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.

Background: Dutasteride, a 5-alpha reductase inhibitor, is prescribed for male androgenetic alopecia (AGA) in Korea and Japan. Despite its efficacy, its use is limited by its long half-life, potent dihydrotestosterone suppression, and adverse effects. Objective: To investigate the efficacy and safety of 0.2 mg dutasteride for male AGA. Methods: Patients with male AGA were randomized to receive 0.2 mg dutasteride, placebo, or 0.5 mg dutasteride (2:2:1) once daily for 24 weeks. Safety and efficacy endpoints were assessed. Results: Overall, 139 men were analyzed. At week 24, the change in hair count within the target area at the vertex from baseline was significantly higher in the 0.2 mg dutasteride group than in the placebo group (21.53 vs. 5.96, p=0.0072). Dutasteride (0.2 mg) treatment led to greater hair growth improvement, as assessed by investigators at week 24 (p=0.0096) and an independent panel at weeks 12 and 24 (p=0.0306, p=0.0001). For all efficacy endpoints, 0.2 mg dutasteride was as effective as 0.5 mg dutasteride. The incidence of adverse events was low and not statistically different between the 0.2 mg dutasteride and placebo groups. The limitation of this study is the limited number of participants. Conclusion Low-dose (0.2 mg) dutasteride for male AGA showed significant efficacy and favorable safety profile.Trial Registration: ClinicalTrials.gov Identifier: NCT04825561

Canine adenovirus type 2 (CAV-2) is a common causative agent of respiratory disease in canines. There have been no reports of CAV-2 variants isolated from raccoon dogs. This study aims to investigate the biological and genetic characteristics of a novel Korean CAV-2 variant. Madin-Darby canine kidney cells were used to isolate the CAV-2 variant from 45 fecal swab samples. Diagnostic tools such as the cytopathic effect (CPE) assay, electron microscopy, polymerase chain reaction, and immunofluorescence and hemagglutination assays were used to confirm the presence of the CAV-2 isolate. A cross-virus neutralization assay was performed to verify the novelty of this CAV variant. Genetic analysis was performed using nucleotide sequences obtained through next-generation sequencing. The isolate was confirmed to be a CAV-2 variant based on the aforementioned methods and designated CAV2232. The number of bases in the fiber and E3 genes of CAV2232 were 1,626 and 414, respectively. Phylogenetic analysis of the fiber and E3 genes confirmed that CAV2232 was classified into a different clade from the known CAV-1 and CAV-2 strains. Mice inoculated with the CAV2232 vaccine developed high virus neutralization antibody titers of 1,024 (210) against CAV2232, while mice inoculated with CAV-1 and CAV-2 vaccines had low virus neutralization antibody titers of 12.9 (23.7) and 6.5 (22.7), respectively, against CAV2232. CAV2232 isolated from wild raccoon dog feces was classified as a novel CAV-2 variant. CAV2232 may therefore be used as an antigen for new vaccine development and serological investigations.

Canine adenovirus type 2 (CAV-2) is a common causative agent of respiratory disease in canines. There have been no reports of CAV-2 variants isolated from raccoon dogs. This study aims to investigate the biological and genetic characteristics of a novel Korean CAV-2 variant. Madin-Darby canine kidney cells were used to isolate the CAV-2 variant from 45 fecal swab samples. Diagnostic tools such as the cytopathic effect (CPE) assay, electron microscopy, polymerase chain reaction, and immunofluorescence and hemagglutination assays were used to confirm the presence of the CAV-2 isolate. A cross-virus neutralization assay was performed to verify the novelty of this CAV variant. Genetic analysis was performed using nucleotide sequences obtained through next-generation sequencing. The isolate was confirmed to be a CAV-2 variant based on the aforementioned methods and designated CAV2232. The number of bases in the fiber and E3 genes of CAV2232 were 1,626 and 414, respectively. Phylogenetic analysis of the fiber and E3 genes confirmed that CAV2232 was classified into a different clade from the known CAV-1 and CAV-2 strains. Mice inoculated with the CAV2232 vaccine developed high virus neutralization antibody titers of 1,024 (210) against CAV2232, while mice inoculated with CAV-1 and CAV-2 vaccines had low virus neutralization antibody titers of 12.9 (23.7) and 6.5 (22.7), respectively, against CAV2232. CAV2232 isolated from wild raccoon dog feces was classified as a novel CAV-2 variant. CAV2232 may therefore be used as an antigen for new vaccine development and serological investigations.

Canine adenovirus type 2 (CAV-2) is a common causative agent of respiratory disease in canines. There have been no reports of CAV-2 variants isolated from raccoon dogs. This study aims to investigate the biological and genetic characteristics of a novel Korean CAV-2 variant. Madin-Darby canine kidney cells were used to isolate the CAV-2 variant from 45 fecal swab samples. Diagnostic tools such as the cytopathic effect (CPE) assay, electron microscopy, polymerase chain reaction, and immunofluorescence and hemagglutination assays were used to confirm the presence of the CAV-2 isolate. A cross-virus neutralization assay was performed to verify the novelty of this CAV variant. Genetic analysis was performed using nucleotide sequences obtained through next-generation sequencing. The isolate was confirmed to be a CAV-2 variant based on the aforementioned methods and designated CAV2232. The number of bases in the fiber and E3 genes of CAV2232 were 1,626 and 414, respectively. Phylogenetic analysis of the fiber and E3 genes confirmed that CAV2232 was classified into a different clade from the known CAV-1 and CAV-2 strains. Mice inoculated with the CAV2232 vaccine developed high virus neutralization antibody titers of 1,024 (210) against CAV2232, while mice inoculated with CAV-1 and CAV-2 vaccines had low virus neutralization antibody titers of 12.9 (23.7) and 6.5 (22.7), respectively, against CAV2232. CAV2232 isolated from wild raccoon dog feces was classified as a novel CAV-2 variant. CAV2232 may therefore be used as an antigen for new vaccine development and serological investigations.

Canine adenovirus type 2 (CAV-2) is a common causative agent of respiratory disease in canines. There have been no reports of CAV-2 variants isolated from raccoon dogs. This study aims to investigate the biological and genetic characteristics of a novel Korean CAV-2 variant. Madin-Darby canine kidney cells were used to isolate the CAV-2 variant from 45 fecal swab samples. Diagnostic tools such as the cytopathic effect (CPE) assay, electron microscopy, polymerase chain reaction, and immunofluorescence and hemagglutination assays were used to confirm the presence of the CAV-2 isolate. A cross-virus neutralization assay was performed to verify the novelty of this CAV variant. Genetic analysis was performed using nucleotide sequences obtained through next-generation sequencing. The isolate was confirmed to be a CAV-2 variant based on the aforementioned methods and designated CAV2232. The number of bases in the fiber and E3 genes of CAV2232 were 1,626 and 414, respectively. Phylogenetic analysis of the fiber and E3 genes confirmed that CAV2232 was classified into a different clade from the known CAV-1 and CAV-2 strains. Mice inoculated with the CAV2232 vaccine developed high virus neutralization antibody titers of 1,024 (210) against CAV2232, while mice inoculated with CAV-1 and CAV-2 vaccines had low virus neutralization antibody titers of 12.9 (23.7) and 6.5 (22.7), respectively, against CAV2232. CAV2232 isolated from wild raccoon dog feces was classified as a novel CAV-2 variant. CAV2232 may therefore be used as an antigen for new vaccine development and serological investigations.

Canine adenovirus type 2 (CAV-2) is a common causative agent of respiratory disease in canines. There have been no reports of CAV-2 variants isolated from raccoon dogs. This study aims to investigate the biological and genetic characteristics of a novel Korean CAV-2 variant. Madin-Darby canine kidney cells were used to isolate the CAV-2 variant from 45 fecal swab samples. Diagnostic tools such as the cytopathic effect (CPE) assay, electron microscopy, polymerase chain reaction, and immunofluorescence and hemagglutination assays were used to confirm the presence of the CAV-2 isolate. A cross-virus neutralization assay was performed to verify the novelty of this CAV variant. Genetic analysis was performed using nucleotide sequences obtained through next-generation sequencing. The isolate was confirmed to be a CAV-2 variant based on the aforementioned methods and designated CAV2232. The number of bases in the fiber and E3 genes of CAV2232 were 1,626 and 414, respectively. Phylogenetic analysis of the fiber and E3 genes confirmed that CAV2232 was classified into a different clade from the known CAV-1 and CAV-2 strains. Mice inoculated with the CAV2232 vaccine developed high virus neutralization antibody titers of 1,024 (210) against CAV2232, while mice inoculated with CAV-1 and CAV-2 vaccines had low virus neutralization antibody titers of 12.9 (23.7) and 6.5 (22.7), respectively, against CAV2232. CAV2232 isolated from wild raccoon dog feces was classified as a novel CAV-2 variant. CAV2232 may therefore be used as an antigen for new vaccine development and serological investigations.