Background/Aims: Left ventricular ejection fraction (LVEF) is a key echocardiographic parameter for assessing LV systolic function, guiding the management of many cardiovascular diseases, including heart failure (HF). While traditional electrocardiography (ECG) has been widely used in clinical practice, it has limitations in predicting LVEF. This study investigated the impact of integrating ECG data with metadata, such as age, N-terminal pro B-type natriuretic peptide (NT-proBNP), and sodium levels, to enhance the accuracy of LVEF prediction, especially in HF with reduced ejection fraction (HFrEF, LVEF ≤ 40%). Methods: This retrospective study analyzed ECG and metadata from two tertiary teaching hospitals in Korea. A deep neural network (EfficientNet B3) was trained to predict LVEF, incorporating clinical metadata alongside ECG inputs. Model performance was assessed using the area under the curve (AUC) and the coefficient of determination (R2). Results: The artificial intelligence (AI) model achieved an AUC of 0.95 when ECG data were combined with age, NT-proBNP, and sodium levels, outperforming models relying on ECG alone (AUC = 0.90). The integration of metadata significantly improved the prediction accuracy, particularly for HFrEF cases. The specificity of the model remained high (96.9%), but sensitivity was relatively low (54.8%), indicating its potential as a screening tool for HFrEF. Conclusions The combination of ECG and metadata results using AI enhances the predictive accuracy of HFrEF detection. This approach offers a scalable and noninvasive method for HF screening and risk stratification, particularly in resource-limited settings. Further validation in diverse populations is needed to confirm its clinical utility.

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.

Purpose: Neoadjuvant treatment (NAT) is now the standard for borderline resectable pancreatic cancer (RPC) and is being considered for RPC. Early recurrence after curative surgery in RPC is often seen as a treatment failure, prompting considerations for NAT. Our goal was to develop an artificial intelligence (AI)-based predictive model utilizing preoperatively available factors to forecast early recurrences of resected RPC. Methods: This study included 469 patients who underwent surgery for RPC between 2011 and 2019. Clinicopathologic and oncologic data were retrospectively reviewed. Preoperative variables, including laboratory data and imaging findings, were collected. Early recurrence was defined as recurrence occurring within a year after surgery. Deep neural networks were then used to select variables by assessing their importance. A new model predicting early recurrence of RPC was subsequently developed. Results: Of the patients evaluated, 199 (42.4%) experienced early recurrence. The predictive model included 14 preoperative variables: CA 19-9, preoperative pancreatitis, serum albumin, platelet count, lymphocyte count, the American Society of Anesthesiologists physical status classification, tumor size, monocyte count, age, body mass index, CRP, hemoglobin, WBC count, and CEA. The area under the curve for the model was 0.786 in the training set and 0.734 in the test set. Conclusion We developed an AI-based model to predict the early recurrence of RPC using preoperative parameters. By identifying patients at risk of early recurrence, optimal individualized treatments such as NAT can be considered. Future prospective studies are crucial to establish clear indications for NAT in RPC.

Robotic thyroidectomy has progressed from multiport to single-port (SP) platforms to minimize invasiveness and improve cosmesis. The da Vinci SP system (Intuitive Surgical) combines a flexible 3-dimensional endoscope with 3 wristed instruments in a single 2.5-cm cannula-enabled concealed remote access route and mitigates external arm collisions.This review synthesized PubMed-indexed reports (2020–2025) on SP robotic thyroidectomy using the following approaches:transaxillary variants, SP areolar, retroauricular/facelift (SP-hairline variants), and transoral approach. We focused on technical refinement, learning curves, and clinical outcomes. We highlight technical refinements and clinical outcomes across access routes. Contemporary series indicate that SP thyroidectomy is feasible and safe in well-selected patients, with high cosmetic satisfaction and operative metrics comparable to those of multiport cohorts. Among the SP routes, transaxillary variants have the most mature peer-reviewed reporting and are therefore discussed in greater detail. Early applications of SP-assisted lateral neck dissection have also been described. The limitations of current SP platforms include constrained counter-traction, reduced internal workspace, and incomplete integration of advanced energy devices.Nonetheless, ongoing device innovations and the growing global experience suggest that SP systems will increasingly shape endocrine neck surgeries.

Soft tissue sarcomas (STSs), a diverse group of mesenchymal malignancies, are characterized primarily by copy-number alterations rather than a high tumor mutation burden. In this study, we sought to identify expression-based biomarkers in complex karyotype STS (CKS) with CDK4-amplification to support improved therapeutic strategies. Using transcriptome data from National Cancer Center (NCC)-CKS samples, we selected genes whose expression levels were more than two-fold higher or less than half in tumor tissues compared with normal tissues. These genes were further filtered by CDK4-amplification status, resulting in 30 candidates, which were refined to 14 differentially expressed genes (DEGs) based on false discovery rate (FDR) significance. Bioinformatics analyses revealed enriched pathways and gene–gene networks related to redox regulation and growth-factor–driven signal transduction, indicating metabolic alterations that may promote tumor survival in CDK4-amplified CKS. A subset of the 14 genes demonstrated prognostic significance in CDK4-amplified patients from the TCGA cohort. Additionally, immune cell marker analysis showed associations between CDK4-amplification and innate immune cell signatures. Together, our findings identify promising therapeutic and prognostic targets linked to CDK4-amplification in CKS. These biomarkers warrant further investigation and may ultimately contribute to improved clinical outcomes for patients with CKS.

Purpose: Several studies suggest that glycolytic enzyme expression may be linked to increased malignancy in various organs. However, the relationship between glycolytic enzyme expression and aggressiveness in papillary thyroid carcinoma (PTC) is not yet fully understood. This study aimed to determine whether glycolytic enzyme expression correlates with aggressiveness, including lymph node metastasis and extrathyroidal extension, using data from The Cancer Genome Atlas (TCGA). Methods: Lactate dehydrogenase A (LDHA), pyruvate kinase isoform M2 (PKM2), and glucose transporter 1 (GLUT1) mRNA expression were examined in 465 PTC samples using TCGA data. We analyzed the correlation between these glycolytic enzymes and transporter protein and the clinicopathological characteristics of PTC, with a particular focus on lymph node metastasis and recurrence. Results: Overexpression of LDHA, PKM2, and GLUT1 was associated with lymph node metastasis and the aggressive subtype of PTC. In the multivariate analysis, younger age, multifocality, advanced T stage (T3/T4), and increased PKM2 mRNA expression were significant predictors of lymph node metastasis. Among the variables, high PKM2 mRNA expression showed the strongest association with lymph node metastasis (odds ratio 6.907, P=0.001). However, there were no significant differences in disease-free survival rates according to LDHA, PKM2, or GLUT1 expression levels. Conclusion LDHA, PKM2, and GLUT1 overexpression is linked to lymph node metastasis and aggressive PTC subtypes. Of these, PKM2 mRNA expression may have particular potential as a biomarker for lymph node metastasis in PTC.

Purpose: Glycolytic enzymes have been extensively studied in various cancer types, revealing their aggressive characteristics and roles in tumor progression. This study aimed to determine whether the expression of glycolytic enzymes is associated with aggressiveness in the presence or absence of chronic lymphocytic thyroiditis (CLT). Methods: The expression of hexokinase 2, lactate dehydrogenase A (LDHA), pyruvate kinase isoform M2 (PKM2), glucose transporter 1 (GLUT1), and monocarboxylate transporter 4 (MCT4) was examined in 233 papillary thyroid carcinoma (PTC) specimens by immunohistochemistry. We evaluated whether the expression of these glycolytic enzymes correlates with lymph node metastasis, extrathyroidal extension (ETE), and recurrence rate, both with and without CLT. In addition, we analyzed the correlation between glycolytic enzyme messenger RNA expression and risk factors in PTC using The Cancer Genome Atlas. Results: All glycolytic enzymes and transporter proteins were overexpressed in PTC compared with normal tissue. PKM2 expression was most highly correlated with the other glycolytic enzymes. High PKM2 expression was significantly linked to increased recurrence risk in patients without CLT (hazard ratio, 1.76; 95% confidence interval, 1.01–3.06; P = 0.046), but this association was not observed in those with CLT. Conclusion Overexpression of LDHA, PKM2, GLUT1, and MCT4 is associated with PTC. CLT is significantly associated with an increased incidence of gross ETE and, paradoxically, with a reduced recurrence rate in PTC. LDHA expression was lower in the presence of CLT, whereas PKM2 remained consistently linked to a higher recurrence rate in its absence.Among the evaluated glycolytic enzymes, PKM2 may serve as a biomarker for recurrence in PTC.

Purpose: Although the combination of androgen deprivation therapy with docetaxel or abiraterone acetate and prednisone has become a standard treatment for metastatic hormone-sensitive prostate cancer (mHSPC) and has shown improved overall survival, a subset of patients still progress to castration-resistant disease. However, the underlying molecular features in these patients remain poorly understood. Materials and Methods: We performed single-cell RNA sequencing (scRNA-seq) on 12 tissue samples, including 2 mHSPC samples, 7 primary prostate cancer (PCa) samples, and 3 matched normal samples from 7 patients. Raw sequencing data was processed by Cell Ranger software (10X Genomics) and aligned to the human reference genome (GRCh38). A comprehensive analysis of samples from patients with mHSPC was also conducted and validated using a cohort of 52 patients with mHSPC. Results: Our results identified distinct subpopulations within luminal and mononuclear phagocyte (MNP) clusters characterized by proliferative activation associated with unfavorable clinical outcomes. Furthermore, we observed that the MNP cluster exhibited significant proliferation activity. To understand the underlying mechanisms associated with aggressiveness, we conducted cell-cell interaction, copy number variation and pseudotime analysis. Utilizing 87 network genes from scRNA-seq, we classified 52 mHSPC patients into 2 molecular subtypes and demonstrated their correlation with distinct transcriptomic profiles and survival outcomes. Importantly, a 14-gene signature derived from 3 distinct gene sets exhibited a strong association with patient survival and drug response. The prognostic value of our findings was further validated in large-scale cohorts comprising localized PCa, metastatic PCa, mHSPC, and metastatic castration-resistant PCa patients. Conclusion This study provides valuable insights into the identification of high-risk patients, novel biomarkers, and potential therapeutic targets for individuals with mHSPC. Furthermore, the results in this study can serve as a basis for future investigations aimed at refining prognostic strategies and developing targeted therapies for patients with mHSPC.

Background/Aims: The kidneys and retina are highly vascularized organs that frequently exhibit shared pathologies, with nephropathy often associated with retinopathy. Previous studies have successfully predicted estimated glomerular filtration rates (eGFRs) using fundus photographs. We evaluated the performance of the Modification of Diet in Renal Disease (MDRD) and Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) formulas in eGFR prediction. Methods: We enrolled patients with fundus photographs and corresponding creatinine measurements taken on the same date. One photograph per eye was randomly selected, resulting in a final dataset of 45,108 patients (88,260 photographs). Data including sex, age, and blood creatinine levels were collected for eGFR calculation using the MDRD and CKD-EPI formulas. EfficientNet B3 models were used to predict each parameter. Results: Deep neural network models accurately predicted age and sex using fundus photographs. Sex was identified as a confounding variable in creatinine prediction. The MDRD formula was more susceptible to this confounding effect than the CKD-EPI formula. Notably, the CKD-EPI formula demonstrated superior performance compared to the MDRD formula (area under the curve 0.864 vs. 0.802). Conclusions Fundus photographs are a valuable tool for screening renal function using deep neural network models, demonstrating the role of noninvasive imaging in medical diagnostics. However, these models are susceptible to the influence of sex, a potential confounding factor. The CKD-EPI formula, less susceptible to sex bias, is recommended to obtain more reliable results.