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: Recent development in perioperative treatment of resectable non–small cell lung cancer (NSCLC) have changed the landscape of early lung cancer management. The ADAURA trial has demonstrated the efficacy of adjuvant osimertinib treatment in resectable NSCLC patients; however, studies are required to show which subgroup of patients are at a high risk of relapse and require adjuvant epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor treatment. This study evaluated risk factors for postoperative relapse among patients who underwent complete resection. Materials and Methods: Data were obtained from the Korean Association for Lung Cancer Registry (KALC-R), a database created using a retrospective sampling survey by the Korean Central Cancer Registry (KCCR) and the Lung Cancer Registration Committee. Results: A total of 3,176 patients who underwent curative resection was evaluated. The mean observation time was approximately 35.4 months. Among stage I to IIIA NSCLC patients, the EGFR-mutant subgroup included 867 patients, and 75.2%, 11.2%, and 11.8% were classified as stage I, stage II, and stage III, respectively. Within the EGFR-mutant subgroup, 44 (5.1%) and 121 (14.0%) patients showed early and late recurrence, respectively. Multivariate analysis on association with postoperative relapse among the EGFR-mutant subgroup showed that age, pathologic N and TNM stages, pleural invasion status, and surgery type were independent significant factors. Conclusion Among the population that underwent complete resection for early NSCLC with EGFR mutation, patients with advanced stage, pleural invasion, or limited resection are more likely to show postoperative relapse.

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: Recent development in perioperative treatment of resectable non–small cell lung cancer (NSCLC) have changed the landscape of early lung cancer management. The ADAURA trial has demonstrated the efficacy of adjuvant osimertinib treatment in resectable NSCLC patients; however, studies are required to show which subgroup of patients are at a high risk of relapse and require adjuvant epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor treatment. This study evaluated risk factors for postoperative relapse among patients who underwent complete resection. Materials and Methods: Data were obtained from the Korean Association for Lung Cancer Registry (KALC-R), a database created using a retrospective sampling survey by the Korean Central Cancer Registry (KCCR) and the Lung Cancer Registration Committee. Results: A total of 3,176 patients who underwent curative resection was evaluated. The mean observation time was approximately 35.4 months. Among stage I to IIIA NSCLC patients, the EGFR-mutant subgroup included 867 patients, and 75.2%, 11.2%, and 11.8% were classified as stage I, stage II, and stage III, respectively. Within the EGFR-mutant subgroup, 44 (5.1%) and 121 (14.0%) patients showed early and late recurrence, respectively. Multivariate analysis on association with postoperative relapse among the EGFR-mutant subgroup showed that age, pathologic N and TNM stages, pleural invasion status, and surgery type were independent significant factors. Conclusion Among the population that underwent complete resection for early NSCLC with EGFR mutation, patients with advanced stage, pleural invasion, or limited resection are more likely to show postoperative relapse.

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: Recent development in perioperative treatment of resectable non–small cell lung cancer (NSCLC) have changed the landscape of early lung cancer management. The ADAURA trial has demonstrated the efficacy of adjuvant osimertinib treatment in resectable NSCLC patients; however, studies are required to show which subgroup of patients are at a high risk of relapse and require adjuvant epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor treatment. This study evaluated risk factors for postoperative relapse among patients who underwent complete resection. Materials and Methods: Data were obtained from the Korean Association for Lung Cancer Registry (KALC-R), a database created using a retrospective sampling survey by the Korean Central Cancer Registry (KCCR) and the Lung Cancer Registration Committee. Results: A total of 3,176 patients who underwent curative resection was evaluated. The mean observation time was approximately 35.4 months. Among stage I to IIIA NSCLC patients, the EGFR-mutant subgroup included 867 patients, and 75.2%, 11.2%, and 11.8% were classified as stage I, stage II, and stage III, respectively. Within the EGFR-mutant subgroup, 44 (5.1%) and 121 (14.0%) patients showed early and late recurrence, respectively. Multivariate analysis on association with postoperative relapse among the EGFR-mutant subgroup showed that age, pathologic N and TNM stages, pleural invasion status, and surgery type were independent significant factors. Conclusion Among the population that underwent complete resection for early NSCLC with EGFR mutation, patients with advanced stage, pleural invasion, or limited resection are more likely to show postoperative relapse.

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: It is well known that a large number of patients with diabetes also have dyslipidemia, which significantly increases the risk of cardiovascular disease (CVD). This study aimed to evaluate the efficacy and safety of combination drugs consisting of metformin and atorvastatin, widely used as therapeutic agents for diabetes and dyslipidemia. Methods: This randomized, double-blind, placebo-controlled, parallel-group and phase III multicenter study included adults with glycosylated hemoglobin (HbA1c) levels >7.0% and <10.0%, low-density lipoprotein cholesterol (LDL-C) >100 and <250 mg/dL. One hundred eighty-five eligible subjects were randomized to the combination group (metformin+atorvastatin), metformin group (metformin+atorvastatin placebo), and atorvastatin group (atorvastatin+metformin placebo). The primary efficacy endpoints were the percent changes in HbA1c and LDL-C levels from baseline at the end of the treatment. Results: After 16 weeks of treatment compared to baseline, HbA1c showed a significant difference of 0.94% compared to the atorvastatin group in the combination group (0.35% vs. −0.58%, respectively; P<0.0001), whereas the proportion of patients with increased HbA1c was also 62% and 15%, respectively, showing a significant difference (P<0.001). The combination group also showed a significant decrease in LDL-C levels compared to the metformin group (−55.20% vs. −7.69%, P<0.001) without previously unknown adverse drug events. Conclusion The addition of atorvastatin to metformin improved HbA1c and LDL-C levels to a significant extent compared to metformin or atorvastatin alone in diabetes and dyslipidemia patients. This study also suggested metformin’s preventive effect on the glucose-elevating potential of atorvastatin in patients with type 2 diabetes mellitus and dyslipidemia, insufficiently controlled with exercise and diet. Metformin and atorvastatin combination might be an effective treatment in reducing the CVD risk in patients with both diabetes and dyslipidemia because of its lowering effect on LDL-C and glucose.