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.

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 aimed to compare tumor tissue DNA (ttDNA) and circulating tumor DNA (ctDNA) to explore the clinical applicability of ctDNA and to better understand clonal evolution in patients with metastatic colorectal cancer undergoing palliative first-line systemic therapy. Materials and Methods: We performed targeted sequencing analysis of 88 cancer-associated genes using germline DNA, ctDNA at baseline (baseline-ctDNA), and ctDNA at progressive disease (PD-ctDNA). The results were compared with ttDNA data. Results: Among 208 consecutively enrolled patients, we selected 84 (41 males; median age, 59 years; range, 35 to 90 years) with all four sample types available. A total of 202 driver mutations were found in 34 genes. ttDNA exhibited the highest mutation frequency (n=232), followed by baseline-ctDNA (n=155) and PD-ctDNA (n=117). Sequencing ctDNA alongside ttDNA revealed additional mutations in 40 patients (47.6%). PD-ctDNA detected 13 novel mutations in 10 patients (11.9%) compared to ttDNA and baseline-ctDNA. Notably, seven mutations in five patients (6.0%) were missense or nonsense mutations in APC, TP53, SMAD4, and CDH1 genes. In baseline-ctDNA, higher maximal variant allele frequency (VAF) values (p=0.010) and higher VAF values of APC (p=0.012), TP53 (p=0.012), and KRAS (p=0.005) mutations were significantly associated with worse overall survival. Conclusion While ttDNA remains more sensitive than ctDNA, our ctDNA platform demonstrated validity and potential value when ttDNA was unavailable. Post-treatment analysis of PD-ctDNA unveiled new pathogenic mutations, signifying cancer’s clonal evolution. Additionally, baseline-ctDNA’s VAF values were prognostic after treatment.

Viral load and the duration of viral shedding of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are important determinants of the transmission of coronavirus disease 2019.In this study, we examined the effects of viral doses on the lung and spleen of K18-hACE2 transgenic mice by temporal histological and transcriptional analyses. Approximately, 1×105 plaque-forming units (PFU) of SARS-CoV-2 induced strong host responses in the lungs from 2 days post inoculation (dpi) which did not recover until the mice died, whereas responses to the virus were obvious at 5 days, recovering to the basal state by 14 dpi at 1×102 PFU. Further, flow cytometry showed that number of CD8+ T cells continuously increased in 1×102 PFU-virusinfected lungs from 2 dpi, but not in 1×105 PFU-virus-infected lungs. In spleens, responses to the virus were prominent from 2 dpi, and number of B cells was significantly decreased at 1×105PFU; however, 1×102 PFU of virus induced very weak responses from 2 dpi which recovered by 10 dpi. Although the defense responses returned to normal and the mice survived, lung histology showed evidence of fibrosis, suggesting sequelae of SARS-CoV-2 infection. Our findings indicate that specific effectors of the immune response in the lung and spleen were either increased or depleted in response to doses of SARS-CoV-2. This study demonstrated that the response of local and systemic immune effectors to a viral infection varies with viral dose, which either exacerbates the severity of the infection or accelerates its elimination.

Background: A healthcare system’s collapse due to a pandemic, such as the coronavirus disease 2019 (COVID-19), can expose healthcare workers (HCWs) to various mental health problems. This study aimed to investigate the impact of the COVID-19 pandemic on the depression and anxiety of HCWs. Methods: A nationwide questionnaire-based survey was conducted on HCWs who worked in healthcare facilities and public health centers in Korea in December 2020. Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) were used to measure depression and anxiety. To investigate factors associated with depression and anxiety, stepwise multiple logistic regression analysis was performed. Results: A total of 1,425 participating HCWs were included. The mean depression score (PHQ-9) of HCWs before and after COVID-19 increased from 2.37 to 5.39, and the mean anxiety score (GAD-7) increased from 1.41 to 3.41. The proportion of HCWs with moderate to severe depression (PHQ-9 ≥ 10) increased from 3.8% before COVID-19 to 19.5% after COVID-19, whereas that of HCWs with moderate to severe anxiety (GAD-7 ≥ 10) increased from 2.0% to 10.1%. In our study, insomnia, chronic fatigue symptoms and physical symptoms after COVID-19, anxiety score (GAD-7) after COVID-19, living alone, and exhaustion were positively correlated with depression. Furthermore, post-traumatic stress symptoms, stress score (Global Assessment of Recent Stress), depression score (PHQ-9) after COVID-19, and exhaustion were positively correlated with anxiety. Conclusion In Korea, during the COVID-19 pandemic, HCWs commonly suffered from mental health problems, including depression and anxiety. Regularly checking the physical and mental health problems of HCWs during the COVID-19 pandemic is crucial, and social support and strategy are needed to reduce the heavy workload and psychological distress of HCWs.

Background: When suspicious lesions are observed on computer-tomography (CT), invasive tests are needed to confirm lung cancer. Compared with other procedures, bronchoscopy has fewer complications. However, the sensitivity of peripheral lesion through bronchoscopy including washing cytology is low. A new test with higher sensitivity through bronchoscopy is needed. In our previous study, DNA methylation of PCDHGA12 in bronchial washing cytology has a diagnostic value for lung cancer. In this study, combination of PCDHGA12 and CDO1 methylation obtained through bronchial washing cytology was evaluated as a diagnostic tool for lung cancer. Methods: A total of 187 patients who had suspicious lesions in CT were enrolled. PCDHGA12methylation test, CDO1 methylation test, and cytological examination were performed using 3-plex LTE-qMSP test. Results: Sixty-two patients were diagnosed with benign diseases and 125 patients were diagnosed with lung cancer. The sensitivity of PCDHGA12 was 74.4% and the specificity of PCDHGA12 was 91.9% respectively. CDO1 methylation test had a sensitivity of 57.6% and a specificity of 96.8%. The combination of both PCDHGA12 methylation test and CDO1 methylation test showed a sensitivity of 77.6% and a specificity of 90.3%. The sensitivity of lung cancer diagnosis was increased by combining both PCDHGA12 and CDO1 methylation tests. Conclusion Checking DNA methylation of both PCDHGA12 and CDO1 genes using bronchial washing fluid can reduce the invasive procedure to diagnose lung cancer.

Background: We investigated the impacts of tocolytic agents on maternal and neonatal blood glucose levels in women with gestational diabetes mellitus (GDM) who used tocolytics for preterm labor. Methods: This multi-center, retrospective cohort study included women with GDM who were admitted for preterm labor from twelve hospitals in South Korea. We excluded women with multiple pregnancies, anomalies, overt DM diagnosed before pregnancy or 23 weeks of gestation, and women who received multiple tocolytics. The patients were divided according to the types of tocolytics; atosiban, ritodrine, and nifedipine group. We collected baseline maternal characteristics, pregnancy outcomes, maternal glucose levels during hospitalization, and neonatal glucose levels. We compared the frequency of maternal hyperglycemia and neonatal hypoglycemia among three groups. A multivariate logistic regression analysis was performed to evaluate the contributing factors to the occurrence of maternal hyperglycemia and neonatal hypoglycemia. Results: A total of 128 women were included: 44 (34.4%), 51 (39.8%), and 33 (25.8%) women received atosiban, ritodrine, and nifedipine, respectively. Mean fasting blood glucose (FBG) (112.3, 109.6, and 89.5 mg/dL, P < 0.001) and 2-hour postprandial glucose (PPG2) levels (145.4, 148.3, and 116.5 mg/dL, P = 0.004) were significantly higher in atosiban and ritodrine group than those in nifedipine group. Even after adjusting for covariates including antenatal steroid use, gestational age at admission, and pre-pregnancy body mass index, there was an increased risk of high maternal mean FBG (≥ 95 mg/dL) and PPG2 (≥ 120 mg/dL) levels in the atosiban and ritodrine group than in nifedipine group. The atosiban and ritodrine groups are also at increased risk of neonatal hypoglycemia (< 47 mg/dL) compared to the nifedipine group with the odds ratio of 4.58 and 4.67, respectively (P < 0.05). Conclusion There is an increased risk of maternal hyperglycemia and neonatal hypoglycemia in women with GDM using atosiban and ritodrine tocolytics for preterm labor compared to those using nifedipine.