-enhanced breast MRI (breast MRI surveillance) is recommended. With the increase in the number of individuals diagnosed with HBOC, the demand for breast MRI surveillance is also rising. However, the current system is inadequate, with factors such as lack of knowledge and indifference among healthcare professionals, and insufficient understanding of breast MRI surveillance being cited.
View Article and Find Full Text PDFBMC Oral Health
January 2025
State Key Laboratory of Oral Diseases & National Clinical Research Center for Oral Diseases & Department of Implant Dentistry, West China Hospital of Stomatology, Sichuan University, Chengdu, 610041, China.
Purpose: This study aimed to evaluate the osteogenic performance of allograft particulate bone and cortical bone blocks combined with xenograft under bovine pericardium membranes, for treating different degrees of labial bone defects in the aesthetic zone.
Materials And Methods: Twenty-four patients with bone defects were divided into two groups based on defect severity (Terheyden 1/4 and 2/4 groups). The Terheyden 1/4 group received granular bone grafts alone, while the Terheyden 2/4 group received cortical bone blocks combined with granular bone grafts.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!