Purpose: Unnecessary prostate biopsies for detecting prostate cancer (PCa) should be minimized. Therefore, this study developed a machine learning (ML) model to predict PCa in Korean men and evaluated its usability. Materials and Methods: We retrospectively analyzed clinical data from 928 patients who underwent prostate biopsies at Kangwon National University Hospital between May 2013 and May 2023. Of these, 377 (41.6%) were diagnosed with PCa, and 551 (59.4%) did not have cancer. For external validation, clinical data from 385 patients aged 48–89 years who underwent prostate biopsies from September 2005 to September 2023 at Wonju Severance Christian Hospital were also included. Twenty-two clinical features were used to develop an ML model to predict PCa. Features were selected based on their contributions to model performance, leading to the inclusion of 15 features. A meta-learner was constructed using logistic regression to predict the probability of PCa, and the classifier was trained and validated on randomly extracted training and test sets at an 8:2 ratio. Results: The prostate health index, prostate volume, age, nodule on digital rectal examination, and prostate-specific antigen were the top 5 features for predicting PCa. The area under the receiver operating characteristic curve (AUC) of the meta-learner logistic regression model was 0.89, and the accuracy, sensitivity, and specificity were 0.828, 0.711, and 0.909, respectively. Our model also showed excellent prediction performance for high-grade PCa, with a Gleason score of 7 or higher and an AUC of 0.903. Furthermore, we evaluated the performance of the model using external cohort clinical data and achieved an AUC of 0.863. Conclusions Our ML model excelled in predicting PCa, specifically clinically significant PCa. Although extensive cross-validation in other clinical cohorts is needed, this ML model is a promising option for future diagnostics.

Purpose: Unnecessary prostate biopsies for detecting prostate cancer (PCa) should be minimized. Therefore, this study developed a machine learning (ML) model to predict PCa in Korean men and evaluated its usability. Materials and Methods: We retrospectively analyzed clinical data from 928 patients who underwent prostate biopsies at Kangwon National University Hospital between May 2013 and May 2023. Of these, 377 (41.6%) were diagnosed with PCa, and 551 (59.4%) did not have cancer. For external validation, clinical data from 385 patients aged 48–89 years who underwent prostate biopsies from September 2005 to September 2023 at Wonju Severance Christian Hospital were also included. Twenty-two clinical features were used to develop an ML model to predict PCa. Features were selected based on their contributions to model performance, leading to the inclusion of 15 features. A meta-learner was constructed using logistic regression to predict the probability of PCa, and the classifier was trained and validated on randomly extracted training and test sets at an 8:2 ratio. Results: The prostate health index, prostate volume, age, nodule on digital rectal examination, and prostate-specific antigen were the top 5 features for predicting PCa. The area under the receiver operating characteristic curve (AUC) of the meta-learner logistic regression model was 0.89, and the accuracy, sensitivity, and specificity were 0.828, 0.711, and 0.909, respectively. Our model also showed excellent prediction performance for high-grade PCa, with a Gleason score of 7 or higher and an AUC of 0.903. Furthermore, we evaluated the performance of the model using external cohort clinical data and achieved an AUC of 0.863. Conclusions Our ML model excelled in predicting PCa, specifically clinically significant PCa. Although extensive cross-validation in other clinical cohorts is needed, this ML model is a promising option for future diagnostics.

Purpose: Unnecessary prostate biopsies for detecting prostate cancer (PCa) should be minimized. Therefore, this study developed a machine learning (ML) model to predict PCa in Korean men and evaluated its usability. Materials and Methods: We retrospectively analyzed clinical data from 928 patients who underwent prostate biopsies at Kangwon National University Hospital between May 2013 and May 2023. Of these, 377 (41.6%) were diagnosed with PCa, and 551 (59.4%) did not have cancer. For external validation, clinical data from 385 patients aged 48–89 years who underwent prostate biopsies from September 2005 to September 2023 at Wonju Severance Christian Hospital were also included. Twenty-two clinical features were used to develop an ML model to predict PCa. Features were selected based on their contributions to model performance, leading to the inclusion of 15 features. A meta-learner was constructed using logistic regression to predict the probability of PCa, and the classifier was trained and validated on randomly extracted training and test sets at an 8:2 ratio. Results: The prostate health index, prostate volume, age, nodule on digital rectal examination, and prostate-specific antigen were the top 5 features for predicting PCa. The area under the receiver operating characteristic curve (AUC) of the meta-learner logistic regression model was 0.89, and the accuracy, sensitivity, and specificity were 0.828, 0.711, and 0.909, respectively. Our model also showed excellent prediction performance for high-grade PCa, with a Gleason score of 7 or higher and an AUC of 0.903. Furthermore, we evaluated the performance of the model using external cohort clinical data and achieved an AUC of 0.863. Conclusions Our ML model excelled in predicting PCa, specifically clinically significant PCa. Although extensive cross-validation in other clinical cohorts is needed, this ML model is a promising option for future diagnostics.

OBJECTIVES: The purpose of this study was to assess the effectiveness of human papillomavirus (HPV) vaccination administered to adolescent girls through Korea’s National Immunization Program. METHODS: This retrospective cohort study included patients who were 12-13 years old, whether vaccinated or unvaccinated, between July 2016 and December 2017. The incidence of genital warts (GWs) was monitored through 2021. Time-stratified hazard ratios (HRs) were estimated, adjusting for birth year, socioeconomic status, and the level of urbanization of the region, and were presented with 95% confidence intervals (CIs). Data were sourced from the Immunization Registry Integration System, linked with the National Health Information Database. RESULTS: The study included 332,062 adolescent girls, with an average follow-up period of approximately 4.6 years. Except for the first year, the HRs for the vaccinated group were lower than those for the unvaccinated group. The HRs for specific cut-off years were as follows: year 2, 0.62 (95% CI, 0.31 to 1.13); year 3, 0.58 (95% CI, 0.35 to 0.96); and year 4 and beyond, 0.39 (95% CI, 0.28 to 0.52). CONCLUSIONS Our findings indicate that HPV vaccination was associated with a reduction in the risk of GWs among adolescent girls. Notably, this reduction became significant as the incidence of GWs increased with age.

Background/Aims: Palliative chemotherapy (PC) is not standardized for patients with advanced ampulla of Vater adenocarcinoma (AA). This multicenter, retrospective study evaluated first-line PC outcomes in patients with AA. Methods: Patients diagnosed with AA between January 2010 and December 2020 who underwent PC were enrolled from 10 institutions. Overall survival (OS) and progression-free survival (PFS) according to the chemotherapy regimen were analyzed. Results: Of 255 patients (mean age, 64.0±10.0 years; male, 57.6%), 14 (5.5%) had locally advanced AA and 241 (94.5%) had metastatic AA. Gemcitabine plus cisplatin (GP) was administered as first-line chemotherapy to 192 patients (75.3%), whereas capecitabine plus oxaliplatin (CAPOX) was administered to 39 patients (15.3%). The median OS of all patients was 19.8 months (95% confidence interval [CI], 17.3 to 22.3), and that of patients who received GP and CAPOX was 20.4 months (95% CI, 17.2 to 23.6) and 16.0 months (95% CI, 11.2 to 20.7), respectively. The median PFS of GP and CAPOX patients were 8.4 months (95% CI, 7.1 to 9.7) and 5.1 months (95% CI, 2.5 to 7.8), respectively. PC for AA demonstrated improved median outcomes in both OS and PFS compared to conventional bile duct cancers that included AA. Conclusions While previous studies have shown mixed prognostic outcomes when AA was analyzed together with other biliary tract cancers, our study unveils a distinct clinical prognosis specific to AA on a large scale with systemic anticancer therapy. These findings suggest that AA is a distinct type of tumor, different from other biliary tract cancers, and AA itself could be expected to have a favorable response to PC.

Objective: The Scales for Outcomes in Parkinson’s Disease–Cognition (SCOPA-Cog) was developed to assess cognition in patients with Parkinson’s disease (PD). In this study, we aimed to evaluate the validity and reliability of the Korean version of the SCOPACog (K-SCOPA-Cog). Methods: We enrolled 129 PD patients with movement disorders from 31 clinics in South Korea. The original version of the SCOPA-Cog was translated into Korean using the translation-retranslation method. The test–retest method with an intraclass correlation coefficient (ICC) and Cronbach’s alpha coefficient were used to assess reliability. Spearman’s rank correlation analysis with the Montreal Cognitive Assessment-Korean version (MOCA-K) and the Korean Mini-Mental State Examination (K-MMSE) were used to assess concurrent validity. Results: The Cronbach’s alpha coefficient was 0.797, and the ICC was 0.887. Spearman’s rank correlation analysis revealed a significant correlation with the K-MMSE and MOCA-K scores (r = 0.546 and r = 0.683, respectively). Conclusion Our results demonstrate that the K-SCOPA-Cog has good reliability and validity.

Background: Brain metastases of peri-Rolandic area is crucial as it directly impacts the quality of life for cancer patients. Surgery or stereotactic radiosurgery (SRS) is considered for peri-Rolandic brain metastases as for other brain metastases. However, the benefit of each treatment modality on functional outcome has not been clearly defined for this tumor. The purpose of this study is to compare the functional course of each treatment and to suggest an effective treatment for patients’ quality of life. Methods: Fifty-two patients who had undergone SRS or surgery for brain metastasis confirmedby enhanced MRI were enrolled retrospectively. Overall survival (OS), progression free survival (PFS), and functional outcomes were estimated using the Kaplan-Meier method, univariate, multivariate analysis, and Cox proportional hazards regression. Results: Median OS and PFS were 13.3 months and 8.9 months in our study population.Treatment modalities were not significant factors for OS and PFS. Extracranial systemic cancer progression was significant factor for both parameters (p=0.030 for OS and p=0.040 for PFS). Median symptom improvement (improvement of at least 1 grade after surgery compared to preoperative state) time was significantly shorter in surgery group than in the SRS group (10.5 days vs. 37.5 days, p=0.034). Conclusion Surgery for brain metastases can contribute to a positive quality of life for the remain-ing duration of the patient’s life.

Background/Aims: The ursodeoxycholic acid (UDCA) response score (URS) was developed to identify poor responders to UDCA before treatment, in order to offer timely and proactive intervention. However, validation of the URS in Asian population is warranted. Methods: A total of 173 Asian patients diagnosed with primary biliary cholangitis (PBC) between 2007 and 2016 at seven academic institutions in Korea who started UDCA treatment were analyzed to validate the performance of URS. UDCA response was defined as an alkaline phosphatase level less than 1.67 times the upper limit of normal after 1-year of UDCA treatment. In addition, prognostic performance of URS for liver-related events, defined as newly developed hepatic decompensation or hepatocellular carcinoma was evaluated. Results: After 1 year of UDCA treatment, 133 patients (76.9%) achieved UDCA response. UDCAresponse rate was 98.7% for those with URS ≥1.41 (n=76) and 58.8% for those with URS <1.41(n=97). The area under the receiver operating characteristic curve of URS in predicting UDCAresponse was 0.84 (95% confidence interval, 0.78 to 0.88). During a median follow-up of 6.5years, liver-related events developed in 18 patients (10.4%). Among 117 patients with PBC stage I-III by histological evaluation, the 5-year liver-related event-free survival rate differed accordingto the URS; 100% for URS ≥1.41 and 86.5% for URS <1.41 (p=0.005). Conclusions URS demonstrated good performance in predicting a UDCA treatment response in Asian PBC patients. In addition, the risk of liver-related events differed according to the URS for the PBC stage. Thus, URS can be used to predict the response and clinical outcome in patients with PBC.

The new Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equations without a race coefficient have gained recognition across the United States. We aimed to test whether these new equations performed well in Korean patients with chronic kidney disease (CKD). Methods: This study included 2,149 patients with CKD G1–G5 without kidney replacement therapy from the Korean Cohort Study for Outcome in Patients with CKD (KNOW-CKD). The estimated glomerular filtration rate (eGFR) was calculated using the new CKD-EPI equations with serum creatinine and cystatin C. The primary outcome was 5-year risk of kidney failure with replacement therapy (KFRT). Results: When we adopted the new creatinine equation [eGFRcr (NEW)], 81 patients (23.1%) with CKD G3a based on the current creatinine equation (eGFRcr) were reclassified as CKD G2. Accordingly, the number of patients with eGFR of <60 mL/min/1.73 m2 decreased from 1,393 (64.8%) to 1,312 (61.1%). The time-dependent area under the receiver operating characteristic curve for 5-year KFRT risk was comparable between the eGFRcr (NEW) (0.941; 95% confidence interval [CI], 0.922–0.960) and eGFRcr (0.941; 95% CI, 0.922–0.961). The eGFRcr (NEW) showed slightly better discrimination and reclassification than the eGFRcr. However, the new creatinine and cystatin C equation [eGFRcr-cys (NEW)] performed similarly to the current creatinine and cystatin C equation. Furthermore, eGFRcr-cys (NEW) did not show better performance for KFRT risk than eGFRcr (NEW). Conclusion: Both the current and the new CKD-EPI equations showed excellent predictive performance for 5-year KFRT risk in Korean patients with CKD. These new equations need to be further tested for other clinical outcomes in Koreans.

Objective: Extramammary Paget’s disease (EMPD) of the vulva is a rare disease which predominantly presents in postmenopausal Caucasian women. As yet, no studies on Asian female patients with EMPD have been performed. This study aimed to identify the clinical features of patients with vulvar EMPD in Korea, and to evaluate the risk factors of recurrence and postoperative complications in surgically treated EMPD. Methods: We retrospectively reviewed 47 patients with vulvar EMPD who underwent wide local excision or radical vulvectomy. The clinical data and surgical and oncological outcomes following surgery were extracted from medical records and analyzed. Univariate and multivariate analyses for predicting recurrence and postoperative complications were performed. Results: 21.3% of patients had complications after surgery, and wound dehiscence was the most common. 14.9% of patients experienced recurrence, and the median interval to recurrence from initial treatment was 69 (range 33–169) months. Vulvar lesions larger than 40 mm was the independent risk factor of postoperative complications (odds ratio [OR]=7.259; 95% confidence interval [CI]=1.545–34.100; p=0.012). Surgical margin status was not associated with recurrence in surgically treated vulvar EMPD patients (OR=0.83; 95% CI=0.16–4.19; p=1.000). Conclusion Positive surgical margin is a frequent finding in the patients with vulvar EMPD, but disease recurrence is not related with surgical margin status. Since EMPD is a slow growing tumor, a surveillance period longer than 5 years is required.