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: 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.

Aplastic anemia, mental retardation, and dwarfism (AMeD) syndrome, also known as aldehyde degradation deficiency (ADD) syndrome, is an autosomal recessive disorder caused by mutations in the ALDH2 and ADH5 genes, leading to decreased activity of the aldehyde dehydrogenase 2 (ALDH2) and alcohol dehydrogenase 5 (ADH5) enzymes, subsequently triggering enhanced cellular levels of formaldehyde and diverse multisystem manifestations. Herein, we present the case of a 7-year-old girl with AMeD syndrome, characterized by pancytopenia, developmental delay, microcephaly, epilepsy, and myelodysplastic syndrome. Whole-exome sequencing revealed compound heterozygous variants (c.832G＞C and c.678delA) in the ADH5 gene and a heterozygous pathogenic variant (c.1510G＞A) in the ALDH2 gene. This case underscores the complexity of AMeD syndrome, emphasizing the importance of genetic testing to ensure diagnosis and aid in the development of potential targeted therapeutic approaches.

Purpose: The purpose of this study was to explore and assess the experiences of cancer patients and their caregivers who had been admitted to comprehensive nursing care service wards. Methods: Data were collected from 10 patients and 10 caregivers by in-depth interviews. The data were analyzed using content analysis of Downe-Wamboldt. Results: Three categories and seven subcategories were extracted. 1) Realizing institutional limitations of comprehensive nursing care service: ‘Wishing for precise operating systems based on patient severity,’ ‘Anticipating active caregiver participation in treatment process,’ ‘Requiring a countermeasure for safety accidents,’ 2) Professional nursing service which provides relief: ‘Patient-centered professional nursing service,’ ‘Inpatient service that provides relief for patients and caregivers,’ 3) Anticipating continuous use of the service: ‘Inpatient service which users are willing to reuse,’ ‘Wishing for expansion and reinforcement of the service.’ Conclusion Cancer patients and their caregivers experienced institutional limitations while satisfied with professional nursing service and willing to reuse the service. To improve this situation, institutional support such as separate wards for severe patients, measures for active caregiver participation and prevention of safety accidents, and adequate staffing would be helpful for relatively severe level cancer patients and their caregivers.

Purpose: This study aimed to examine general nurses' nursing leadership in patient care using focus group interviews. Methods: This study was conducted after obtaining approval from the ethics committee of a university.After completing a focus group interview with 13 general nurses working at a general hospital, we performed qualitative content analysis according to Kreuger's guidelines. Results: A total of 170 meaningful statement units of nursing leadership that appeared in the clinical experience of general nurses were extracted, and 10 final sub-themes and the three themes connecting them were derived. The themes derived were “leading patients into nursing,” “experiencing the power of growth,” and “facilitating situations that allow focus on patient care.” Conclusion This study helps in understanding the nursing leadership of general nurses in patient care. To encourage general nurses to exert their nursing leadership and grow as autonomous nurses, nursing educators must appropriately present the learning outcomes and content of nursing leadership. Additionally, in the clinical setting, organizational support is necessary to foster understanding and the demonstration of general nurses' nursing leadership.

Purpose: The aim was to develop guidelines for delegating nursing tasks among nurses in integrated nursing care wards. Methods: This was a methodological approach. Literature reviews were conducted on delegation policies and practices for nurses in Korea and other countries to explore the area of nursing delegation. Focus group interviews were performed with nurses to identify the strength and weakness of the delegation of nursing tasks in clinical practice, and qualitative content analysis was conducted based on the interview. Ten areas and 115 items were derived through these steps, and their validity was confirmed using the Delphi technique. Results: The delegation guidelines of nursing tasks consisted of nine domains, 21 sub-categories, and 101 items, including Nurses and nursing assistants' duties, the necessity of delegation, definition of terms, scope of delegation, considerations for delegation, procedure, characteristics, and principles of delegation, and educational content for delegation. Conclusion These guidelines can help nurses to make decisions about delegating nursing tasks according to the delegation procedure.Education on the delegation of nursing tasks is necessary for both nurses and nursing assistants. The guidelines developed in this study can serve as a standard for delegating nursing tasks to ensure patient safety.

Purpose: This study aimed to examine general nurses' nursing leadership in patient care using focus group interviews. Methods: This study was conducted after obtaining approval from the ethics committee of a university.After completing a focus group interview with 13 general nurses working at a general hospital, we performed qualitative content analysis according to Kreuger's guidelines. Results: A total of 170 meaningful statement units of nursing leadership that appeared in the clinical experience of general nurses were extracted, and 10 final sub-themes and the three themes connecting them were derived. The themes derived were “leading patients into nursing,” “experiencing the power of growth,” and “facilitating situations that allow focus on patient care.” Conclusion This study helps in understanding the nursing leadership of general nurses in patient care. To encourage general nurses to exert their nursing leadership and grow as autonomous nurses, nursing educators must appropriately present the learning outcomes and content of nursing leadership. Additionally, in the clinical setting, organizational support is necessary to foster understanding and the demonstration of general nurses' nursing leadership.

Purpose: The aim was to develop guidelines for delegating nursing tasks among nurses in integrated nursing care wards. Methods: This was a methodological approach. Literature reviews were conducted on delegation policies and practices for nurses in Korea and other countries to explore the area of nursing delegation. Focus group interviews were performed with nurses to identify the strength and weakness of the delegation of nursing tasks in clinical practice, and qualitative content analysis was conducted based on the interview. Ten areas and 115 items were derived through these steps, and their validity was confirmed using the Delphi technique. Results: The delegation guidelines of nursing tasks consisted of nine domains, 21 sub-categories, and 101 items, including Nurses and nursing assistants' duties, the necessity of delegation, definition of terms, scope of delegation, considerations for delegation, procedure, characteristics, and principles of delegation, and educational content for delegation. Conclusion These guidelines can help nurses to make decisions about delegating nursing tasks according to the delegation procedure.Education on the delegation of nursing tasks is necessary for both nurses and nursing assistants. The guidelines developed in this study can serve as a standard for delegating nursing tasks to ensure patient safety.