Comparative analysis of IR-Biotyper, MLST, cgMLST, and WGS for clustering of vancomycin-resistant Enterococcus faecium in a neonatal intensive care unit.

Healthcare-associated infections caused by vancomycin-resistant Enterococcus faecium (VREFM) pose a significant threat to healthcare. Confirming the relatedness of the bacterial isolates from different patients is challenging. We aimed to assess the efficacy of IR-Biotyper, multilocus sequencing typing (MLST), and core-genome MLST (cgMLST) in comparison with whole-genome sequencing (WGS) for outbreak confirmation in the neonatal intensive care unit (NICU). Twenty VREFM isolates from four neonates and ten control isolates from unrelated patients were analyzed. Genomic DNA extraction, MLST, cgMLST, and WGS were performed. An IR-Biotyper was used with colonies obtained after 24 h of incubation on tryptic soy agar supplemented with 5% sheep blood. The optimal clustering cutoff for the IR-Biotyper was determined by comparing the results with WGS. Clustering concordance was assessed using the adjusted Rand and Wallace indices. MLST and cgMLST identified sequence types (ST) and complex types (CT), revealing suspected outbreak isolates with a predominance of ST17 and CT6553, were confirmed by WGS. For the IR-Biotyper, the proposed optimal clustering cut-off range was 0.106-0.111. Despite lower within-run precision, of the IR-Biotyper, the clustering concordance with WGS was favorable, meeting the criteria for real-time screening. This study confirmed a nosocomial outbreak of VREFM in the NICU using an IR-Biotyper, showing promising results compared to MLST. Although within-run precision requires improvement, the IR-Biotyper demonstrated high discriminatory power and clustering concordance with WGS. These findings suggest its potential as a real-time screening tool for the detection of VREFM-related nosocomial outbreaks. IMPORTANCE: In this study, we evaluated the performance of the IR-Biotyper in detecting nosocomial outbreaks caused by vancomycin-resistant Enterococcus faecium, comparing it with MLST, cgMLST, and WGS. We proposed a cutoff that showed the highest concordance compared to WGS and assessed the within-run precision of the IR-Biotyper by evaluating the consistency in genetically identical strain when repeated in the same run.

Validation of the Accuracy of Automatic Measurement of Blood Volume in Culture Bottles for Blood Culture.

Several manufacturers have developed systems that automatically measure the amount of blood in culture bottles. We compared the volumes measured automatically by the Virtuo instrument (bioMérieux, France) (height-based volumes) and those calculated by weighing the bottles. In all, 150 pairs of aerobic and anaerobic blood culture bottles (BacT/ALERT FA/FN Plus, bioMérieux) were randomly selected over two periods to compare the height- and weight-based volumes and analyze the effect of foam. We also estimated the limit of detection (LOD) and the cut-off value for 5 mL equine blood. The mean height-based volume was approximately 0.67 mL greater than the weight-based volume, particularly in anaerobic culture bottles. Foam did not have a significant effect. The LOD for the automatic height-based volume of equine blood was 0.2-0.4 mL. The 5 mL cut-off was 4-4.2 mL. Therefore, when reporting or monitoring blood volume within culture bottles in the laboratory, these performance characteristics should be adequately considered.

Evaluation of SARS-CoV-2 Detection Systems Using Clinical Samples and Standard Material: A Comparative Study.

Due to the decreasing trends in daily confirmed COVID-19 cases and daily confirmed tests, there is a need for a new testing system capable of quickly and efficiently testing small amounts of samples. Therefore, we compared and evaluated the testing performance of the Aptima SARS-CoV-2 assay, an automated testing system that allows continuous loading of samples, and the Real-Q Direct SARS-CoV-2 detection kit that is currently being used in our laboratory. We compared the results of the two testing systems using 259 residual individual nasopharyngeal specimens and 91 residual pooled nasopharyngeal specimens that were submitted for COVID-19 testing in January and February 2023. The 95% limit of detection (LoD) for the Aptima SARS-CoV-2 assay determined using reference material for SARS-CoV-2 nucleic acid was confirmed to be 17.793 copies/mL, while the LoD for the Real-Q Direct SARS-CoV-2 detection kit was determined to be 131.842 copies/mL for the RdRP gene and 241.77 copies/mL for the E gene. The comparative study using clinical specimens showed almost perfect agreement. Our data showed that the Aptima SARS-CoV-2 assay has a very low LoD. In addition, the Aptima SARS-CoV-2 assay and Real-Q Direct detection kit have comparable clinical performance for SARS-CoV-2 for individual and pooled samples.

Korean Adolescent Patient with Manifestations of Lymphocyte Variant Hypereosinophilic Syndrome and Episodic Angioedema with Eosinophilia, Treated with Reslizumab.

A four-year-old female patient visited the pediatric hematologic clinic due to periodic generalized edema and eosinophilia. Laboratory assessment showed an eosinophil count of 40.02×109/L (73.6% of white blood cells). A bone marrow aspirate smear film showed no signs of malignant cells but had hypercellular marrow particles with eosinophilia (45% of all nucleated cells) and 52% of eosinophils were immature. Other laboratory tests showed an increased IgM level of 827 mg/dL, and lymphocyte phenotyping by flow cytometry revealed an aberrant CD3-CD4+ T-cell population of 27-53×109/L (1.9-3.6% of lymphocytes). Polymerase chain reaction analysis for the T-cell receptor gamma gene rearrangement showed a T-cell clonality peak. At the age of 13, allogeneic stem cell transplantation was performed, but with primary rejection. From the age of 17, she has continued receiving 3 mg/kg of reslizumab intravenously every 4 weeks for 21 months. Since reslizumab treatment was initiated, her eosinophil count remained consistently within the normal range. This is the first report describing the effective use of reslizumab in a Korean adolescent patient for the management of lymphocytic-variant hypereosinophilic syndrome (L-HES). Since the patient showed clinical manifestations of L-HES as well as episodic angioedema with eosinophilia (EAE), a continuous periodic examination is required given the higher risk of developing lymphoma or leukemia.

Next Generation Sequencing is a Reliable Tool for Detecting BRCA1/2 Mutations, Including Large Genomic Rearrangements.

BACKGROUND: Next-generation sequencing (NGS) has been implemented as a rapid and cost-effective BRCA1/2 test strategy. The Oncomine™ BRCA Research Assay is an NGS-based tool for simultaneous detection of small-scale mutations and large genomic rearrangements (LGRs). We evaluated this NGS assay using different versions of Ion Reporter™ (IR) software. METHODS: A total of 258 patients with breast, ovarian, primary peritoneal, and fallopian tube cancer, or a family history thereof, were enrolled in the study. The NGS assay was implemented for all samples, and the results were compared with those of Sanger sequencing and MLPA. RESULTS: All small-scale variations in Sanger sequencing were successfully detected by NGS assay. For the detection of LGRs, this assay showed 100% sensitivity from IR v5.10, and the latest version of the software (v5.16) showed the highest sensitivity and specificity. CONCLUSIONS: NGS with an appropriately updated workflow proved reliable for comprehensive BRCA1/2 gene testing, including LGR screening, which could facilitate efficient and accurate decision-making regarding treatment.

Serological evaluation of patients with coronavirus disease-2019 in Daegu, South Korea.

BACKGROUND: Early and accurate detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is critical to prevent spread of the infection. Understanding of the antibody response to SARS-CoV-2 in patients with coronavirus disease 2019 (COVID-19) is insufficient, particularly in relation to those whose responses persist for more than 1 month after the onset of symptoms. We conducted a SARS-CoV-2 antibody test to identify factors affecting the serological response and to evaluate its diagnostic utility in patients with COVID-19. METHODS AND FINDING: We collected 1,048 residual serum samples from 396 patients with COVID-19 confirmed by real-time reverse transcription polymerase chain reaction (RT-PCR) for SARS-CoV-2. The samples had been used for routine admission tests in six healthcare institutions in Daegu. Antibody to SARS-CoV-2 was analyzed and the cutoff index (COI) was calculated for quantitative analysis. The patients' information was reviewed to evaluate the relationship between antibody positivity and clinical characteristics. The anti-SARS-CoV-2 antibody positivity rate was 85% and the average COI was 24·3. The positivity rate and COI increased with time elapsed since symptom onset. Anti-SARS-CoV-2 antibody persisted for at least 13 weeks after symptom onset at a high COI. There was a significant difference in anti-SARS-CoV-2 antibody positivity rate between patients with and without symptoms, but not according to sex or disease course. The descending COI pattern at weeks 1 to 5 after symptom onset was significantly more frequent in patients who died than in those who recovered. CONCLUSIONS: Anti-SARS-CoV-2 antibody persisted for at least 13 weeks at a high COI in patients with COVID-19. A decreasing COI pattern up to fifth week may be associated with a poor prognosis of COVID-19. As new treatments and vaccines are introduced, it is important to monitor continuously the usefulness of anti-SARS-CoV-2 antibody assays.

Comprehensive Laboratory Data Analysis to Predict the Clinical Severity of Coronavirus Disease 2019 in 1,952 Patients in Daegu, Korea.

BACKGROUND: Laboratory parameter abnormalities are commonly observed in COVID-19 patients; however, their clinical significance remains controversial. We assessed the prevalence, characteristics, and clinical impact of laboratory parameters in COVID-19 patients hospitalized in Daegu, Korea. METHODS: We investigated the clinical and laboratory parameters of 1,952 COVID-19 patients on admission in nine hospitals in Daegu, Korea. The average patient age was 58.1 years, and 700 (35.9%) patients were men. The patients were classified into mild (N=1,612), moderate (N=294), and severe (N=46) disease groups based on clinical severity scores. We used chi-square test, multiple comparison analysis, and multinomial logistic regression to evaluate the correlation between laboratory parameters and disease severity. RESULTS: Laboratory parameters on admission in the three disease groups were significantly different in terms of hematologic (Hb, Hct, white blood cell count, lymphocyte%, and platelet count), coagulation (prothrombin time and activated partial thromboplastin time), biochemical (albumin, aspartate aminotransferase, alanine aminotransferase, lactate, blood urea nitrogen, creatinine, and electrolytes), inflammatory (C-reactive protein and procalcitonin), cardiac (creatinine kinase MB isoenzyme and troponin I), and molecular virologic (Ct value of SARS-CoV-2 RdRP gene) parameters. Relative lymphopenia, prothrombin time prolongation, and hypoalbuminemia were significant indicators of COVID-19 severity. Patients with both hypoalbuminemia and lymphopenia had a higher risk of severe COVID-19. CONCLUSIONS: Laboratory parameter abnormalities on admission are common, are significantly associated with clinical severity, and can serve as independent predictors of COVID-19 severity. Monitoring the laboratory parameters, including albumin and lymphocyte count, is crucial for timely treatment of COVID-19.

Severe Acute Respiratory Syndrome Coronavirus-2 Antibody Responses in Hospitalized Patients with Coronavirus Disease 2019 in Daegu, Korea.

BACKGROUND: Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) started to spread in Daegu beginning at the end of February 2020. IgG and IgM antibodies against SARS-CoV-2 were measured in hospitalized patients with COVID-19 with moderate to severe symptoms to improve the understanding of antibody responses. METHODS: We enrolled 312 patients with COVID-19 admitted to seven hospitals located in Daegu. Using serum (or plasma) samples from patients with polymerase chain reaction (PCR)-confirmed SARS-CoV-2 infections, both IgG and IgM antibodies were measured using commercial enzyme-linked immunosorbent assay (R-FIND CO¬VID-19 ELISA, SG medical, Seoul, Korea). RESULTS: The median value from the initial diagnosis, confirmed by SARS-CoV-2 PCR, to the sampling date was 24 days (day 1 to 88). The total positive rate of IgG was 93.9% and the positive IgM rate was 39.4%, without considering the elapsed period after diagnosis. Positive IgG and IgM rates were highest at 100.0% and 59.0%, respectively, at 3 weeks (15 - 21 days). IgG showed a high positive rate of 79.3% even within 7 days after the initial diag-nosis of the disease and maintained a positive rate of 97.8% until after 8 weeks. CONCLUSIONS: Among hospitalized patients with COVID-19, IgG was detected from the beginning of the diagnosis and persisted for an extended time period.

Viral load and rebound in children with coronavirus disease 2019 during the first outbreak in Daegu city.

BACKGROUND: Viral load and shedding duration are highly associated with the transmission of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection. However, limited studies have reported on viral load or shedding in children and adolescents infected with sudden acute respiratory syndrome coronavirus 2 (SARS-CoV-2). PURPOSE: This study aimed to investigate the natural course of viral load in asymptomatic or mild pediatric cases. METHODS: Thirty-one children (<18 years) with confirmed SARS-CoV-2 infection were hospitalized and enrolled in this study. Viral loads were evaluated in nasopharyngeal swab samples using real-time reverse transcription polymerase chain reaction (E, RdRp, N genes). cycle threshold (Ct) values were measured when patients met the clinical criteria to be released from quarantine. RESULTS: The mean age of the patients was 9.8 years, 18 (58%) had mild disease, and 13 (42%) were asymptomatic. Most children were infected by adult family members, most commonly by their mothers. The most common symptoms were fever and sputum (26%), followed by cough and runny nose. Nine patients (29%) had a high or intermediate viral load (Ct value≤30) when they had no clinical symptoms. Viral load showed no difference between symptomatic and asymptomatic patients. Viral rebounds were found in 15 cases (48%), which contributed to prolonged viral detection. The mean duration of viral detection was 25.6 days. Viral loads were significantly lower in patients with viral rebounds than in those with no rebound (E, P=0.003; RdRp, P=0.01; N, P=0.02). CONCLUSION: Our study showed that many pediatric patients with coronavirus disease 2019 (COVID-19) experienced viral rebound and showed viral detection for more than 3 weeks. Further studies are needed to investigate the relationship between viral rebound and infectiousness in COVID-19.

Pregnancy Outcome, Antibodies, and Placental Pathology in SARS-CoV-2 Infection during Early Pregnancy.

There are reports that pregnant women infected with SARS-CoV-2 not only have increased morbidity but also increased complications and evidence of maternal and fetal vascular malperfusion on placental pathology. This was a retrospective study of pregnant women diagnosed with SARS-CoV-2 infection after March 2020. The results of reverse transcription polymerase chain reaction testing and IgM and IgG antibody testing of the amniotic fluid, cord blood, placenta, and maternal blood were confirmed at delivery. Placentas were evaluated histopathologically. The study included seven pregnant women diagnosed with SARS-CoV-2 infection during pregnancy at a mean gestational age of 14.5 weeks. Out of the seven women, five were infected during the first trimester. The mean gestational age at delivery was 38.4 weeks. The reverse transcription polymerase chain reaction results for maternal plasma, cord blood, placenta, and amniotic fluid were negative and IgG antibodies were detected in maternal plasma and cord blood. On placental pathology, maternal vascular malperfusion was found in only one case, fetal vascular malperfusion in four cases, and inflammatory changes were found in two cases. Pregnancy outcomes for women diagnosed with SARS-CoV-2 infection during early pregnancy are positive and it is likely that maternal antibodies are passed to the fetus, which results in a period of immunity.

Analysis of BRCA1/2 variants of unknown significance in the prospective Korean Hereditary Breast Cancer study.

Genetic testing for BRCA1 and BRCA2 is crucial in diagnosing hereditary breast and ovarian cancer syndromes and has increased with the development of multigene panel tests. However, results classified as variants of uncertain significance (VUS) present challenges to clinicians in attempting to choose an appropriate management plans. We reviewed a total of 676 breast cancer patients included in the Korean Hereditary Breast Cancer (KOHBRA) study with a VUS on BRCA mutation tests between November 2007 and April 2013. These results were compared to the ClinVar database. We calculated the incidence and odds ratios for these variants using the Korean Reference Genome Database. A total of 58 and 91 distinct VUS in BRCA1 and BRCA2 were identified in the KOHBRA study (comprising 278 and 453 patients, respectively). A total of 27 variants in the KOHBRA study were not registered in the Single Nucleotide Polymorphism database. Among BRCA1 VUSs, 20 were reclassified as benign or likely benign, four were reclassified as pathogenic or likely pathogenic, and eight remained as VUSs according to the ClinVar database. Of the BRCA2 VUSs, 25 were reclassified as benign or likely benign, two were reclassified as pathogenic or likely pathogenic, and 33 remained as VUS according to the ClinVar database. There were 12 variants with conflicting interpretations of pathogenicity for BRCA1 and 18 for BRCA2. Among them, p.Leu1780Pro showed a particularly high odds ratio. Six pathogenic variants and one conflicting variant identified using ClinVar could be reclassified as pathogenic variants in this study. Using updated ClinVar information and calculating odds ratios can be helpful when reclassifying VUSs in BRCA1/2.

Evaluation of a deep learning-based computer-aided detection algorithm on chest radiographs: Case-control study.

ABSTRACT: Along with recent developments in deep learning techniques, computer-aided diagnosis (CAD) has been growing rapidly in the medical imaging field. In this work, we evaluate the deep learning-based CAD algorithm (DCAD) for detecting and localizing 3 major thoracic abnormalities visible on chest radiographs (CR) and to compare the performance of physicians with and without the assistance of the algorithm. A subset of 244 subjects (60% abnormal CRs) was evaluated. Abnormal findings included mass/nodules (55%), consolidation (21%), and pneumothorax (24%). Observer performance tests were conducted to assess whether the performance of physicians could be enhanced with the algorithm. The area under the receiver operating characteristic (ROC) curve (AUC) and the area under the jackknife alternative free-response ROC (JAFROC) were measured to evaluate the performance of the algorithm and physicians in image classification and lesion detection, respectively. The AUCs for nodule/mass, consolidation, and pneumothorax were 0.9883, 1.000, and 0.9997, respectively. For the image classification, the overall AUC of the pooled physicians was 0.8679 without DCAD and 0.9112 with DCAD. Regarding lesion detection, the pooled observers exhibited a weighted JAFROC figure of merit (FOM) of 0.8426 without DCAD and 0.9112 with DCAD. DCAD for CRs could enhance physicians' performance in the detection of 3 major thoracic abnormalities.

Deep learning-based automated detection algorithm for active pulmonary tuberculosis on chest radiographs: diagnostic performance in systematic screening of asymptomatic individuals.

OBJECTIVES: Performance of deep learning-based automated detection (DLAD) algorithms in systematic screening for active pulmonary tuberculosis is unknown. We aimed to validate DLAD algorithm for detection of active pulmonary tuberculosis and any radiologically identifiable relevant abnormality on chest radiographs (CRs) in this setting. METHODS: We performed out-of-sample testing of a pre-trained DLAD algorithm, using CRs from 19.686 asymptomatic individuals (ages, 21.3 ± 1.9 years) as part of systematic screening for tuberculosis between January 2013 and July 2018. Area under the receiver operating characteristic curves (AUC) for diagnosis of tuberculosis and any relevant abnormalities were measured. Accuracy measures including sensitivities, specificities, positive predictive values (PPVs), and negative predictive values (NPVs) were calculated at pre-defined operating thresholds (high sensitivity threshold, 0.16; high specificity threshold, 0.46). RESULTS: All five CRs from four individuals with active pulmonary tuberculosis were correctly classified as having abnormal findings by DLAD with specificities of 0.959 and 0.997, PPVs of 0.006 and 0.068, and NPVs of both 1.000 at high sensitivity and high specificity thresholds, respectively. With high specificity thresholds, DLAD showed comparable diagnostic measures with the pooled radiologists (p values > 0.05). For the radiologically identifiable relevant abnormality (n = 28), DLAD showed an AUC value of 0.967 (95% confidence interval, 0.938-0.996) with sensitivities of 0.821 and 0.679, specificities of 0.960 and 0.997, PPVs of 0.028 and 0.257, and NPVs of both 0.999 at high sensitivity and high specificity thresholds, respectively. CONCLUSIONS: In systematic screening for tuberculosis in a low-prevalence setting, DLAD algorithm demonstrated excellent diagnostic performance, comparable with the radiologists in the detection of active pulmonary tuberculosis. KEY POINTS: • Deep learning-based automated detection algorithm detected all chest radiographs with active pulmonary tuberculosis with high specificities and negative predictive values in systematic screening. • Deep learning-based automated detection algorithm had comparable diagnostic measures with the radiologists for detection of active pulmonary tuberculosis on chest radiographs. • For the detection of radiologically identifiable relevant abnormalities on chest radiographs, deep learning-based automated detection algorithm showed excellent diagnostic performance in systematic screening.

COVID-19: Comparing the applicability of shared room and single room occupancy.

To curb the COVID-19 pandemic, isolation measures are required. Shared room occupancy is recommended when isolation rooms are insufficient. However, there is little evidence of the applicability of shared and single room occupancy for patients with COVID-19 to determine whether shared room occupancy is feasible. COVID-19-infected patients admitted to the Daegu Dongsan Hospital of Keimyung University from 21 February 2020 to 20 April 2020 were enrolled in the study and randomly assigned to hospital rooms. Clinical symptoms, underlying diseases and epidemiological data of patients were analysed after dividing participants into a shared room occupancy group (group A) and a single room occupancy group (group B). Outcomes analysed included microbiological cure rates, time to clinical symptom improvement, time to defervescence and negative-to-positive conversion rates of polymerase chain reaction (PCR) results during hospitalization. A total of 666 patients were included in this study, 535 and 131 patients in groups A and B, respectively. Group B included more underlying conditions, such as pregnancy and solid organ transplantation, and was more closely associated with severe pneumonia during hospitalization. Besides, no statistically significant differences between the two groups in terms of negative PCR rates at HD 7 and 14, conversion rates of PCR results from negative-to-positive, as well as time to the improvement of clinical symptoms, and time to defervescence were observed. Our results suggest that the shared room occupancy of patients with mild symptoms could be an alternative to single room occupancy during the COVID-19 pandemic.

Analytical validation of the droplet digital PCR assay for diagnosis of spinal muscular atrophy.

BACKGROUND: Spinal muscular atrophy (SMA) is a progressive motor neuron disease caused by homozygote loss of exon 7 on the survival motor neuron 1 (SMN1) gene. The severity of the SMA phenotype is influenced by copies of SMN2, a gene that is highly homologous with SMN1. METHODS: We validated analytical performance of droplet digital polymerase chain reaction (ddPCR) for detection of copy number variation of SMN1 and SMN2 genes for diagnosis of SMA using clinical samples. For accuracy performance evaluation, ddPCR results were compared with those of multiplex ligation-dependent probe amplification (MLPA) as a reference standard. Copy numbers of SMN1/SMN2 exon 7 from 200 clinical samples were concordant between ddPCR and MLPA. RESULTS: For all samples, the copy number of SMN1/SMN2 exon 7 was concordant between MLPA and ddPCR. The ddPCR also showed acceptable degrees of repeatability and total imprecision. CONCLUSION: Therefore, ddPCR is expected to be useful for SMA diagnosis and to predict phenotypic severity of SMA patients by determining the copy number of SMN2 in clinical laboratories.

Performance of a Deep Learning Algorithm Compared with Radiologic Interpretation for Lung Cancer Detection on Chest Radiographs in a Health Screening Population.

Background The performance of a deep learning algorithm for lung cancer detection on chest radiographs in a health screening population is unknown. Purpose To validate a commercially available deep learning algorithm for lung cancer detection on chest radiographs in a health screening population. Materials and Methods Out-of-sample testing of a deep learning algorithm was retrospectively performed using chest radiographs from individuals undergoing a comprehensive medical check-up between July 2008 and December 2008 (validation test). To evaluate the algorithm performance for visible lung cancer detection, the area under the receiver operating characteristic curve (AUC) and diagnostic measures, including sensitivity and false-positive rate (FPR), were calculated. The algorithm performance was compared with that of radiologists using the McNemar test and the Moskowitz method. Additionally, the deep learning algorithm was applied to a screening cohort undergoing chest radiography between January 2008 and December 2012, and its performances were calculated. Results In a validation test comprising 10 285 radiographs from 10 202 individuals (mean age, 54 years ± 11 [standard deviation]; 5857 men) with 10 radiographs of visible lung cancers, the algorithm's AUC was 0.99 (95% confidence interval: 0.97, 1), and it showed comparable sensitivity (90% [nine of 10 radiographs]) to that of the radiologists (60% [six of 10 radiographs]; P = .25) with a higher FPR (3.1% [319 of 10 275 radiographs] vs 0.3% [26 of 10 275 radiographs]; P < .001). In the screening cohort of 100 525 chest radiographs from 50 070 individuals (mean age, 53 years ± 11; 28 090 men) with 47 radiographs of visible lung cancers, the algorithm's AUC was 0.97 (95% confidence interval: 0.95, 0.99), and its sensitivity and FPR were 83% (39 of 47 radiographs) and 3% (2999 of 100 478 radiographs), respectively. Conclusion A deep learning algorithm detected lung cancers on chest radiographs with a performance comparable to that of radiologists, which will be helpful for radiologists in healthy populations with a low prevalence of lung cancer. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Armato in this issue.

Next-Generation Sequencing in Korean Children With Autism Spectrum Disorder and Comorbid Epilepsy.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by impairments in social communication and restricted and repetitive behaviors and interests. Identifying the genetic background may be one of the key features for the future diagnosis and treatment of ASD. With the tremendous development in genetic diagnosis techniques, next-generation sequencing (NGS) can be used to analyze multiple genes simultaneously with a single test in laboratory and clinical settings and is well suited for investigating autism genetics. According to previous studies, there are two types of genetic variants in ASD, rare variants and common variants, and both are important in explaining pathogenesis. In this study, NGS data from 137 participants with ASD were reviewed retrospectively with consideration for comorbid epilepsy. Diagnostic yield was 17.51% (24/137), and pathogenic/likely pathogenic variants were seen more frequently in female participants. Fourteen participants were diagnosed with comorbid epilepsy, six of them had pathogenic/likely pathogenic variants (43%). Genes with variants of unknown significance (VOUS) which have one or more evidence of pathogenicity following the American College of Medical Genetics (ACMG) criteria were also reviewed in both ASD and ASD with comorbid epilepsy groups. We found that most frequently found VOUS genes have previously been reported as genes related to ASD or other developmental disorders. These results suggest that when interpreting the NGS results in the clinical setting, careful observation of VOUS with some pathological evidence might contribute to the discovery of genetic pathogenesis of neurodevelopmental disorders such as ASD and epilepsy.