Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Purpose: The female sex is reported to have a higher risk of adverse events (AEs) from cytotoxic chemotherapy. Few studies examined the sex differences in AEs and their impact on the use of medical services during adjuvant chemotherapy. This sub-study aimed to compare the incidence of any grade and grade ≥ 3 AEs, healthcare utilization, chemotherapy completion rate, and dose intensity according to sex. Materials and Methods: This is a sub-study of a multicenter cohort conducted in Korea that evaluated the impact of healthcare reimbursement on AE evaluation in patients who received adjuvant chemotherapy between September 2013 and December 2016 at four hospitals in Korea. Results: A total of 1,170 patients with colorectal, gastric, or non–small cell lung cancer were included in the study. Female patients were younger, had fewer comorbidities, and experienced less postoperative weight loss of > 10%. Females had significantly higher rates of any grade AEs including nausea, abdominal pain, stomatitis, vomiting, and neutropenia, and experienced more grade ≥ 3 neutropenia, nausea, and vomiting. The dose intensity of chemotherapy was significantly lower in females, and they also experienced more frequent dose reduction after the first cycle. Moreover, female patients receiving platinum-containing regimens had significantly higher rates of unscheduled outpatient visits. Conclusion Our study found that females experienced a higher incidence of multiple any-grade AEs and severe neutropenia, nausea, and vomiting, across various cancer types, leading to more frequent dose reductions. Physicians should be aware of sex differences in AEs for chemotherapy decisions.

Background/Aims: Metabolic dysfunction-associated steatotic liver disease (MASLD) is characterized by fat accumulation in the liver. MASLD encompasses both steatosis and MASH. Since MASH can lead to cirrhosis and liver cancer, steatosis and MASH must be distinguished during patient treatment. Here, we investigate the genomes, epigenomes, and transcriptomes of MASLD patients to identify signature gene set for more accurate tracking of MASLD progression. Methods: Biopsy-tissue and blood samples from patients with 134 MASLD, comprising 60 steatosis and 74 MASH patients were performed omics analysis. SVM learning algorithm were used to calculate most predictive features. Linear regression was applied to find signature gene set that distinguish the stage of MASLD and to validate their application into independent cohort of MASLD. Results: After performing WGS, WES, WGBS, and total RNA-seq on 134 biopsy samples from confirmed MASLD patients, we provided 1,955 MASLD-associated features, out of 3,176 somatic variant callings, 58 DMRs, and 1,393 DEGs that track MASLD progression. Then, we used a SVM learning algorithm to analyze the data and select the most predictive features. Using linear regression, we identified a signature gene set capable of differentiating the various stages of MASLD and verified it in different independent cohorts of MASLD and a liver cancer cohort. Conclusions We identified a signature gene set (i.e., CAPG, HYAL3, WIPI1, TREM2, SPP1, and RNASE6) with strong potential as a panel of diagnostic genes of MASLD-associated disease.

Background: Although several techniques for the treatment of ulnar impaction syndrome (UIS) have been introduced, there have still been reports on various complications such as delayed union, nonunion, refracture, wrist pain, plate irritation, and chronic regional pain syndrome. This study aimed to compare the differences in radiological and clinical outcomes of patients in which intramedullary bone grafting was performed in addition to plate stabilization with those without additional bone grafting during ulnar shortening osteotomies (USOs). Methods: Between November 2014 and June 2021, 53 wrists of 50 patients with idiopathic UIS were retrospectively reviewed. Patients were divided into 2 groups according to whether intramedullary bone grafting was performed. Among the 53 wrists, USO with an intramedullary bone graft was performed in 21 wrists and USO without an intramedullary bone graft was performed in 32 wrists. Demographic data and factors potentially associated with bone union time were analyzed. Results: There was no significant difference between the 2 groups when comparing postoperative radioulnar distance, postoperative ulnar variance, amount of ulnar shortening, and postoperative Disabilities of the Arm, Shoulder and Hand score. Compared to the without-intramedullary bone graft group, bone union time of the osteotomy site was significantly shortened, from 8.8 ± 3.0 weeks to 6.7 ± 1.3 weeks in the with-intramedullary bone graft group. Moreover, there were no cases of nonunion or plate-induced symptoms. Both in univariable and multivariable analyses, intramedullary bone grafting was associated with shorter bone union time. Conclusions USO with an intramedullary bone graft for idiopathic UIS has favorable radiological and clinical outcomes. The advantage of this technique is the significant shortening of bone union time.

OBJECTIVES: The escalating burden of cardiovascular disease (CVD) is a critical public health issue worldwide. CVD, especially acute myocardial infarction (AMI) and stroke, is the leading contributor to morbidity and mortality in Korea. We aimed to develop algorithms for identifying AMI and stroke events from the National Health Insurance Service (NHIS) database and validate these algorithms through medical record review. METHODS: We first established a concept and definition of “hospitalization episode,” taking into account the unique features of health claims-based NHIS database. We then developed first and recurrent event identification algorithms, separately for AMI and stroke, to determine whether each hospitalization episode represents a true incident case of AMI or stroke. Finally, we assessed our algorithms’ accuracy by calculating their positive predictive values (PPVs) based on medical records of algorithm- identified events. RESULTS: We developed identification algorithms for both AMI and stroke. To validate them, we conducted retrospective review of medical records for 3,140 algorithm-identified events (1,399 AMI and 1,741 stroke events) across 24 hospitals throughout Korea. The overall PPVs for the first and recurrent AMI events were around 92% and 78%, respectively, while those for the first and recurrent stroke events were around 88% and 81%, respectively. CONCLUSIONS We successfully developed algorithms for identifying AMI and stroke events. The algorithms demonstrated high accuracy, with PPVs of approximately 90% for first events and 80% for recurrent events. These findings indicate that our algorithms hold promise as an instrumental tool for the consistent and reliable production of national CVD statistics in Korea.

Thyroid nodules represent a prevalent condition that is detectable via palpation or ultrasound. In recent years, there has been a paradigm shift toward enhanced diagnostic precision and less aggressive therapeutic approaches, highlighting the growing necessity for tailored clinical recommendations to optimize patient outcomes. The Korean Thyroid Association (KTA) has developed guidelines for managing patients with thyroid nodules, following a comprehensive review by task force members of the relevant literature identified via electronic database searches. The recommendations are provided with a level of recommendation for each section. The guidelines encompass thyroid cancer screening in high-risk groups, appropriate diagnostic methods for thyroid nodules, role of pathologic and molecular marker testing in making a diagnosis, long-term follow-up and treatment of benign thyroid nodules, and special considerations for pregnant women. The major revisions that were made in the 2023 guidelines were the definition of high-risk groups for thyroid cancer screening, application of the revised Korean Thyroid Imaging Reporting and Data System (K-TIRADS), addition of the role of core needle biopsy and molecular marker tests, application of active surveillance in patients with low-risk papillary thyroid microcarcinoma, and updated indications for nonsurgical treatment of benign thyroid nodules. In the 2024 revision of the KTA guidelines for thyroid cancer, the evidence for some recommendations has been updated to address the tumor size in the context of active surveillance in patients with low-risk thyroid cancer and the surgical size cutoff. These evidence-based recommendations serve to inform clinical decision-making in the management of thyroid nodules, thereby facilitating the delivery of optimal and efficacious treatments to patients.