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.

We updated the Korean Society of Gynecologic Oncology (KSGO) practice guideline for the management of ovarian cancer as version 5.1. The ovarian cancer guideline team of the KSGO published announced the fifth version (version 5.0) of its clinical practice guidelines for the management of ovarian cancer in December 2023. In version 5.0, the selection of the key questions and the systematic reviews were based on the data available up to December 2022.Therefore, we updated the guidelines version 5.0 with newly accumulated clinical data and added 5 new key questions reflecting the latest insights in the field of ovarian cancer between 2023 and 2024. For each question, recommendation was provided together with corresponding level of evidence and grade of recommendation, all established through expert consensus.

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.

We updated the Korean Society of Gynecologic Oncology (KSGO) practice guideline for the management of ovarian cancer as version 5.1. The ovarian cancer guideline team of the KSGO published announced the fifth version (version 5.0) of its clinical practice guidelines for the management of ovarian cancer in December 2023. In version 5.0, the selection of the key questions and the systematic reviews were based on the data available up to December 2022.Therefore, we updated the guidelines version 5.0 with newly accumulated clinical data and added 5 new key questions reflecting the latest insights in the field of ovarian cancer between 2023 and 2024. For each question, recommendation was provided together with corresponding level of evidence and grade of recommendation, all established through expert consensus.

We updated the Korean Society of Gynecologic Oncology (KSGO) practice guideline for the management of ovarian cancer as version 5.1. The ovarian cancer guideline team of the KSGO published announced the fifth version (version 5.0) of its clinical practice guidelines for the management of ovarian cancer in December 2023. In version 5.0, the selection of the key questions and the systematic reviews were based on the data available up to December 2022.Therefore, we updated the guidelines version 5.0 with newly accumulated clinical data and added 5 new key questions reflecting the latest insights in the field of ovarian cancer between 2023 and 2024. For each question, recommendation was provided together with corresponding level of evidence and grade of recommendation, all established through expert consensus.

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.

Serological tests for Helicobacter pylori needs local validation as the diagnostic accuracy may vary depending on the prevalence of H.pylori. This study examined the diagnostic performance of two ELISA, GastroPanel® (GastroPanel ELISA; Biohit Oyj) and GENE-DIA® (GENEDIA® H. pylori ELISA, Green Cross Co.) in Korean population. One thousand seventy seven patients who visited for esophagogastroduodenoscopy between 2013 and 2023 were prospectively enrolled, and serum samples from the subjects were tested using both GastroPanel® and GENEDIA® . The two tests were compared for their diagnostic accuracy in detecting atrophic gastritis (AG), intestinal metaplasia (IM), gastric adenoma (GA), and gastric cancer (GC), and the positivity rates by age and sexwere observed. There was substantial correlation (Pearson coefficient [r] = 0.512, P < 0.001) and agreement (Cohen’s Kappa coefficient [κ] = 0.723, P < 0.001) between the results obtained using GastroPanel® and GENEDIA® . The test results from the two kits did not match perfectly with a discrepancy observed in approximately 16% of cases, that 67 subjects were positive only on GENE-DIA® while 75 subjects were positive only on GastroPanel® . The area under receiver operating characteristic curve for AG, IM, GA,and GC using GastroPanel® were 0.666, 0.635, 0.540, and 0.575, while the results tested using GENEDIA® were 0.649, 0.604, 0.553, and 0.555, respectively, without significant difference between the two results. GastroPanel® and GENEDIA® showed similar performance in terms of diagnostic accuracy; but the test results did not match perfectly. A large-scale validation study in Koreansis needed.

Objectives: Sepsis is a leading global cause of mortality, and predicting its outcomes is vital for improving patient care. This study explored the capabilities of ChatGPT, a state-of-the-art natural language processing model, in predicting in-hospital mortality for sepsis patients. Methods: This study utilized data from the Korean Sepsis Alliance (KSA) database, collected between 2019 and 2021, focusing on adult intensive care unit (ICU) patients and aiming to determine whether ChatGPT could predict all-cause mortality after ICU admission at 7 and 30 days. Structured prompts enabled ChatGPT to engage in in-context learning, with the number of patient examples varying from zero to six. The predictive capabilities of ChatGPT-3.5-turbo and ChatGPT-4 were then compared against a gradient boosting model (GBM) using various performance metrics. Results: From the KSA database, 4,786 patients formed the 7-day mortality prediction dataset, of whom 718 died, and 4,025 patients formed the 30-day dataset, with 1,368 deaths. Age and clinical markers (e.g., Sequential Organ Failure Assessment score and lactic acid levels) showed significant differences between survivors and non-survivors in both datasets. For 7-day mortality predictions, the area under the receiver operating characteristic curve (AUROC) was 0.70–0.83 for GPT-4, 0.51–0.70 for GPT-3.5, and 0.79 for GBM. The AUROC for 30-day mortality was 0.51–0.59 for GPT-4, 0.47–0.57 for GPT-3.5, and 0.76 for GBM. Zero-shot predictions using GPT-4 for mortality from ICU admission to day 30 showed AUROCs from the mid-0.60s to 0.75 for GPT-4 and mainly from 0.47 to 0.63 for GPT-3.5. Conclusions GPT-4 demonstrated potential in predicting short-term in-hospital mortality, although its performance varied across different evaluation metrics.

Since the latest practice guidelines for ovarian cancer were developed by the Korean Society of Gynecologic Oncology (KSGO) in 2021, many studies have examined the efficacy and safety of various treatments for epithelial ovarian cancer (EOC). Therefore, the need to develop recommendations for EOC treatments has been raised. This study searched the literature using 4 key items and the Population, Intervention, Comparison, and Outcome: the efficacy and safety of poly-ADP ribose polymerase inhibitors in newly diagnosed advanced EOC; the efficacy and safety of intraperitoneal plus intravenous chemotherapy in optimally debulked advanced EOC; the efficacy and safety of secondary cytoreductive surgery in platinumsensitive recurrent ovarian cancer; and the efficacy and safety of the addition of bevacizumab to platinum-based chemotherapy in first platinum-sensitive recurrent EOC patients who received prior bevacizumab. The evidence for these recommendations, according to each key question, was evaluated using a systematic review and meta-analysis. The committee of ovarian cancer of the KSGO developed updated guidelines for treatments of EOC.