Background: Time-of-flight (TOF) magnetic resonance angiography (MRA) is widely used to identify aneurysm in human brain. Various deep learning models have been developed to help TOF-MRA reading in the field. The performance of those TOF-MRA analysis tools, however, faces several limitations in cerebral aneurysm detection. These challenges primarily come from the fact that cerebral aneurysms occupy less than 0.1% of the total TOF-MRA voxel size. This study aims to improve the efficiency of cerebral aneurysm detection by developing a landmark-based semi-supervised deep learning method, a technology that automatically generates landmark boxes in areas with a high probability of cerebral aneurysm occurrence. Methods: We used data from a total of 500 aneurysm-positive and 50 aneurysm-negative subjects. The aneurysm detection model was developed using clustering and a dilated residual network. Results: When the number of landmarks was ten and their size was 36 mm3, the best performance was achieved in our experiment. Although landmark occupies a small portion of the entire image, up to 98.2% of landmarks were cerebral aneurysms. The sensitivity of the model for cerebral aneurysm detection was 83.0%, with a false positive rate of 3.4%. Conclusions This study developed a deep learning model using TOF-MRA image. This model generates the most suitable landmarks for each individual, excluding unnecessary areas for cerebral aneurysm detection, which makes it possible to focus on areas with a high probability of occurrence. This model is expected to enhance the efficiency and accuracy of cerebral aneurysm detection in the field.

Background: Time-of-flight (TOF) magnetic resonance angiography (MRA) is widely used to identify aneurysm in human brain. Various deep learning models have been developed to help TOF-MRA reading in the field. The performance of those TOF-MRA analysis tools, however, faces several limitations in cerebral aneurysm detection. These challenges primarily come from the fact that cerebral aneurysms occupy less than 0.1% of the total TOF-MRA voxel size. This study aims to improve the efficiency of cerebral aneurysm detection by developing a landmark-based semi-supervised deep learning method, a technology that automatically generates landmark boxes in areas with a high probability of cerebral aneurysm occurrence. Methods: We used data from a total of 500 aneurysm-positive and 50 aneurysm-negative subjects. The aneurysm detection model was developed using clustering and a dilated residual network. Results: When the number of landmarks was ten and their size was 36 mm3, the best performance was achieved in our experiment. Although landmark occupies a small portion of the entire image, up to 98.2% of landmarks were cerebral aneurysms. The sensitivity of the model for cerebral aneurysm detection was 83.0%, with a false positive rate of 3.4%. Conclusions This study developed a deep learning model using TOF-MRA image. This model generates the most suitable landmarks for each individual, excluding unnecessary areas for cerebral aneurysm detection, which makes it possible to focus on areas with a high probability of occurrence. This model is expected to enhance the efficiency and accuracy of cerebral aneurysm detection in the field.

Background: Time-of-flight (TOF) magnetic resonance angiography (MRA) is widely used to identify aneurysm in human brain. Various deep learning models have been developed to help TOF-MRA reading in the field. The performance of those TOF-MRA analysis tools, however, faces several limitations in cerebral aneurysm detection. These challenges primarily come from the fact that cerebral aneurysms occupy less than 0.1% of the total TOF-MRA voxel size. This study aims to improve the efficiency of cerebral aneurysm detection by developing a landmark-based semi-supervised deep learning method, a technology that automatically generates landmark boxes in areas with a high probability of cerebral aneurysm occurrence. Methods: We used data from a total of 500 aneurysm-positive and 50 aneurysm-negative subjects. The aneurysm detection model was developed using clustering and a dilated residual network. Results: When the number of landmarks was ten and their size was 36 mm3, the best performance was achieved in our experiment. Although landmark occupies a small portion of the entire image, up to 98.2% of landmarks were cerebral aneurysms. The sensitivity of the model for cerebral aneurysm detection was 83.0%, with a false positive rate of 3.4%. Conclusions This study developed a deep learning model using TOF-MRA image. This model generates the most suitable landmarks for each individual, excluding unnecessary areas for cerebral aneurysm detection, which makes it possible to focus on areas with a high probability of occurrence. This model is expected to enhance the efficiency and accuracy of cerebral aneurysm detection in the field.

Purpose: In 2024, medical researchers in the Republic of Korea were invited to amend the health and medical data utilization guidelines (Government Publications Registration Number: 11-1352000-0052828-14). This study aimed to show the overall impact of the guideline revision, with a focus on clinical genomic data. Materials and Methods: This study amended the pseudonymization of genomic data defined in the previous version through a joint study led by the Ministry of Health and Welfare, the Korea Health Information Service, and the Korea Genome Organization. To develop the previous version, we held three conferences with four main medical research institutes and seven academic societies. We conducted two surveys targeting special genome experts in academia, industry, and institutes. Results: We found that cases of pseudonymization in the application of genome data were rare and that there was ambiguity in the terminology used in the previous version of the guidelines. Most experts (>~90%) agreed that the ‘reserved’ condition should be eliminated to make genomic data available after pseudonymization. In this study, the scope of genomic data was defined as clinical next-generation sequencing data, including FASTQ, BAM/SAM, VCF, and medical records. Pseudonymization targets genomic sequences and metadata, embedding specific elements, such as germline mutations, short tandem repeats, single-nucleotide polymorphisms, and identifiable data (for example, ID or environmental values). Expression data generated from multi-omics can be used without pseudonymization. Conclusion This amendment will not only enhance the safe use of healthcare data but also promote advancements in disease prevention, diagnosis, and treatment.

Background: and Purpose The optimal blood pressure (BP) control after successful endovascular thrombectomy (EVT) in acute ischemic stroke (AIS) with large vessel occlusion (LVO) remains debatable. We conducted a systematic review and meta-analysis of randomized controlled trials (RCTs) that evaluate the efficacy and safety of standard BP control (with systolic BP ≤180 mm Hg) versus intensive BP control (systolic BP <140 mm Hg) during the 24 hours after successful EVT in AIS with LVO. Methods: PubMed, Scopus, the Cochrane Central Register of Controlled Trials, and Embase were searched to identify relevant trials. The crude odds ratio (OR) and 95% confidence interval (CI) were calculated and estimates using random-effects models were pooled. This meta-analysis followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines (PROSPERO ID: CRD42023450673). Results: Four RCTs involving 1,559 participants were included. Regarding efficacy outcomes, intensive BP control was associated with a lower likelihood of functional independence (OR: 0.68; 95% CI: 0.51–0.91 for modified Rankin Scale [mRS] ≤2) and walking without assistance (OR: 0.65; 95% CI: 0.53–0.81 for mRS ≤3). For safety outcomes, consistent with the efficacy findings, intensive BP control was significantly associated with severe disability or death (mRS 5 or 6) (OR: 1.34; 95% CI: 1.07–1.69). However, there were no significant differences including all-cause mortality, any intracerebral hemorrhage (ICH), symptomatic ICH, parenchymal hematoma type 2, and stroke recurrence. Conclusion While all four RCTs were conducted to demonstrate the superiority of intensive BP control over standard BP control, standard BP control may be beneficial for the outcome after EVT for AIS with LVO without increasing adverse safety outcomes. Caution should be needed with the application of intensive BP control during the 24 hours following successful recanalization after EVT.

Background/Aims: Recent evidence has identified the significance of type 2 iodothyronine deiodinase (DIO2) in various diseases. However, the role of DIO2 polymorphism in metabolic parameters in patients with hypothyroidism is not fully understood. Methods: We assessed the polymorphism of the DIO2 gene and various clinical parameters in 118 patients who were diagnosed with hypothyroidism from the Ansan-Anseong cohort of the Korean Genome and Epidemiology Study. Furthermore, we systematically analyzed Genotype-Tissue Expression (GTEx) data. Results: A total of 118 participants with hypothyroidism were recruited; 32 (27.1%) were homozygous for the Thr allele, 86 (73.9%) were homozygous for the Ala allele or heterozygous. Patients with hypothyroidism with DIO2 polymorphism without hypertension at baseline had higher incidence of hypertension compared to patients without DIO2 polymorphism. Analysis of the GTEx database revealed that elevation of DIO2 expression is associated with enhancement of genes involved in blood vessel regulation and angiogenesis. Conclusions Commonly inherited variation in the DIO2 gene is associated with high blood pressure and prevalence of hypertension in patients with hypothyroidism. Our results suggest that genetic variation in the hypothalamic-pituitary-thyroid pathway in influencing susceptibility to hypertension.

Purpose: The purpose of this study was to provide foundational knowledge on nursing tasks performed on patients with COVID-19 in a nationally-designated inpatient treatment unit. Methods: This study employs both quantitative and qualitative approaches. The quantitative method investigated the content and frequency of nursing tasks for 460 patients (age ≥ 18y, 57.4% men) from January 20, 2020, to September 30, 2021, by analyzing hospital information system records. Qualitative data were collected via focus group interviews. The study involved interviews with three focus groups comprising 18 nurses overall to assess their experiences and perspectives on nursing care during the pandemic from February 3, 2022, to February 15, 2022. The data were examined with thematic analysis. Results: Overall, 49 different areas of nursing tasks (n = 130,687) were identified based on the Korean Patient Classification System for nurses during the study period. Among the performed tasks, monitoring of oxygen saturation and measuring of vital signs were considered high-priority. From the focus group interview, three main themes and eleven sub-themes were generated. The three main themes are “Experiencing eventfulness in isolated settings,” “All-around player,” and “Reflections for solutions.” Conclusion During the COVID-19 pandemic, it is imperative to ensure adequate staffing levels, compensation, and educational support for nurses. The study further propose improving guidelines for emerging infectious diseases and patient classification systems to improve the overall quality of patient care.