Biagio Merlino

Background/Objectives: Radiology often presents communication challenges due to its technical complexity, particularly for patients, trainees, and non-specialist clinicians. This study aims to evaluate the effectiveness of RadioBot, an AI-powered chatbot developed on the Botpress platform, in enhancing radiological communication through natural language processing (NLP). Methods: RadioBot was designed to provide context-sensitive responses based on guidelines from the American College of Radiology (ACR) and the Radiological Society of North America (RSNA). It addresses queries related to imaging indications, contraindications, preparation, and post-procedural care. A structured evaluation was conducted with twelve participants—patients, residents, and radiologists—who assessed the chatbot using a standardized quality and satisfaction scale. Results: The chatbot received high satisfaction scores, particularly from patients (mean = 4.425) and residents (mean = 4.250), while radiologists provided more critical feedback (mean = 3.775). Users appreciated the system’s clarity, accessibility, and its role in reducing informational bottlenecks. The perceived usefulness of the chatbot inversely correlated with the user’s level of expertise, serving as an educational tool for novices and a time-saving reference for experts. Conclusions: RadioBot demonstrates strong potential in improving radiological communication and supporting clinical workflows, especially with patients where it plays an important role in personalized medicine by framing radiology data within each individual’s cognitive and emotional context, which improves understanding and reduces associated diagnostic anxiety. Despite limitations such as occasional contextual incoherence and limited multimodal capabilities, the system effectively disseminates radiological knowledge. Future developments should focus on enhancing personalization based on user specialization and exploring alternative platforms to optimize performance and user experience.

Objectives: To develop and internally validate a pre-treatment score for the safe selection of the best candidates for the transradial approach when performing liver cancer intra-arterial procedures. Methods: One hundred and twenty-two patients undergoing hepatic endovascular treatments via radial access between January and December 2022 were retrospectively selected to develop a prediction model. Pre-procedural imaging data were analyzed, and variables were selected to develop the RAD-access score. Intra-procedural data were analyzed to assess effective procedural complexity (ePC). The relationship between ePC and pre-procedural variables was statistically tested, and cutoff points were defined. Results: A final score (RAD-access) was created and prospectively validated on 139 patients enrolled between June and September 2023. Aortic arch diameter and angulation, left subclavian artery angulation, suprarenal abdominal aorta diameter, celiac trunk take-off angle, and radial artery diameter were the significant variables used to build the score. In the validation cohort, based on the pre-treatment RAD-access score, 69 patients underwent a transradial approach, with a significantly lower ePC rate obtained (78.2% easy, 20.3% intermediate, 1.5% complex). No major adverse events occurred. Conclusions: Pre-treatment RAD-access score provides a good prediction for the procedural complexity of the transradial approach in patients undergoing liver cancer intra-arterial treatments, identifying the best candidates for an easy and safe transradial procedure.

Dir Journal Diagnostic and Interventional Radiology