Background/Objectives: Aortic-arch calcification (AAC) is a robust predictor of cardiovascular events often overlooked on routine chest radiographs (CXR). This systematic review aimed to evaluate the diagnostic accuracy of artificial intelligence (AI) models for detecting AAC on CXR and assess their potential for clinical implementation. Methods: The review followed PRISMA 2020 guidelines (PROSPERO: CRD420251208627). A search of Embase, PubMed, Scopus, and Web of Science was conducted (Jan 2020–Oct 2025) for studies evaluating AI models detecting AAC in adults. Bias was assessed using QUADAS-2. Due to methodological heterogeneity, a narrative synthesis was performed instead of a meta-analysis. Results: Out of 115 records, three retrospective studies (2022–2024) utilizing CNNs across ~2.7 million images were included. Models demonstrated high diagnostic discrimination (AUROC 0.81–0.99), though performance estimates were often attenuated in external cohorts. Pronounced sensitivity–specificity trade-offs occurred: one model achieved 95.9% recall, while another exhibited near-perfect specificity (0.99) despite markedly low sensitivity (0.22). Although the risk of bias was predominantly low, the overall GRADE certainty remained low due to methodological heterogeneity and the absence of cross-sectional imaging reference standards. Conclusions: Deep learning-based models reliably detect AAC on routine CXR, offering a scalable tool for opportunistic cardiovascular risk stratification. However, significant heterogeneity in model architectures and validation strategies currently limits broad comparability. Future research requires standardized annotation protocols and external validation to ensure clinical generalizability.

Background: Muscle and tendon injuries of the lower limb are common in athletes and often require prolonged rehabilitation before returning to sport. Shear-wave elastography (SWE) enables quantitative assessment of tissue mechanical properties and may provide information beyond conventional morphological imaging.Aim: Sports activity resumption after lower-limb muscle and tendon injuries is a key focus of this narrative review, which summarizes current evidence on SWE in diagnosis, monitoring of healing and rehabilitation, and assessment of readiness to return to sport.Material and methods: Studies evaluating SWE in lower-limb muscle and tendon injuries were reviewed.Results: Studies demonstrate measurable SWE changes in hamstring and calf muscle injuries, Achilles tendon pathology and rupture, and patellar tendinopathy. However, the direction and magnitude of stiffness changes vary according to tissue type, injury stage, loading conditions, training status, acquisition protocol, and ultrasound system. Serial SWE measurements may therefore be more informative than isolated absolute values, particularly when performed under standardized conditions and interpreted alongside clinical and functional recovery.Conclusions: At present, SWE should be considered a complementary tool rather than a stand-alone diagnostic or return-to-sport criterion. Universal reference ranges and validated cutoff values are lacking, and the relationship between SWE normalization, re-injury risk, and readiness to return to sport remains uncertain. Further prospective studies using standardized protocols and clinically relevant outcomes are needed.

Introduction: Recent advancements in artificial intelligence (AI) language models, such as ChatGPT, have sparked interest in their application across various domains, including medicine. Aim of the research: This study evaluates the performance of the ChatGPT-o1-preview model on the Polish Specialist Examination (PES) in cardiology. Material and methods: A total of 120 single-choice questions from the Spring 2023 PES cardiology exam were analysed. Each question was submitted to the model five times in separate sessions using a standardised prompt. We assessed the accuracy of the responses and the model’s consistency by introducing a “Confidence Index of Language Model” (defined as the ratio of the frequency of the most commonly selected answer to the total number of sessions). Questions were classified according to Bloom’s Taxonomy, and statistical relationships between model performance and question characteristics were analysed. Results: ChatGPT-o1-preview provided 97 correct answers (80.83%), well above the passing threshold of 60%. Statistically significant correlations were observed between answer accuracy and difficulty indices (both the Human Difficulty Index and the Confidence Index of Language Model). Questions that were more difficult for human examinees also proved more challenging for the model. No significant differences in model performance were found based on question type (clinical versus other) or content (comprehension and critical thinking versus memory). Conclusions: ChatGPT-o1-preview successfully completed a specialised cardiology exam. It is essential to conduct further, more extensive research based on a significantly larger and more diverse set of questions. Only then will it be possible to reliably determine the true potential and limitations of AI in medical applications.

Purpose: The aim of this study was to evaluate the performance of the ChatGPT-o1-preview language model in solving the Polish National Specialization Exam (PES) in radiology and imaging diagnostics and compare its results with previous versions of the model. Material and methods: The aim of this study was to evaluate the performance of the ChatGPT-o1-preview language model in solving the Polish National Specialization Exam (PES) in radiology and imaging diagnostics and compare its results with previous versions of the model.A set of 119 valid radiology exam questions from Spring 2023 was analyzed. Each question was classified by type, subtype, and clinical relevance. ChatGPT answered each question five times using a standardized prompt with a 5-point confidence scale. Performance was assessed using accuracy and declared and calculated difficulty indices. Statistical analysis was performed in Python with a significance level of p < 0.05, and results were compared with a previous model version. Results: The model achieved a score of 93.33% correct answers, comparable to the average physician score of 94.86%. ChatGPT-o1-preview showed exceptional accuracy in “memory” questions, with over 96% correct answers. This result, significantly higher than that of the older ChatGPT-3.5 model (52%), demonstrates progress in artificial intelligence (AI) capabilities. The model also exhibited higher confidence in its responses, indicating better adaptation to medical exams. Conclusions: Despite its high accuracy, the study was based on a relatively small set of questions, which limits the ability to fully assess the model’s effectiveness. The results indicate the potential of AI as a tool to support clinical work, but further, more extensive research is necessary to evaluate its applicability and reliability in the medical environment.