Accurate and early identification of stroke and large vessel occlusion (LVO) in emergency settings is essential for improving patient outcomes and ensuring the efficient allocation of medical resources. This clinical practice guideline systematically reviews domestic and international literature and conducts meta-analyses to evaluate the utility and diagnostic accuracy of stroke assessment tools used in prehospital emergency medical services (EMS). We developed a guideline based on evidence from systematic reviews and meta-analyses via a de novo process. A systematic literature review was conducted to evaluate the usefulness of diagnostic EMS assessment tools for diagnosing stroke and LVO. Overall, 70 non-randomized control studies were selected for this study. A meta-analysis was conducted with a subgroup analysis to distinguish between patients with stroke and those with LVO. EMS tools demonstrated high sensitivity but low specificity for diagnosing stroke. In the prehospital setting, using validated EMS stroke assessment tools is recommended for the early identification of stroke and LVO. Upon hospital arrival, stroke specialists should conduct further evaluation and triage to confirm the diagnosis and guide appropriate management. Delays in diagnosing LVO are frequently unacceptable. While experts advocate for the use of EMS assessment tools to facilitate early identification of LVO, these tools alone lack adequate sensitivity. Therefore, further diagnostic evaluations and consultation with stroke specialists upon hospital arrival are recommended.

In patients with type 2 diabetes mellitus (T2DM), diabetic kidney disease (DKD) is diagnosed based on clinical features. A kidney biopsy is used only in selected cases. This study aimed to reconsider the role of a biopsy in predicting renal outcomes. Methods: Clinical and laboratory parameters and renal biopsy results were obtained from 237 patients with T2DM who underwent renal biopsies at Soonchunhyang University Cheonan Hospital between January 2000 and March 2020 and were analyzed. Results: Of 237 diabetic patients, 29.1% had DKD only, 61.6% had non-DKD (NDKD), and 9.3% had DKD with coexisting NDKD (DKD/NDKD). Of the patients with DKD alone, 43.5% progressed to end-stage kidney disease (ESKD), while 15.8% of NDKD patients and 36.4% of DKD/NDKD patients progressed to ESKD (p < 0.001). In the DKD-alone group, pathologic features like ≥50% global sclerosis (p < 0.001), tubular atrophy (p < 0.001), interstitial fibrosis (p < 0.001), interstitial inflammation (p < 0.001), and the presence of hyalinosis (p = 0.03) were related to worse renal outcomes. The Cox regression model showed a higher risk of progression to ESKD in the DKD/NDKD group compared to the DKD-alone group (hazard ratio [HR], 2.73; p = 0.032), ≥50% global sclerosis (HR, 3.88; p < 0.001), and the degree of mesangial expansion (moderate: HR, 2.45; p = 0.045 and severe: HR, 6.22; p < 0.001). Conclusion: In patients with T2DM, a kidney biopsy can help in identifying patients with NDKD for appropriate treatment, and it has predictive value.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Objective: Suicide is a significant public health issue, with South Korea having the highest suicide rate among Organisation for Economic Cooperation and Development countries. This study aimed to develop clinical guidelines for suicide prevention in psychiatric patients in Korea using the ADAPTE methodology. Methods: The development process involved a comprehensive review of literature, expert consultations, and consensus-building using the Nominal Group Technique and Delphi method. The guidelines focus on evidence-based psychiatric treatments, including both pharmacological and non-pharmacological approaches, tailored to the Korean context. Key findings underscoring the need for standardized treatment protocols for patients with major psychiatric disorders, including bipolar disorder, major depressive disorder, and schizophrenia. Results: The guidelines incorporate treatments like lithium, clozapine, atypical antipsychotics, electroconvulsive therapy, and cognitive behavioral therapy, which have shown effectiveness in suicide prevention. Applicability and acceptability within Korea’s healthcare system were addressed, ensuring feasibility given the country’s medical insurance coverage and accessibility. The guidelines were validated through expert reviews and Delphi rounds, achieving consensus on the final recommendations. Conclusion The developed guidelines provide a structured, evidence-based approach to reducing suicide rates among psychiatric patients in Korea. Future research will focus on expanding these guidelines to include screening protocols for high-risk groups.

Objectives: This study examined the changes in the characteristics of high-risk suicide groups in South Korea before and after the COVID-19 pandemic using the Korean Cohort for the Model Predicting a Suicide and Suicide-related Behavior (K-COMPASS) cohort. Methods: The K-COMPASS is a longitudinal cohort study that started in 2015. The participants included suicide attempters and individuals with suicidal ideation from various hospitals and mental health centers in South Korea. This study compared the sociodemographic and psychiatric characteristics of 800 participants from the first cohort (2015–2019) with 511 participants from the second and third cohorts (2019–2024). Data were collected through structured interviews and validated scales. Results: The second and third cohort participants were younger, had a higher proportion of females, and exhibited more severe psychiatric symptoms and higher suicidal risk than the first cohort. The prevalence of physical illnesses decreased, while the use of psychiatric medications and the severity of mental health issues increased. In addition, significant sociodemographic changes were observed, such as higher educational levels and urban residency. Conclusion Significant shifts in the characteristics of high-risk suicide groups were observed during the COVID-19 pandemic, highlighting the need for targeted mental health interventions focusing on younger individuals and females to prevent suicide in high-risk groups.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Objectives: This study examined the changes in the characteristics of high-risk suicide groups in South Korea before and after the COVID-19 pandemic using the Korean Cohort for the Model Predicting a Suicide and Suicide-related Behavior (K-COMPASS) cohort. Methods: The K-COMPASS is a longitudinal cohort study that started in 2015. The participants included suicide attempters and individuals with suicidal ideation from various hospitals and mental health centers in South Korea. This study compared the sociodemographic and psychiatric characteristics of 800 participants from the first cohort (2015–2019) with 511 participants from the second and third cohorts (2019–2024). Data were collected through structured interviews and validated scales. Results: The second and third cohort participants were younger, had a higher proportion of females, and exhibited more severe psychiatric symptoms and higher suicidal risk than the first cohort. The prevalence of physical illnesses decreased, while the use of psychiatric medications and the severity of mental health issues increased. In addition, significant sociodemographic changes were observed, such as higher educational levels and urban residency. Conclusion Significant shifts in the characteristics of high-risk suicide groups were observed during the COVID-19 pandemic, highlighting the need for targeted mental health interventions focusing on younger individuals and females to prevent suicide in high-risk groups.