Synthetic data, generated using advanced artificial intelligence (AI) techniques, replicates the statistical properties of real-world datasets while excluding identifiable information.Although synthetic data does not consist of actual data points, it is derived from original datasets, thereby enabling analyses that yield results comparable to those obtained with real data. Synthetic datasets are evaluated based on their utility—a measure of how effectively they mirror real data for analytical purposes. This paper presents the generation of synthetic datasets through the Healthcare Big Data Showcase Project (2019–2023). The original dataset comprises comprehensive multi-omics data from 400 individuals, including cancer survivors, chronic disease patients, and healthy participants. Synthetic data facilitates efficient access and robust analyses, serving as a practical tool for research and education. It addresses privacy concerns, supports AI research, and provides a foundation for innovative applications across diverse fields, such as public health and precision medicine.

Synthetic data, generated using advanced artificial intelligence (AI) techniques, replicates the statistical properties of real-world datasets while excluding identifiable information.Although synthetic data does not consist of actual data points, it is derived from original datasets, thereby enabling analyses that yield results comparable to those obtained with real data. Synthetic datasets are evaluated based on their utility—a measure of how effectively they mirror real data for analytical purposes. This paper presents the generation of synthetic datasets through the Healthcare Big Data Showcase Project (2019–2023). The original dataset comprises comprehensive multi-omics data from 400 individuals, including cancer survivors, chronic disease patients, and healthy participants. Synthetic data facilitates efficient access and robust analyses, serving as a practical tool for research and education. It addresses privacy concerns, supports AI research, and provides a foundation for innovative applications across diverse fields, such as public health and precision medicine.

Background: The diagnosis of tuberculous pleural effusion (TPE) often relies on pleural fluid adenosine deaminase (ADA) levels. The diagnostic utility of ADA, however, is influenced by the prevalence of tuberculosis (TB) in local populations. Malignant pleural effusion (MPE) cases can exhibit moderately elevated ADA levels comparable to those seen in TPE. As population aging potentially impacts ADA levels, global TB incidence is decreasing whereas the burden of malignancy is on the rise. Consequently, epidemiological shifts and temporal changes in ADA distribution complicate the differential diagnosis between TPE and MPE when ADA levels are within the 40–70 IU/L range. Nonetheless, data specific to this subset are scarce. Methods: This retrospective study included consecutive patients aged > 18 years with confirmed TPE and MPE, spanning from 2012 to 2023. ADA levels in pleural fluid were categorized into three groups: < 40 IU/L, 40–70 IU/L, and > 70 IU/L. The study examined annual trends in the frequency of new cases and ADA level distributions over time and identified discriminating factors between TPE and MPE in cases with ADA levels of 40–70 IU/L. Results: In total, 297 TPE and 369 MPE cases were included in this study. Over the study period, the frequency of TPE progressively declined, while that of MPE increased. In the most recent four-year period, new TPE and MPE cases with ADA levels of 40–70 IU/L occurred at comparable numbers. Multivariable analysis identified pleural fluid carcinoembryonic antigen (CEA) levels and the number of focal pleural nodules as independent predictors for MPE. Specifically, the presence of either CEA levels > 15.7 ng/mL or more than eight pleural nodules yielded the highest diagnostic accuracy with a sensitivity of 88%, specificity of 100%, and an area under the curve of 0.95. Conclusion The differential diagnosis between TPE and MPE with pleural ADA levels of 40–70 IU/L has become increasingly critical due to evolving epidemiological patterns and ADA distribution changes over time. Pleural fluid CEA levels and the characteristics of pleural nodules may offer valuable guidance in distinguishing between TPE and MPE within this diagnostic gray zone.

Background: The accuracy of Logical Observation Identifiers Names and Codes (LOINC) mappings is reportedly low, and the LOINC codes used for research purposes in Korea have not been validated for accuracy or usability. Our study aimed to evaluate the discrepancies and similarities in interoperability using existing LOINC mappings in actual patient care settings. Methods: We collected data on local test codes and their corresponding LOINC mappings from seven university hospitals. Our analysis focused on laboratory tests that are frequently requested, excluding clinical microbiology and molecular tests. Codes from nationwide proficiency tests served as intermediary benchmarks for comparison. A research team, comprising clinical pathologists and terminology experts, utilized the LOINC manual to reach a consensus on determining the most suitable LOINC codes. Results: A total of 235 LOINC codes were designated as optimal codes for 162 frequent tests.Among these, 51 test items, including 34 urine tests, required multiple optimal LOINC codes, primarily due to unnoted properties such as whether the test was quantitative or qualitative, or differences in measurement units. We analyzed 962 LOINC codes linked to 162 tests across seven institutions, discovering that 792 (82.3%) of these codes were consistent. Inconsistencies were most common in the analyte component (38 inconsistencies, 33.3%), followed by the method (33 inconsistencies, 28.9%), and properties (13 inconsistencies, 11.4%). Conclusion This study reveals a significant inconsistency rate of over 15% in LOINC mappings utilized for research purposes in university hospitals, underlining the necessity for expert verification to enhance interoperability in real patient care.

Background: In 2023, we experienced an outbreak from a case of undiagnosed crusted scabies, resulting in a significant number of exposed individuals and secondary cases. In this report, we describe the outbreak control measures, the attack rate, and the risk factors for acquisition of scabies among healthcare workers (HCWs). Methods: This study was conducted in a 2,700-bed tertiary care hospital in Seoul, South Korea. The attack rate was defined both for microscopic proven cases per exposed individuals and as the sum of proven and probable cases per exposed individuals. Outbreak control measures included identifying and treating all potentially exposed individuals with or without symptoms, as well as environmental disinfection. Results: From the index, there was potential quinary transmission resulting in 63 proven cases, 142 probable cases, and a total of 1,820 exposed individuals, including 734 contacts from the index case. The attack rate from the index was 7% (50/734) based on proven cases and 19% (138/734) based on proven and probable cases. Among the 526 HCWs who received preemptive topical treatment with permethrin applied once, 21 (4%) were later diagnosed as scabies. In addition, 5 of 20 HCWs (25%) with initial proven scabies had a persistent positive microscopic exam after four permethrin treatments. In the case group, there were significantly more nurses (60% vs. 43%, P = 0.007) and nurse assistants (20% vs. 9%, P = 0.006). There were significantly more cases than controls involving direct contact with the index case (94% vs. 64%, P < 0.001). Conclusion Lowering the threshold for suspicion of crusted scabies is important, as a single missed case could lead to a large outbreak. Simultaneously applying preemptive permethrin cream to all potentially exposed individuals might have been effective in preventing further transmission. However, caution is needed because the development of scabies or persistent scabies is possible even with preemptive or therapeutic treatment.

Purpose: This study investigated the effects of a nursing leadership program on self-leadership, interpersonal relationships, clinical performance, problem-solving abilities, and nursing professionalism among nursing students in South Korea. Methods: A quasi-experimental study was conducted. The Practice-Driven Nursing Leadership Program for Students (PDNLP-S) was developed based on the ADDIE model (analysis, design, development, implementation, and evaluation). This quasi-experimental study design included 60 nursing students. The experimental group (n=30) participated in the PDNLP-S for 120-minute sessions over 5 weeks, while the control group (n=30) received usual lectures. The PDNLP-S included lectures, discussions, and individual and group activities to cultivate core nursing leadership competencies such as individual growth, collaboration, nursing excellence, creative problem-solving, and influence. Data were analyzed using descriptive statistics, the Mann-Whitney U-test, and the independent t-test with IBM SPSS Windows ver. 26.0. Results: The experimental group demonstrated significant improvements in self-leadership (t=3.28, p=.001), interpersonal relationships (t=3.07, p=.002), clinical performance (U=268.50, p=.004), and problem-solving abilities (t=2.20, p=.017) compared to the control group. No significant difference was observed in nursing professionalism (t=0.50, p=.311). Conclusion This study demonstrates that the PDNLP-S improved nursing students’ self-leadership, interpersonal relationships, clinical performance, and problem-solving abilities. The PDNLP-S can play a significant role in cultivating future nurse leaders by enhancing these nursing leadership competencies among nursing students.

Anticancer treatment for acute lymphocytic leukemia is based on drugs such as methotrexate, 6-mercaptopurine, vincristine, and asparaginase. Asparaginase-related pancreatitis is known to have an incidence of up to 18%, and is a major cause of discontinuation of anticancer treatment for leukemia due to acute onset and chronic complications. There were various cases of treatment of peripancreatic fluid retention caused by anticancer drugs in leukemia patients. Use of lumen-apposing metal stents (LAMS) for walled-off necrosis (WON) drainage has recently increased. The electrocautery-enhanced delivery system allowed simpler and faster stent placement, streamlining the overall procedure and potentially reducing procedure time. Therefore, favorable outcomes have been reported with the use of LAMS for endoscopic drainage of various conditions. In this paper, we discuss a case in which hot-system LAMS was performed to treat L-asparaginase-induced acute pancreatitis and pancreatic pseudocyst in an adult patient with acute lymphoblastic leukemia.

Incidentally detected gallbladder polyps (GBPs) and gallbladder wall thickening (GBWT) are frequently encountered in clinical practice. However, characterizing GBPs and GBWT in asymptomatic patients can be challenging and may result in overtreatment, including unnecessary follow-ups or surgeries. The Korean Society of Abdominal Radiology (KSAR) Clinical Practice Guideline Committee has developed expert recommendations that focus on standardized imaging interpretation and follow-up strategies for both GBPs and GBWT, with support from the Korean Society of Radiology and KSAR. These guidelines, which address 24 key questions, aim to standardize the approach for the interpretation of imaging findings, reporting, imaging-based workups, and surveillance of incidentally detected GBPs and GBWT. This recommendation promotes evidence-based practice, facilitates communication between radiologists and referring physicians, and reduces unnecessary interventions.

Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.