Dong Hyun Yang

Background and Objectives: Routine preoperative chest radiography (CXR) has limited value for perioperative risk prediction when interpreted qualitatively. The Automated Diagnosis of Cardiovascular abnormalities (ADC) model enables automated quantification of cardiomediastinal vascular border (CVB) parameters on CXR. This study evaluated the associations of AI-derived CVB metrics with postoperative major adverse cardiovascular events (MACE) and their incremental predictive value beyond clinical factors. Materials and Methods: This retrospective cohort study included patients who underwent surgery under general anesthesia at a tertiary academic center. The ADC model quantified CVB parameters as raw measurements and age- and sex-adjusted z-scores. The primary outcome was postoperative in-hospital MACE. Associations were assessed using multivariable logistic regression, and discrimination was evaluated using receiver operating characteristic curve analysis. Incremental predictive performance was assessed by adding selected CVB parameters to a clinical reference model. Results: Among 101,531 patients, MACE occurred in 1655 patients (1.6%). All ADC-derived CVB parameters remained independently associated with MACE after multivariable adjustment. For cardiothoracic ratio, the adjusted OR was 1.64 (95% CI, 1.58–1.70; p < 0.001), with an AUC of 0.789. For the composite CVB z-score, the adjusted OR was 1.88 (95% CI, 1.79–1.97; p < 0.001), with an AUC of 0.762. Adding either the CT ratio or composite CVB z-score to the clinical reference model increased the AUC from 0.894 to 0.906 (p < 0.001 for both), with similar improvement in temporal validation. Conclusions: AI-derived CVB parameters from preoperative CXR were independently associated with postoperative in-hospital MACE and provided modest incremental predictive information beyond routinely available clinical factors. Automated CVB analysis may provide additional cardiovascular risk information from a routinely obtained preoperative CXR without additional imaging or patient burden, although further external validation is required to establish its clinical utility.

Background: Hospitals worldwide need to upskill their workforce in advanced AI technologies; yet, published guidance on how to design and deliver such training, particularly in agent-level tools like retrieval-augmented generation (RAG) and the model context protocol (MCP), remains virtually absent. Objective: To describe the design, implementation, and lessons learned from an 8-week, 56-hour intensive generative AI training program for a multidisciplinary hospital workforce, drawing on both quantitative outcome data and participants’ own reflections on their learning experience. Methods: The program was delivered on-site at Asan Medical Center with simultaneous online broadcast to 2 regional affiliate hospitals. The curriculum was built around the premise that MCP and AI agents would become the foundation of health care AI use, allocating 37% (11.5/31 hours) of on-site instructional time to MCP, and 71% (22/31 hours) to hands-on practice. Participants progressed from foundational concepts through RAG and MCP to team-based capstone projects, supported by funded AI tool subscriptions, a dedicated internal cloud platform, and 3‐6 hours of weekly mentoring per team. A pre-post survey (pre: n=83; post: n=64) evaluated outcomes across Kirkpatrick levels 1‐3, complemented by thematic analysis of open-ended reflections on self-perceived growth. Results: The technologies that received the greatest curricular investment were associated with the largest self-efficacy differences (MCP: d =1.57; overall effect: r =.574), and participants most frequently cited MCP and RAG when describing how abstract concepts “became concrete and actionable.” Non-IT professionals, clinicians, health information managers, researchers, and administrative staff showed consistently larger gains than IT specialists; several reported coding for the first time through vibe coding, challenging the assumption that advanced AI training requires technical backgrounds. Despite significant overall gains, a knowledge-practice gap persisted: job-specific competency remained below the scale midpoint, though participants spontaneously reported generating workplace application ideas. Curriculum pacing was rated lowest despite high overall satisfaction (4.03/5), signaling that even 56 hours may progress too quickly for mixed-expertise cohorts. Capstone projects with dedicated mentoring received the highest satisfaction ratings; 11 of 12 teams presented functional prototypes, and one has since entered active pilot use in clinical departments ahead of planned hospital-wide deployment. Conclusions: To our knowledge, this is the first program to teach 4 agent-level generative AI technologies, MCP, RAG, LangGraph orchestration, and AI agent design, to both IT and non-IT hospital staff. This program suggests that transforming a multidisciplinary hospital workforce into AI-capable professionals is achievable through intensive, hands-on training centered on agent-level technologies, and that capstone projects with dedicated mentoring can serve as a pathway from classroom learning toward institutional AI adoption. The knowledge-practice gap highlights the need for posttraining support structures to translate self-efficacy gains into sustained workplace practice.

BACKGROUND Hospitals worldwide need to upskill their workforce in advanced AI technologies, yet published guidance on how to design and deliver such training—particularly in agent-level tools like Retrieval-Augmented Generation (RAG) and the Model Context Protocol (MCP)—remains virtually absent. OBJECTIVE To describe the design, implementation, and lessons learned from an 8-week, 56-hour intensive generative AI training program for multidisciplinary healthcare professionals, drawing on both quantitative outcome data and participants’ own reflections on their learning experience. METHODS The program was delivered on-site at Asan Medical Center with simultaneous online broadcast to two regional affiliate hospitals. The curriculum was built around the premise that MCP and AI agents would become the foundation of healthcare AI utilization, allocating 37% of instructional time to MCP and 71% overall to hands-on practice. Participants progressed from foundational concepts through RAG and MCP to team-based capstone projects, supported by funded AI tool subscriptions, a dedicated internal cloud platform, and 3–6 hours of weekly mentoring per team. A pre-post survey (pre: n = 83; post: n = 64) evaluated outcomes across Kirkpatrick Levels 1–3, complemented by thematic analysis of open-ended reflections on self-perceived growth. RESULTS The technologies that received the greatest curricular investment produced the largest self-efficacy gains (MCP: d = 1.57; overall effect: r = .574), and participants most frequently cited MCP and RAG when describing how abstract concepts “became concrete and actionable.” Non-IT professionals—clinicians, health information managers, and researchers—showed consistently larger gains than IT specialists; several reported coding for the first time through vibe coding, challenging the assumption that advanced AI training requires technical backgrounds. Despite significant overall gains, a knowledge-practice gap persisted: job-specific competency remained below the scale midpoint, though participants spontaneously reported generating workplace application ideas. Curriculum pacing was rated lowest despite high overall satisfaction (4.03/5.0), signaling that even 56 hours may progress too quickly for mixed-expertise cohorts. Capstone projects with dedicated mentoring received the highest satisfaction ratings; 11 of 12 teams presented functional prototypes, one received the Minister of Health and Welfare Award, and two have since been deployed in hospital operations. CONCLUSIONS This program demonstrates that transforming a multidisciplinary hospital workforce into AI-capable professionals is feasible through intensive, hands-on training centered on agent-level technologies, and that capstone projects with dedicated mentoring can serve as a pipeline from classroom learning to institutional AI adoption. The knowledge-practice gap highlights the need for post-training support structures to translate self-efficacy gains into sustained workplace practice.

Background: The evolution of left ventricular (LV) intracardiac flow characteristics following myocardial infarction (MI), and their relationship to LV remodeling, remains incompletely understood, particularly from longitudinal in vivo observations with dense temporal sampling. Methods: Two porcine models with experimentally induced myocardial infarction at the left anterior descending artery were longitudinally followed from baseline to 11 weeks, with 10 cardiac MRI sessions per animal. Cardiac MRI assessed myocardial tissue characteristics (LGE, native T1/T2 mapping, and extracellular volume), global left ventricular function, and strain. Four-dimensional flow MRI was used to characterize intracardiac flow features, including E/A ratio, vorticity, and diastolic helical vortex structures. Longitudinal changes were examined descriptively within each animal. Overall temporal trends were summarized using the Theil–Sen estimator, with uncertainty assessed by residual bootstrap-derived 95% confidence intervals. Results: Both animals demonstrated overall remodeling patterns consistent with post-infarction progression, including temporal reductions in LGE with secondary changes during the chronic phase, thinning of the infarcted myocardial wall, and increases in indexed end-diastolic and end-systolic volumes. Native T1 relaxation time increased over time in one animal and showed a similar directional pattern in the other. Despite these structural and tissue-level changes, regional intracardiac vorticity remained relatively preserved throughout the study period. In contrast, the angle of the helical filling vortex between the anatomical LV and the vortex core centerlines was observed to increase in both animals. Conclusion: In this exploratory longitudinal study, both animals demonstrated similar temporal patterns of LV remodeling after MI, despite differences in the absolute magnitude of the measured parameters. In addition, our findings suggest that the angle of the helical filling vortex may have potential as a remodeling marker, which warrants validation in larger cohorts.

Hwang SH, et al. Cardiovasc Imaging Asia. 2026 Jul;10(3):45-59. https://doi.org/10.22468/cvia.2026.00052

Kim HR, et al. Yonsei Med J. 2026 ;67:e61. https://doi.org/10.3349/ymj.2026.0540

옥지윤, et al. J Korean Soc Radiol. 2026 ;87:e52. https://doi.org/10.3348/jksr.2025.0131

Cardiac CT has become an essential imaging modality in the diagnostic and therapeutic workflow for valvular heart disease (VHD), particularly in the era of transcatheter and minimally invasive valve therapies. The existing guidelines emphasize cardiac CT infrastructure and expertise as core requirements for both primary and comprehensive valve centers. Advances in CT acquisition and image reconstruction allow precise evaluation of valvular morphology, motion, and calcification, supporting accurate disease-severity grading and procedural planning. In comparison with echocardiography, cardiac CT provides superior spatial resolution and is less affected by acoustic shadowing from heavy calcification or prosthetic materials, making it especially valuable in complex or inconclusive cases. This review summarizes the CT scanning protocols and reconstruction strategies for valvular assessment and discusses CT-based evaluations of native-valve stenosis and regurgitation, prosthetic-valve dysfunction—including structural degeneration, thrombosis, and pannus—and infective endocarditis, highlighting the complementary role of CT alongside echocardiography in comprehensive VHD management.

Park SH, et al. Korean J Radiol. 2026 ;27:e26. https://doi.org/10.3348/kjr.2026.0115