Background: Lifestyle-related factors have been studied as a fundamental aspect in the onset and progression of type 2 diabetes mellitus. However, behavioral factors are easily overlooked in clinical practice. This study investigated whether lifestyle changes were associated with diabetes remission in newly diagnosed type 2 diabetes patients. Methods: We enrolled patients with new-onset type 2 diabetes from 2009 to 2012 using a health examination cohort from the Korean National Health Insurance Service (KNHIS).Remission was defined as a fasting glucose level less than 126 mg/dL at least once during a health examination after stopping medication. A self-administered questionnaire was used to investigate patients’ lifestyles. We investigated smoking, alcohol consumption, and regular exercise before and after starting diabetes medication and the odds ratios (ORs) of logistic regression on remission to evaluate the associations. Results: A total of 138,211 patients diagnosed with type 2 diabetes from 2009 to 2012 were analyzed, and 8,192 (6.3%) reported remission during the follow-up period to 2017. Baseline fasting blood glucose level measured before starting diabetes medication was significantly higher in the non-remission group (180 mg/dL vs. 159 mg/dL, P < 0.001). In addition, the use rate of combined oral hypoglycemic agent treatment was higher in the non-remission group (15% vs. 8%, P < 0.001). Consistent smoking and drinking showed negative associations with remission (OR, 0.72; 95% confidence interval [CI], 0.67–0.77 and OR, 0.90; 95% CI, 0.84– 0.95, respectively), and initiation of regular exercise presented a positive association with remission (OR, 1.54; 95% CI, 0.46–1.63). Abstinence from alcohol increased the likelihood of remission in the male population (OR, 1.20; 95% CI, 1.10–1.32). The association with smoking history or smoking cessation was not clear, but new smoking behavior interfered with remission in women (OR, 0.48; 95% CI, 0.28–0.81). Conclusion We confirmed associations between a healthy lifestyle and diabetic remission in new-onset type 2 diabetes patients. The results of this study suggest that improving lifestyle after diabetes diagnosis may contribute to disease remission.

Background: Lifestyle-related factors have been studied as a fundamental aspect in the onset and progression of type 2 diabetes mellitus. However, behavioral factors are easily overlooked in clinical practice. This study investigated whether lifestyle changes were associated with diabetes remission in newly diagnosed type 2 diabetes patients. Methods: We enrolled patients with new-onset type 2 diabetes from 2009 to 2012 using a health examination cohort from the Korean National Health Insurance Service (KNHIS).Remission was defined as a fasting glucose level less than 126 mg/dL at least once during a health examination after stopping medication. A self-administered questionnaire was used to investigate patients’ lifestyles. We investigated smoking, alcohol consumption, and regular exercise before and after starting diabetes medication and the odds ratios (ORs) of logistic regression on remission to evaluate the associations. Results: A total of 138,211 patients diagnosed with type 2 diabetes from 2009 to 2012 were analyzed, and 8,192 (6.3%) reported remission during the follow-up period to 2017. Baseline fasting blood glucose level measured before starting diabetes medication was significantly higher in the non-remission group (180 mg/dL vs. 159 mg/dL, P < 0.001). In addition, the use rate of combined oral hypoglycemic agent treatment was higher in the non-remission group (15% vs. 8%, P < 0.001). Consistent smoking and drinking showed negative associations with remission (OR, 0.72; 95% confidence interval [CI], 0.67–0.77 and OR, 0.90; 95% CI, 0.84– 0.95, respectively), and initiation of regular exercise presented a positive association with remission (OR, 1.54; 95% CI, 0.46–1.63). Abstinence from alcohol increased the likelihood of remission in the male population (OR, 1.20; 95% CI, 1.10–1.32). The association with smoking history or smoking cessation was not clear, but new smoking behavior interfered with remission in women (OR, 0.48; 95% CI, 0.28–0.81). Conclusion We confirmed associations between a healthy lifestyle and diabetic remission in new-onset type 2 diabetes patients. The results of this study suggest that improving lifestyle after diabetes diagnosis may contribute to disease remission.

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: 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: Lifestyle-related factors have been studied as a fundamental aspect in the onset and progression of type 2 diabetes mellitus. However, behavioral factors are easily overlooked in clinical practice. This study investigated whether lifestyle changes were associated with diabetes remission in newly diagnosed type 2 diabetes patients. Methods: We enrolled patients with new-onset type 2 diabetes from 2009 to 2012 using a health examination cohort from the Korean National Health Insurance Service (KNHIS).Remission was defined as a fasting glucose level less than 126 mg/dL at least once during a health examination after stopping medication. A self-administered questionnaire was used to investigate patients’ lifestyles. We investigated smoking, alcohol consumption, and regular exercise before and after starting diabetes medication and the odds ratios (ORs) of logistic regression on remission to evaluate the associations. Results: A total of 138,211 patients diagnosed with type 2 diabetes from 2009 to 2012 were analyzed, and 8,192 (6.3%) reported remission during the follow-up period to 2017. Baseline fasting blood glucose level measured before starting diabetes medication was significantly higher in the non-remission group (180 mg/dL vs. 159 mg/dL, P < 0.001). In addition, the use rate of combined oral hypoglycemic agent treatment was higher in the non-remission group (15% vs. 8%, P < 0.001). Consistent smoking and drinking showed negative associations with remission (OR, 0.72; 95% confidence interval [CI], 0.67–0.77 and OR, 0.90; 95% CI, 0.84– 0.95, respectively), and initiation of regular exercise presented a positive association with remission (OR, 1.54; 95% CI, 0.46–1.63). Abstinence from alcohol increased the likelihood of remission in the male population (OR, 1.20; 95% CI, 1.10–1.32). The association with smoking history or smoking cessation was not clear, but new smoking behavior interfered with remission in women (OR, 0.48; 95% CI, 0.28–0.81). Conclusion We confirmed associations between a healthy lifestyle and diabetic remission in new-onset type 2 diabetes patients. The results of this study suggest that improving lifestyle after diabetes diagnosis may contribute to disease remission.