Objectives: Large language models (LLMs) demonstrate remarkable potential in healthcare communication. However, whether they can process complex, high-volume medical information, such as stroke-related content, remains insufficiently validated. This study aimed to evaluate the natural language processing capabilities of LLMs in handling such content and to develop an evaluation instrument. Methods: A survey compared educational materials generated by two LLMs (ChatGPT 4.0 and Claude 3) with neurologist-authored content on stroke. The materials were based on two clinical scenarios representing distinct stroke etiologies: cardioembolism and large-artery atherosclerosis. They were evaluated in terms of accuracy, legality, ethics, comprehensiveness, and information delivery. Scores for comprehensiveness and information delivery were compared according to participants’ agreement with the use of LLMs in healthcare. Results: ChatGPT received the highest scores across all domains, except for legality in Scenario 2. In Scenario 1, the ranking for accuracy and summarization of clinical information was, from highest to lowest, ChatGPT, Claude, and the neurologist (η2 = 0.140, p < 0.001; η2 = 0.175, p < 0.001). The same hierarchy was observed in Scenario 2 for accuracy (η2 = 0.077, p < 0.001) and summarization (η2 = 0.194, p < 0.001). Participants who agreed with the use of LLMs in healthcare assigned higher scores for the comprehensiveness (Scenario 1, p = 0.005; Scenario 2, p = 0.007) and information delivery (Scenario 1, p = 0.003; Scenario 2, p = 0.026) of ChatGPT-generated materials than participants who did not agree. Conclusions LLMs demonstrated adequate capability to convey complex content, such as stroke-related information, in an accessible and understandable manner for non-experts.

Background and Objectives: Clinical characteristics and outcomes in acute heart failure (AHF) vary by phenotype. We assessed phenotype-specific features, treatment patterns, and outcomes in a nationwide Korean cohort. Methods: The Korean Heart Failure III registry prospectively enrolled 7,351 AHF admissions at 47 hospitals. Among 6,777 patients with available left ventricular ejection fraction (EF), phenotypes were defined as heart failure with reduced EF (HFrEF, ≤40%), mildly reduced EF (HFmrEF,41–49%), or preserved EF (HFpEF, ≥50%). The primary endpoint was a 12-month composite of all-cause death or heart transplantation, evaluated from index admission and, among hospital survivors, from discharge. We used inverse probability weighting (multinomial generalized boosted models with stabilized, trimmed weights) and weighted Cox proportional-hazards models to estimate hazard ratios (HRs). Results: Phenotype distribution was 58.9% HFrEF, 13.6% HFmrEF, and 27.5% HFpEF. Crude 12-month composite rates from index admission were 13.4% (HFrEF), 12.7% (HFmrEF), and 16.8% (HFpEF). After weighting, from index admission, HFmrEF (HR, 0.892; 95% confidence interval [CI], 0.731–1.088) and HFpEF (HR, 1.101; 95% CI, 0.939–1.291) did not differ from HFrEF; from discharge, HFpEF had modestly higher risk (HR, 1.207; 95% CI, 1.008–1.445) whereas HFmrEF did not (HR, 1.039; 95% CI, 0.844–1.279). Hyponatremia and chronic kidney disease were consistent adverse markers, while angiotensin-converting enzyme inhibitor/ angiotensin II receptor blocker use at discharge was protective. Conclusions Across the EF spectrum, phenotypes showed distinct profiles and risk. Postdischarge risk was modestly higher in HFpEF, supporting phenotype-tailored care and systematic discharge optimization in Korean patients with AHF.

Heart failure (HF) prevalence and associated socio-economic costs have risen rapidly in Korea, creating urgent demand for a national, standardized prospective registry to support quality monitoring, outcome comparison, and real-world evidence. Standardized data definitions are essential for valid comparisons across studies and healthcare settings. We created a unified national HF cohort by integrating the two largest Korean registries, KorAHF (2011–2014;n=5,625) and KorHF III (2018–2023; n=7,351), yielding 12,976 hospitalized HF patients. Because heterogeneous variable definitions impeded direct comparisons, we implemented a harmonization pipeline across demographic, clinical, imaging, biomarker, therapeutic, and outcome domains, aligned with international standards and reinforced by systematic data quality checks.A multidisciplinary panel then conducted a structured decision process to produce the Korean HF Standard Dataset, a tiered and interoperable variable set spanning six domains: demographics, presentation at admission, in-hospital events and comorbidities, discharge status, outpatient follow-up, and readmission events. This integrated platform and standardized variables enable precise identification of HF patient phenotypes and prognostic factors, establishing an evidence-based foundation for disease management. This supports an analysis of temporal changes in treatment patterns and outcomes, generates data to inform future clinical practice guidelines, and provides a practical basis for planning large, continuous, prospective HF registries. Furthermore, it also facilitates pragmatic, registry-based randomized clinical trials and unmet-needs assessments that can guide national health policy. Establishing a foundation for future linkage with national health databases, this platform will allow for enhanced accuracy, comparability, and representativeness, powering quality improvement initiatives and population-level monitoring of Korea’s growing HF burden.

In patients with differentiated thyroid cancer (DTC), initial recurrence risk stratification based on clinical, histopathological, and perioperative data remains the key determinant for guiding management strategies during the first 1-2 years post-treatment. However, the adoption of ongoing risk stratification (ORS), which dynamically reassesses risk by integrating longitudinal clinical data and treatment response, enables more precise long-term prognostic assessment and facilitates highly individualized management. Building upon recent guidelines, the 2026 KTA guideline has been further refined by incorporating robust evidence from large-scale national cohorts and comprehensive systematic reviews. These updated recommendations outline contemporary concepts of ORS, risk-adapted TSH suppression targets, optimized surveillance modalities for recurrence detection, and disease-specific long-term follow-up strategies. Reflecting the paradigm shift toward de-escalated treatment, this revision integrates evolved perspectives on TSH suppression intensity, the clinical interpretation of thyroglobulin levels, and tailored follow-up intervals. These evidence-based recommendations aim to minimize unnecessary treatment and excessive surveillance in the large proportion of patients with excellent prognosis after initial therapy, while ensuring that each patient receives appropriately tailored and effective long-term management.

Background: Left bundle branch block (LBBB) significantly increases the risk of left ventricular systolic dysfunction (LVSD) due to cardiac dyssynchrony. Although artificial intelligence–enabled electrocardiography (AI-ECG) mod‑ els show promise in detecting LVSD, their performance in LBBB patients remains underexplored. We hypothesized that an AI-ECG model clinically validated for detecting LVSD would accurately detect LVSD and predict future clinical outcomes in LBBB patients. Methods: In this retrospective multicenter study, 5,689 expert-validated LBBB ECGs collected from 2,813 patients between 2016 and 2024 were analyzed using a previously developed and validated AI-ECG model. LVSD was defined as an ejection fraction of ≤ 40%. Model performance was assessed using the area under the receiver operating char‑ acteristic curve (AUROC), the area under the precision-recall curve (AUPRC), sensitivity, and specificity. Patients were stratified into high- and low-risk groups based on a threshold that achieved 90% sensitivity. A Kaplan–Meier analysis was used to compare clinical outcomes. Results: Among the 2,813 LBBB patients (mean age, 70.7 years; male sex, 43.7%), hypertension and a history of heart failure were common. The AiTiALVSD model showed strong diagnostic performance for LVSD (AUROC, 0.930 [95% CI, 0.924–0.937]; AUPRC, 0.913 [95% CI, 0.902–0.923]; sensitivity, 0.979; specificity, 0.473). During the mean follow-up of 4.1 years, high-risk patients had significantly higher hazards than low-risk patients for all-cause mortality (adjusted hazard ratio [HR], 1.87; 95% CI, 1.53–2.28), implantable cardioverter defibrillator/cardiac resynchronization therapy implantation (adjusted HR, 15.2; 95% CI, 7.51–30.77), and cardiovascular hospitalization (adjusted HR, 1.11; 95% CI, 0.96–1.28). Conclusions AiTiALVSD effectively detects LVSD and stratifies long-term cardiovascular risk in LBBB patients, support‑ ing its clinical utility for early detection and patient management.

Rectal cancer, which accounts for approximately 40% of colorectal cancers, remains a major clinical concern. Recent advances in diagnostic imaging, surgical techniques, radiotherapy, and systemic treatment have steadily improved rectal cancer outcomes. Considering this, the Korean Rectal Cancer Multidisciplinary (KRCM) Committee has aimed to provide clinicians and policymakers with up-to-date, evidence-based clinical practice guidelines to support optimal decision-making, reflecting current evidence, the Korean healthcare context, and patient values and preferences. The Clinical Practice Guidelines for Rectal Cancer version 2.0 were developed through multidisciplinary collaboration with related academic societies, building upon and updating the KRCM Clinical Practice Guidelines version 1.0 (titled “Multidisciplinary guidelines for the management of rectal cancer”). These consensus guidelines of the KRCM were established based on a comprehensive literature review, evidence synthesis, with recommendation development guided by the GRADE (Grading of Recommendations Assessment, Development and Evaluation) methodology, and consideration of applicability in real-world clinical practice under the national health insurance system. Each recommendation has been presented with its strength and level of evidence.

Background: Psoriasis is acknowledged for its association with diabetes and obesity. However, the comprehension of the correlation between obesity and psoriasis risk in individuals with diabetes remains limited. Objective: We aimed to examine the association of body mass index and waist circumference (WC) with the risk of developing psoriasis in individuals with type 2 diabetes mellitus (T2DM). Methods: This retrospective cohort study utilized nationwide data for exploratory analysis.A total of 2,480,489 participants, all diagnosed with T2DM, were included. Results: Over a 6.77±1.69-year follow-up, 71,514 patients (2.88%) were diagnosed with psoriasis. Adjusting for multiple variables, the study revealed a J-shaped pattern association between BMI levels and the hazard ratio (HR) for psoriasis in patients with T2DM. A linear pattern relationship was observed regarding WC, with the highest WC group showing the most elevated HR (HR, 1.123; 95% confidence interval, 1.091–1.156). Conclusion Understanding the relationship between psoriasis risk and obesity in diabetic individuals holds the potential to enhance the management of patients with T2DM.

Purpose: Psychiatric conditions are common in children and adolescents with diabetes and can hinder disease management. In this study, we examined whether mental health status at diagnosis predicts glycemic control at 1 year. Methods: We included 57 patients aged 6–18 years diagnosed with type 1 or type 2 diabetes between 2019 and 2023 at Seoul National University Bundang Hospital. Mental health was assessed within 3 months of diagnosis using the Eating Disorder Inventory-2, Children’s Depression Inventory, and Child Behavior Checklist (CBCL) for ages 6–18. Poor glycemic control was defined as glycated hemoglobin >6.5% at 1 year. Associations between screening results and glycemic control were analyzed using Fisher exact test and multivariate logistic regression. Results: Of the 57 patients, 32 (56.1%) had type 1 diabetes, and the mean age at diagnosis was 12.9±3.1 years; 31 (54.4%) were male. Poor glycemic control at 1 year was observed in 16 patients (28.1%). Although individual subscale positivity was not significantly associated with glycemic control, borderline somatic complaints on the CBCL were significantly associated with poor control (p=0.022). In multivariate analysis, having 2 or more positive CBCL subscales showed a trend toward association with poor glycemic control (adjusted odds ratio=21.47, p=0.054). Conclusion Early psychological screening, especially for somatic symptoms or multiple psychological problems, may help identify those at risk for poor glycemic control in pediatric diabetes. These findings underscore the importance of early detection and intervention in optimizing diabetes management.