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.

Objectives: This study aimed to explore factors influencing satisfaction with medical services among medically underserved populations at the free medical clinic, providing data to improve free medical services for these populations. Methods: We employed a descriptive correlational study design involving 112 individuals (aged 19 years and older) from medically underserved populations who visited the clinic. Data were collected through face-to-face surveys from September to October 2023, and statistical analyses (t-tests, analysis of variance, Pearson correlation, and hierarchical multiple regression) were used to identify key predictors of satisfaction. Results: Perceived support from healthcare providers emerged as the strongest predictor ofsatisfaction with medical services, demonstrating a significant positive association. While socialsupport was positively correlated with perceived support from healthcare providers, it did not independently predict satisfaction. Conclusion These findings underscore the importance of healthcare provider and social supportin increasing satisfaction with medical services among medically underserved populations.Developing tailored healthcare programs and specialized healthcare provider training are essential strategies to improve healthcare access and outcomes for these vulnerable groups.

Objectives: This study aimed to explore factors influencing satisfaction with medical services among medically underserved populations at the free medical clinic, providing data to improve free medical services for these populations. Methods: We employed a descriptive correlational study design involving 112 individuals (aged 19 years and older) from medically underserved populations who visited the clinic. Data were collected through face-to-face surveys from September to October 2023, and statistical analyses (t-tests, analysis of variance, Pearson correlation, and hierarchical multiple regression) were used to identify key predictors of satisfaction. Results: Perceived support from healthcare providers emerged as the strongest predictor ofsatisfaction with medical services, demonstrating a significant positive association. While socialsupport was positively correlated with perceived support from healthcare providers, it did not independently predict satisfaction. Conclusion These findings underscore the importance of healthcare provider and social supportin increasing satisfaction with medical services among medically underserved populations.Developing tailored healthcare programs and specialized healthcare provider training are essential strategies to improve healthcare access and outcomes for these vulnerable groups.

Objectives: This study aimed to explore factors influencing satisfaction with medical services among medically underserved populations at the free medical clinic, providing data to improve free medical services for these populations. Methods: We employed a descriptive correlational study design involving 112 individuals (aged 19 years and older) from medically underserved populations who visited the clinic. Data were collected through face-to-face surveys from September to October 2023, and statistical analyses (t-tests, analysis of variance, Pearson correlation, and hierarchical multiple regression) were used to identify key predictors of satisfaction. Results: Perceived support from healthcare providers emerged as the strongest predictor ofsatisfaction with medical services, demonstrating a significant positive association. While socialsupport was positively correlated with perceived support from healthcare providers, it did not independently predict satisfaction. Conclusion These findings underscore the importance of healthcare provider and social supportin increasing satisfaction with medical services among medically underserved populations.Developing tailored healthcare programs and specialized healthcare provider training are essential strategies to improve healthcare access and outcomes for these vulnerable groups.

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.

Objectives: This study aimed to explore factors influencing satisfaction with medical services among medically underserved populations at the free medical clinic, providing data to improve free medical services for these populations. Methods: We employed a descriptive correlational study design involving 112 individuals (aged 19 years and older) from medically underserved populations who visited the clinic. Data were collected through face-to-face surveys from September to October 2023, and statistical analyses (t-tests, analysis of variance, Pearson correlation, and hierarchical multiple regression) were used to identify key predictors of satisfaction. Results: Perceived support from healthcare providers emerged as the strongest predictor ofsatisfaction with medical services, demonstrating a significant positive association. While socialsupport was positively correlated with perceived support from healthcare providers, it did not independently predict satisfaction. Conclusion These findings underscore the importance of healthcare provider and social supportin increasing satisfaction with medical services among medically underserved populations.Developing tailored healthcare programs and specialized healthcare provider training are essential strategies to improve healthcare access and outcomes for these vulnerable groups.

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.

Objectives: This study aimed to explore factors influencing satisfaction with medical services among medically underserved populations at the free medical clinic, providing data to improve free medical services for these populations. Methods: We employed a descriptive correlational study design involving 112 individuals (aged 19 years and older) from medically underserved populations who visited the clinic. Data were collected through face-to-face surveys from September to October 2023, and statistical analyses (t-tests, analysis of variance, Pearson correlation, and hierarchical multiple regression) were used to identify key predictors of satisfaction. Results: Perceived support from healthcare providers emerged as the strongest predictor ofsatisfaction with medical services, demonstrating a significant positive association. While socialsupport was positively correlated with perceived support from healthcare providers, it did not independently predict satisfaction. Conclusion These findings underscore the importance of healthcare provider and social supportin increasing satisfaction with medical services among medically underserved populations.Developing tailored healthcare programs and specialized healthcare provider training are essential strategies to improve healthcare access and outcomes for these vulnerable groups.

Background: We aimed to investigate the characteristics of pediatric ulcerative colitis (UC) at diagnosis in Korea. Methods: This was a multicenter, registry-based, inception cohort study conducted in Korea between 2021 and 2023. Children and adolescents newly diagnosed with UC < 18 years were included. Baseline clinicodemographics, results from laboratory, endoscopic exams, and Paris classification factors were collected, and associations between factors at diagnosis were investigated. Results: A total 205 patients with UC were included. Male-to-female ratio was 1.59:1, and the median age at diagnosis was 14.7 years (interquartile range 11.9–16.2). Disease extent of E1 comprised 12.2% (25/205), E2 24.9% (51/205), E3 11.2% (23/205), and E4 51.7% (106/205) of the patients. S1 comprised 13.7% (28/205) of the patients. The proportion of patients with a disease severity of S1 was significantly higher in patients with E4 compared to the other groups (E1: 0% vs. E2: 2% vs. E3: 0% vs. E4: 24.5%, P < 0.001). Significant differences between disease extent groups were also observed in Pediatric Ulcerative Colitis Activity Index (median 25 vs. 35 vs. 40 vs. 45, respectively, P < 0.001), hemoglobin (median 13.5 vs.13.2 vs. 11.6 vs. 11.4 g/dL, respectively, P < 0.001), platelet count (median 301 vs. 324 vs. 372 vs. 377 × 103 /μL, respectively, P = 0.001), C-reactive protein (median 0.05 vs. 0.10 vs. 0.17 vs. 0.38 mg/dL, respectively, P < 0.001), and Ulcerative Colitis Endoscopic Index of Severity (median 4 vs. 4 vs. 4 vs. 5, respectively, P = 0.006). No significant differences were observed in factors between groups divided according to sex and diagnosis age. Conclusion This study represents the largest multicenter pediatric inflammatory bowel disease cohort in Korea. Disease severity was associated with disease extent in pediatric patients with UC at diagnosis.