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: Hematopoietic stem cell transplantation (HSCT) has been an important method of treatment in the advance of pediatric acute lymphoblastic leukemia (ALL). The indications for HSCT are evolving and require updated establishment. In this study, we aimed to investigate the efficacy of HSCT on the treatment outcome of pediatric ALL, considering the indications for HSCT and subgroups. Materials and Methods: A retrospective analysis was conducted on ALL patients diagnosed and treated at a single center. Risk groups were categorized based on age at diagnosis, initial white blood cell count, disease lineage (B/T), and cytogenetic study results. Data on the patients’ disease status at HSCT and indications of HSCT were collected. Indications for HSCT were categorized as upfront HSCT at 1st complete remission, relapse, and refractory disease. Results: Among the 549 screened patients, a total of 418 patients were included in the study; B-cell ALL (n=379) and T-cell ALL (T-ALL) (n=39). HSCT was conducted on a total of 106 patients (25.4%), with a higher frequency as upfront HSCT in higher-risk groups and specific cytogenetics. The overall survival (OS) was significantly better when done upfront than in relapsed or refractory state in T-ALL patients (p=0.002). The KMT2A-rearranged ALL patients showed superior event-free survival (p=0.002) and OS (p=0.022) when HSCT was done as upfront treatment. Conclusion HSCT had a substantial positive effect in a specific subset of pediatric ALL. In particular, frontline HSCT for T-ALL and KMT2A-rearranged ALL offered a better prognosis than when HSCT was conducted in a relapsed or refractory setting.

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: Hematopoietic stem cell transplantation (HSCT) has been an important method of treatment in the advance of pediatric acute lymphoblastic leukemia (ALL). The indications for HSCT are evolving and require updated establishment. In this study, we aimed to investigate the efficacy of HSCT on the treatment outcome of pediatric ALL, considering the indications for HSCT and subgroups. Materials and Methods: A retrospective analysis was conducted on ALL patients diagnosed and treated at a single center. Risk groups were categorized based on age at diagnosis, initial white blood cell count, disease lineage (B/T), and cytogenetic study results. Data on the patients’ disease status at HSCT and indications of HSCT were collected. Indications for HSCT were categorized as upfront HSCT at 1st complete remission, relapse, and refractory disease. Results: Among the 549 screened patients, a total of 418 patients were included in the study; B-cell ALL (n=379) and T-cell ALL (T-ALL) (n=39). HSCT was conducted on a total of 106 patients (25.4%), with a higher frequency as upfront HSCT in higher-risk groups and specific cytogenetics. The overall survival (OS) was significantly better when done upfront than in relapsed or refractory state in T-ALL patients (p=0.002). The KMT2A-rearranged ALL patients showed superior event-free survival (p=0.002) and OS (p=0.022) when HSCT was done as upfront treatment. Conclusion HSCT had a substantial positive effect in a specific subset of pediatric ALL. In particular, frontline HSCT for T-ALL and KMT2A-rearranged ALL offered a better prognosis than when HSCT was conducted in a relapsed or refractory setting.

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: Hematopoietic stem cell transplantation (HSCT) has been an important method of treatment in the advance of pediatric acute lymphoblastic leukemia (ALL). The indications for HSCT are evolving and require updated establishment. In this study, we aimed to investigate the efficacy of HSCT on the treatment outcome of pediatric ALL, considering the indications for HSCT and subgroups. Materials and Methods: A retrospective analysis was conducted on ALL patients diagnosed and treated at a single center. Risk groups were categorized based on age at diagnosis, initial white blood cell count, disease lineage (B/T), and cytogenetic study results. Data on the patients’ disease status at HSCT and indications of HSCT were collected. Indications for HSCT were categorized as upfront HSCT at 1st complete remission, relapse, and refractory disease. Results: Among the 549 screened patients, a total of 418 patients were included in the study; B-cell ALL (n=379) and T-cell ALL (T-ALL) (n=39). HSCT was conducted on a total of 106 patients (25.4%), with a higher frequency as upfront HSCT in higher-risk groups and specific cytogenetics. The overall survival (OS) was significantly better when done upfront than in relapsed or refractory state in T-ALL patients (p=0.002). The KMT2A-rearranged ALL patients showed superior event-free survival (p=0.002) and OS (p=0.022) when HSCT was done as upfront treatment. Conclusion HSCT had a substantial positive effect in a specific subset of pediatric ALL. In particular, frontline HSCT for T-ALL and KMT2A-rearranged ALL offered a better prognosis than when HSCT was conducted in a relapsed or refractory setting.

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: The increasing rate of excess body weight (EBW) in the global population has led to growing health concerns, including cancer-related EBW. We aimed to estimate the population attributable fraction (PAF) of cancer incidence and deaths linked to EBW in Korean individuals from 2015 to 2030 and to compare its value with various body mass index cutoffs. Methods: Levin’s formula was used to calculate the PAF; the prevalence rates were computed using the Korean National Health and Nutrition Examination Survey data, while the relative risks of specific cancers related to EBW were estimated based on the results of Korean cohort studies. To account for the 15-year latency period when estimating the PAF in 2020, the prevalence rates from 2015 and attributable cases or deaths from 2020 were used. Results: The PAF attributed to EBW was similar for both cancer incidence and deaths using either the World Health Organization (WHO) Asian-Pacific region standard or a modified Asian standard, with the WHO standard yielding the lowest values. In the Korean population, the PAFs of EBW for cancer incidence were 2.96% in men and 3.61% in women, while those for cancer deaths were 0.67% in men and 3.06% in women in 2020. Additionally, PAFs showed a gradual increase in both sexes until 2030. Conclusion The EBW continues to have a significant impact on cancer incidence and deaths in Korea. Effective prevention strategies targeting the reduction of this modifiable risk factor can substantially decrease the cancer burden.

Background: The increasing rate of excess body weight (EBW) in the global population has led to growing health concerns, including cancer-related EBW. We aimed to estimate the population attributable fraction (PAF) of cancer incidence and deaths linked to EBW in Korean individuals from 2015 to 2030 and to compare its value with various body mass index cutoffs. Methods: Levin’s formula was used to calculate the PAF; the prevalence rates were computed using the Korean National Health and Nutrition Examination Survey data, while the relative risks of specific cancers related to EBW were estimated based on the results of Korean cohort studies. To account for the 15-year latency period when estimating the PAF in 2020, the prevalence rates from 2015 and attributable cases or deaths from 2020 were used. Results: The PAF attributed to EBW was similar for both cancer incidence and deaths using either the World Health Organization (WHO) Asian-Pacific region standard or a modified Asian standard, with the WHO standard yielding the lowest values. In the Korean population, the PAFs of EBW for cancer incidence were 2.96% in men and 3.61% in women, while those for cancer deaths were 0.67% in men and 3.06% in women in 2020. Additionally, PAFs showed a gradual increase in both sexes until 2030. Conclusion The EBW continues to have a significant impact on cancer incidence and deaths in Korea. Effective prevention strategies targeting the reduction of this modifiable risk factor can substantially decrease the cancer burden.

Background: The increasing rate of excess body weight (EBW) in the global population has led to growing health concerns, including cancer-related EBW. We aimed to estimate the population attributable fraction (PAF) of cancer incidence and deaths linked to EBW in Korean individuals from 2015 to 2030 and to compare its value with various body mass index cutoffs. Methods: Levin’s formula was used to calculate the PAF; the prevalence rates were computed using the Korean National Health and Nutrition Examination Survey data, while the relative risks of specific cancers related to EBW were estimated based on the results of Korean cohort studies. To account for the 15-year latency period when estimating the PAF in 2020, the prevalence rates from 2015 and attributable cases or deaths from 2020 were used. Results: The PAF attributed to EBW was similar for both cancer incidence and deaths using either the World Health Organization (WHO) Asian-Pacific region standard or a modified Asian standard, with the WHO standard yielding the lowest values. In the Korean population, the PAFs of EBW for cancer incidence were 2.96% in men and 3.61% in women, while those for cancer deaths were 0.67% in men and 3.06% in women in 2020. Additionally, PAFs showed a gradual increase in both sexes until 2030. Conclusion The EBW continues to have a significant impact on cancer incidence and deaths in Korea. Effective prevention strategies targeting the reduction of this modifiable risk factor can substantially decrease the cancer burden.