Project description:Aspirin-exacerbated respiratory disease (AERD) has association with severe asthma and aspirin can cause asthma to worsen, often in the form of a severe and sudden attack. The oral aspirin challenge (OAC) is the gold standard to confirm the diagnosis of AERD but it is time consuming and produces serious complications in some cases. Therefore more efficient and practical method is needed to predict AERD patients. The aim of the present study was to identify AERD-related gene expression in peripheral blood mononuclear cells (PBMCs) and examine the diagnostic potential of these candidate gene(s) for predicting AERD. To do this, RNAs from 24 subjects with AERD and 18 subjects with aspirin-tolerant asthma (ATA) were subjected to microarray analysis of ~34,560 genes. In total, 10 genes were selected as candidate gene markers by applying p ≤ 0.001(t-test) and ≥ 8-fold change and to correct for multiple comparisons, the false discovery rate (FDR) analyses were performed. By applying multiple logistic regression analysis, among possible 1023 models (210–1), a model consisting of CNKSR3, SPTBN2, and IMPACT was selected as candidate set, because this set showed the best AUC (0.98) with 88% sensitivity and 89% specificity. For validation, mRNA levels by real-time PCR on PBMCs from two population sets in a gene-chip study and another replication sample: 20 AERD, 20 ATA, and 8 normal controls, were significantly different between groups with 100% sensitivity and 100% specificity in each of the two population sets. However, IMPACT gene didn’t differentiate between AERD and normal controls. The set of the two genes (CNKSR3 and SPTBN2) showed the best AUC (0.96) with 88% sensitivity and 94% specificity in a gene chip study sample. In addition, this set showed perfect discriminative power with AUC (1.0, 100% sensitivity and 100% specificity) in each of the two population sets: the gene-chip samples and the replication samples. It also showed perfect discrimination for AERD form NC (AUC 1.0) and ATA from NC (AUC 1.0). In conclusion, we developed the two gene markers (CNKSR3 and SPTBN2) of PBMC which differentiate between AERD and ATA with a perfect discriminative power. These gene markers may be an efficient and practical method useful for predicting AERD.

Project description:Aspirin-exacerbated respiratory disease (AERD) has association with severe asthma and aspirin can cause asthma to worsen, often in the form of a severe and sudden attack. The oral aspirin challenge (OAC) is the gold standard to confirm the diagnosis of AERD but it is time consuming and produces serious complications in some cases. Therefore more efficient and practical method is needed to predict AERD patients. The aim of the present study was to identify AERD-related gene expression in peripheral blood mononuclear cells (PBMCs) and examine the diagnostic potential of these candidate gene(s) for predicting AERD. To do this, RNAs from 24 subjects with AERD and 18 subjects with aspirin-tolerant asthma (ATA) were subjected to microarray analysis of ~34,560 genes. In total, 10 genes were selected as candidate gene markers by applying p ≤ 0.001(t-test) and ≥ 8-fold change and to correct for multiple comparisons, the false discovery rate (FDR) analyses were performed. By applying multiple logistic regression analysis, among possible 1023 models (210–1), a model consisting of CNKSR3, SPTBN2, and IMPACT was selected as candidate set, because this set showed the best AUC (0.98) with 88% sensitivity and 89% specificity. For validation, mRNA levels by real-time PCR on PBMCs from two population sets in a gene-chip study and another replication sample: 20 AERD, 20 ATA, and 8 normal controls, were significantly different between groups with 100% sensitivity and 100% specificity in each of the two population sets. However, IMPACT gene didn’t differentiate between AERD and normal controls. The set of the two genes (CNKSR3 and SPTBN2) showed the best AUC (0.96) with 88% sensitivity and 94% specificity in a gene chip study sample. In addition, this set showed perfect discriminative power with AUC (1.0, 100% sensitivity and 100% specificity) in each of the two population sets: the gene-chip samples and the replication samples. It also showed perfect discrimination for AERD form NC (AUC 1.0) and ATA from NC (AUC 1.0). In conclusion, we developed the two gene markers (CNKSR3 and SPTBN2) of PBMC which differentiate between AERD and ATA with a perfect discriminative power. These gene markers may be an efficient and practical method useful for predicting AERD. Total 24 AERD (Aspirin-exacerbated respiratory disease) and 18 ATA(aspirin-tolerant asthma) samples were used to find bio-markers using 35K op-array.

Project description:PurposeTo assess the contribution of a generative adversarial network (GAN) to improve intermanufacturer reproducibility of radiomic features (RFs).Materials and methodsThe authors retrospectively developed a cycle-GAN to translate texture information from chest radiographs acquired using one manufacturer (Siemens) to chest radiographs acquired using another (Philips), producing fake chest radiographs with different textures. The authors prospectively evaluated the ability of this texture-translation cycle-GAN to reduce the intermanufacturer variability of RFs extracted from the lung parenchyma. This study assessed the cycle-GAN's ability to fool several machine learning (ML) classifiers tasked with recognizing the manufacturer on the basis of chest radiography inputs. The authors also evaluated the cycle-GAN's ability to mislead radiologists who were asked to perform the same recognition task. Finally, the authors tested whether the cycle-GAN had an impact on radiomic diagnostic accuracy for chest radiography in patients with congestive heart failure (CHF).ResultsRFs, extracted from chest radiographs after the cycle-GAN's texture translation (fake chest radiographs), showed decreased intermanufacturer RF variability. Using cycle-GAN-generated chest radiographs as inputs, ML classifiers categorized the fake chest radiographs as belonging to the target manufacturer rather than to a native one. Moreover, cycle-GAN fooled two experienced radiologists who identified fake chest radiographs as belonging to a target manufacturer class. Finally, reducing intermanufacturer RF variability with cycle-GAN improved the discriminative power of RFs for patients without CHF versus patients with CHF (from 55% to 73.5%, P < .001).ConclusionBoth ML classifiers and radiologists had difficulty recognizing the chest radiographs' manufacturer. The cycle-GAN improved RF intermanufacturer reproducibility and discriminative power for identifying patients with CHF. This deep learning approach may help counteract the sensitivity of RFs to differences in acquisition.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Alderson in this issue.

Dataset Information

Unearthing new genomic markers of drug response by improved measurement of discriminative power.

Publications

Unearthing new genomic markers of drug response by improved measurement of discriminative power.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets