Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Background: Group B Streptococcus (GBS) is one of the leading causes of neonatal earlyonset sepsis, resulting in high mortality and significant comorbidity. Intrapartum penicillin prophylaxis is recommended for pregnant women with GBS colonization to prevent vertical transmission. For pregnant women at high risk of anaphylaxis to penicillin, clindamycin is recommended only if the susceptibility of GBS isolates has been identified. We retrospectively examined the GBS detection rate and clindamycin resistance among Korean women of reproductive age over the last 20 years. Methods: Microbiologic studies using vaginal, vaginal–rectal or vaginal–perianal swabs from female patients 15–49 years of age during 2003–2022 were reviewed. Annual GBS detection rates and clindamycin resistance rates were calculated. The study period was divided into two periods (period 1, 2003–2015; period 2, 2016–2022) based on the introduction of universal culture-based GBS screening in our center in 2016. GBS detection rates and clindamycin resistance rates were compared between the periods using χ2 tests. Results: A total of 14,571 women were tested 16,879 times and GBS was isolated in 1,054 tests (6.2%), with 423 clindamycin-resistant isolates (40.1%). The GBS detection rate increased from 3.4% (301/8,869) in period 1 to 9.4% (2,753/8,010) in period 2 (P < 0.001). Even during period 1, the GBS detection rate was higher in 2009–2015 compared to 2003–2008 (P < 0.001). Clindamycin resistance rates have remained at similar levels since 2009, which were 39.5% (199/301) in period 1 and 40.2% (303/753) in period 2 (P = 0.833). Conclusion This study demonstrated that GBS detection rates in Korean women of reproductive age significantly increased almost three times during the twenty years of the study period, with a persistently high clindamycin resistance rate of up to 40%.

Background: Group B Streptococcus (GBS) is one of the leading causes of neonatal earlyonset sepsis, resulting in high mortality and significant comorbidity. Intrapartum penicillin prophylaxis is recommended for pregnant women with GBS colonization to prevent vertical transmission. For pregnant women at high risk of anaphylaxis to penicillin, clindamycin is recommended only if the susceptibility of GBS isolates has been identified. We retrospectively examined the GBS detection rate and clindamycin resistance among Korean women of reproductive age over the last 20 years. Methods: Microbiologic studies using vaginal, vaginal–rectal or vaginal–perianal swabs from female patients 15–49 years of age during 2003–2022 were reviewed. Annual GBS detection rates and clindamycin resistance rates were calculated. The study period was divided into two periods (period 1, 2003–2015; period 2, 2016–2022) based on the introduction of universal culture-based GBS screening in our center in 2016. GBS detection rates and clindamycin resistance rates were compared between the periods using χ2 tests. Results: A total of 14,571 women were tested 16,879 times and GBS was isolated in 1,054 tests (6.2%), with 423 clindamycin-resistant isolates (40.1%). The GBS detection rate increased from 3.4% (301/8,869) in period 1 to 9.4% (2,753/8,010) in period 2 (P < 0.001). Even during period 1, the GBS detection rate was higher in 2009–2015 compared to 2003–2008 (P < 0.001). Clindamycin resistance rates have remained at similar levels since 2009, which were 39.5% (199/301) in period 1 and 40.2% (303/753) in period 2 (P = 0.833). Conclusion This study demonstrated that GBS detection rates in Korean women of reproductive age significantly increased almost three times during the twenty years of the study period, with a persistently high clindamycin resistance rate of up to 40%.

Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Background: Group B Streptococcus (GBS) is one of the leading causes of neonatal earlyonset sepsis, resulting in high mortality and significant comorbidity. Intrapartum penicillin prophylaxis is recommended for pregnant women with GBS colonization to prevent vertical transmission. For pregnant women at high risk of anaphylaxis to penicillin, clindamycin is recommended only if the susceptibility of GBS isolates has been identified. We retrospectively examined the GBS detection rate and clindamycin resistance among Korean women of reproductive age over the last 20 years. Methods: Microbiologic studies using vaginal, vaginal–rectal or vaginal–perianal swabs from female patients 15–49 years of age during 2003–2022 were reviewed. Annual GBS detection rates and clindamycin resistance rates were calculated. The study period was divided into two periods (period 1, 2003–2015; period 2, 2016–2022) based on the introduction of universal culture-based GBS screening in our center in 2016. GBS detection rates and clindamycin resistance rates were compared between the periods using χ2 tests. Results: A total of 14,571 women were tested 16,879 times and GBS was isolated in 1,054 tests (6.2%), with 423 clindamycin-resistant isolates (40.1%). The GBS detection rate increased from 3.4% (301/8,869) in period 1 to 9.4% (2,753/8,010) in period 2 (P < 0.001). Even during period 1, the GBS detection rate was higher in 2009–2015 compared to 2003–2008 (P < 0.001). Clindamycin resistance rates have remained at similar levels since 2009, which were 39.5% (199/301) in period 1 and 40.2% (303/753) in period 2 (P = 0.833). Conclusion This study demonstrated that GBS detection rates in Korean women of reproductive age significantly increased almost three times during the twenty years of the study period, with a persistently high clindamycin resistance rate of up to 40%.

Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Background: Group B Streptococcus (GBS) is one of the leading causes of neonatal earlyonset sepsis, resulting in high mortality and significant comorbidity. Intrapartum penicillin prophylaxis is recommended for pregnant women with GBS colonization to prevent vertical transmission. For pregnant women at high risk of anaphylaxis to penicillin, clindamycin is recommended only if the susceptibility of GBS isolates has been identified. We retrospectively examined the GBS detection rate and clindamycin resistance among Korean women of reproductive age over the last 20 years. Methods: Microbiologic studies using vaginal, vaginal–rectal or vaginal–perianal swabs from female patients 15–49 years of age during 2003–2022 were reviewed. Annual GBS detection rates and clindamycin resistance rates were calculated. The study period was divided into two periods (period 1, 2003–2015; period 2, 2016–2022) based on the introduction of universal culture-based GBS screening in our center in 2016. GBS detection rates and clindamycin resistance rates were compared between the periods using χ2 tests. Results: A total of 14,571 women were tested 16,879 times and GBS was isolated in 1,054 tests (6.2%), with 423 clindamycin-resistant isolates (40.1%). The GBS detection rate increased from 3.4% (301/8,869) in period 1 to 9.4% (2,753/8,010) in period 2 (P < 0.001). Even during period 1, the GBS detection rate was higher in 2009–2015 compared to 2003–2008 (P < 0.001). Clindamycin resistance rates have remained at similar levels since 2009, which were 39.5% (199/301) in period 1 and 40.2% (303/753) in period 2 (P = 0.833). Conclusion This study demonstrated that GBS detection rates in Korean women of reproductive age significantly increased almost three times during the twenty years of the study period, with a persistently high clindamycin resistance rate of up to 40%.

Background: and Purpose The wearing-off (WO) phenomenon is the most common motor complication in advanced Parkinson’s disease (PD), but its identification remains challenging. The 9- and 19-item Wearing-off Questionnaires (WOQ-9 and WOQ-19) are self-assessment tools for motor and nonmotor symptoms that are widely used for WO screening. We produced Korean versions of the WOQ-19 and WOQ-9 (K-WOQ-19 and K-WOQ-9) and investigated their validity and reliability. Methods: We used the translation–back translation method to produce K-WOQ-19 and KWOQ-9, which were self-administered by 124 patients with PD. We conducted in-depth 10-minute interviews for confirming the presence of the WO phenomenon, and then stratified the participants into groups with and without WO. Diagnostic accuracy was assessed by analyzing receiver operating characteristic curves. Concurrent validity was assessed using the Movement Disorder Society–Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) and the Hoehn and Yahr stage with Spearman’s rank correlation analysis. Reliability was assessed based on test–retest Cohen’s kappa (κ) values and intraclass correlation coefficients (ICCs). Results: The optimal cutoff scores on the K-WOQ-19 and K-WOQ-9 for WO screening were 4 and 2, respectively. The test–retest ICCs of K-WOQ-19 and K-WOQ-9 were 0.943 and 0.938, respectively. Nineteen of the combined 20 items in K-WOQ-19 and K-WOQ-9 showed moderate-to-substantial agreement (κ=0.412–0.771, p<0.001). The scores on the translated scales were significantly correlated with MDS-UPDRS IV scores. Conclusions K-WOQ-19 and K-WOQ-9 are reliable and valid tools for detecting WO, with optimal cutoff scores of 4 and 2, respectively.

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.