Search

Objective: Radiology reporting is an essential component of clinical diagnosis and decision-making. With the advent of advanced artificial intelligence (AI) models like GPT-4 (Generative Pre-trained Transformer 4), there is growing interest in evaluating their potential for optimizing or generating radiology reports. This study aimed to compare the quality and content of radiologist-generated and GPT-4 AI-generated radiology reports. Methods: A comparative study design was employed in the study, where a total of 100 anonymized radiology reports were randomly selected and analyzed. Each report was processed by GPT-4, resulting in the generation of a corresponding AI-generated report. Quantitative and qualitative analysis techniques were utilized to assess similarities and differences between the two sets of reports. Results: The AI-generated reports showed comparable quality to radiologist-generated reports in most categories. Significant differences were observed in clarity (p = 0.027), ease of understanding (p = 0.023), and structure (p = 0.050), favoring the AI-generated reports. AI-generated reports were more concise, with 34.53 fewer words and 174.22 fewer characters on average, but had greater variability in sentence length. Content similarity was high, with an average Cosine Similarity of 0.85, Sequence Matcher Similarity of 0.52, BLEU Score of 0.5008, and BERTScore F1 of 0.8775. Conclusion: The results of this proof-of-concept study suggest that GPT-4 can be a reliable tool for generating standardized radiology reports, offering potential benefits such as improved efficiency, better communication, and simplified data extraction and analysis. However, limitations and ethical implications must be addressed to ensure the safe and effective implementation of this technology in clinical practice. Clinical relevance statement: The findings of this study suggest that GPT-4 (Generative Pre-trained Transformer 4), an advanced AI model, has the potential to significantly contribute to the standardization and optimization of radiology reporting, offering improved efficiency and communication in clinical practice. Key Points: • Large language model–generated radiology reports exhibited high content similarity and moderate structural resemblance to radiologist-generated reports. • Performance metrics highlighted the strong matching of word selection and order, as well as high semantic similarity between AI and radiologist-generated reports. • Large language model demonstrated potential for generating standardized radiology reports, improving efficiency and communication in clinical settings. [ABSTRACT FROM AUTHOR]

Introduction: Dysfunction or malpositioning of the aortic valve prosthesis is an uncommon but a known complication. Deployment of a second transcatheter aortic valve within previously implanted transcatheter aortic valve prosthesis is referred to as TAV-in-TAV. This procedure is often performed to treat aortic regurgitation occurring shortly after transcatheter aortic valve replacement (TAVR). Objective: The purpose of our study was to see if TAVR approach (transfemoral vs. transapical) impacted the incidence of periprocedural TAVin- TAV. Methods: A retrospective record review of consecutive patients was performed at a single center. The incidence of periprocedural TAVin- TAV was recorded and compared between patients' undergoing TAVR via transfemoral and transapical approach. Periprocedural complications and imaging findings were also recorded. Results: Out of 489 patients undergoing TAVR, only 10 patients (2%) required urgent periprocedural TAV-in-TAV, 5 patients each from the transfemoral and transapical groups (1.6% vs. 2.7%, respectively, p = 0.51). TAV-in-TAV deployment was technically successful in 8 patients (80%) and unsuccessful in 2 patients (20%; 1 transfemoral and 1 transapical), who required conversion to openheart surgery. The primary cause of TAVR failure requiring periprocedural TAV-in-TAV in both transfemoral and transapical patients was prosthesis malposition, frequently complicated by moderate to severe paravalvular aortic insufficiency. Statistically, there was no difference between the periprocedural morbidity and 30- day mortality for patients undergoing TAV-in-TAV via transfemoral versus transapical approach. Conclusion: Periprocedural TAV-in-TAV was uncommon in our cohort, primarily resulting from prosthesis malposition causing paravalvular aortic insufficiency. We found no difference in the number of patients requiring TAV-in-TAV in relation to TAVR approach. [ABSTRACT FROM AUTHOR]