Engineering Organ-on-a-Chip Systems for Vascular Diseases.

Vascular diseases, such as atherosclerosis and thrombosis, are major causes of morbidity and mortality worldwide. Traditional in vitro models for studying vascular diseases have limitations, as they do not fully recapitulate the complexity of the in vivo microenvironment. Organ-on-a-chip systems have emerged as a promising approach for modeling vascular diseases by incorporating multiple cell types, mechanical and biochemical cues, and fluid flow in a microscale platform. This review provides an overview of recent advancements in engineering organ-on-a-chip systems for modeling vascular diseases, including the use of microfluidic channels, ECM (extracellular matrix) scaffolds, and patient-specific cells. We also discuss the limitations and future perspectives of organ-on-a-chip for modeling vascular diseases.

Clustering analysis of HRCT parameters measured using a texture-based automated system: relationship with clinical outcomes of IPF.

PURPOSE: The extent of honeycombing and reticulation predict the clinical prognosis of IPF. Emphysema, consolidation, and ground glass opacity are visible in HRCT scans. To date, there have been few comprehensive studies that have used these parameters. We conducted automated quantitative analysis to identify predictive parameters for clinical outcomes and then grouped the subjects accordingly. METHODS: CT images were obtained while patients held their breath at full inspiration. Parameters were analyzed using an automated lung texture quantification system. Cluster analysis was conducted on 159 IPF patients and clinical profiles were compared between clusters in terms of survival. RESULTS: Kaplan-Meier analysis revealed that survival rates declined as fibrosis, reticulation, honeycombing, consolidation, and emphysema scores increased. Cox regression analysis revealed that reticulation had the most significant impact on survival rate, followed by honeycombing, consolidation, and emphysema scores. Hierarchical and K-means cluster analyses revealed 3 clusters. Cluster 1 (n = 126) with the lowest values for all parameters had the longest survival duration, and relatively-well preserved FVC and DLCO. Cluster 2 (n = 15) with high reticulation and consolidation scores had the lowest FVC and DLCO values with a predominance of female, while cluster 3 (n = 18) with high honeycombing and emphysema scores predominantly consisted of male smokers. Kaplan-Meier analysis revealed that cluster 2 had the lowest survival rate, followed by cluster 3 and cluster 1. CONCLUSION: Automated quantitative CT analysis provides valuable information for predicting clinical outcomes, and clustering based on these parameters may help identify the high-risk group for management.

S100 Calcium-Binding Protein A9, a Potential Novel Diagnostic Biomarker for Idiopathic Pulmonary Fibrosis.

BACKGROUND: Neutrophilic inflammation is a characteristic feature of idiopathic pulmonary fibrosis (IPF). S100 calcium-binding protein A9 (S100A9) is a neutrophil-derived protein involved in the development of neutrophil-related chronic inflammatory disorders. However, the role of S100A9 in IPF remains unclear. METHODS: We used enzyme-linked immunosorbent assays to measure S100A9 levels in bronchoalveolar lavage fluid (BALF) and serum obtained from healthy controls (HCs) and patients with IPF, non-specific interstitial pneumonia, hypersensitivity pneumonitis, and sarcoidosis. RESULTS: Compared with HCs, BALF S100A9 levels were significantly higher in IPF patients (P < 0.001), patients with hypersensitivity pneumonitis (P = 0.043), and patients with nonspecific interstitial pneumonia (P < 0.001). The S100A9 level in BALF of 0.093 ng/mL could distinguish IPF patients from HCs, with a specificity of 78.8% and a sensitivity of 81.6%. Similarly, the S100A9 level in BALF of 0.239 ng/mL had a specificity of 64.7% and a sensitivity of 66.7% for distinguishing IPF patients from patients with other interstitial lung diseases. Additionally, BALF S100A9 levels were significantly correlated with neutrophil counts (r = 0.356, P < 0.001) in BALF. IPF patients with S100A9 levels in BALF > 0.533 ng/mL had lower survival rates, compared with patients who had levels ≤ 0.553 ng/mL (n = 49; hazard ratio [HR], 3.62; P = 0.021). Combination analysis revealed that IPF patients with S100A9 levels in BALF> 0.553 ng/mL or neutrophil percentages > 49.1% (n = 43) had significantly lower survival rates than patients with S100A9 levels in BALF ≤ 0.553 ng/mL and neutrophil percentages ≤ 49.1% (n = 41) (HR, 3.91; P = 0.014). Additionally, patients with serum S100A9 levels > 0.077 ng/mL (n = 29) had significantly lower survival rates than patients with levels ≤ 0.077 ng/mL (n = 53, HR, 2.52; P = 0.013). S100A9 was expressed on neutrophils and macrophages in BALF from IPF patients as well as α-smooth muscle actin positive cells in the lung tissues. CONCLUSION: S100A9 is involved in the development and progression of IPF. Moreover, S100A9 levels in BALF and serum may be surrogate markers for IPF diagnosis and survival prediction, particularly when analyzed in combination with neutrophil percentages.

Pattern Mining-Based Pig Behavior Analysis for Health and Welfare Monitoring.

The increasing popularity of pigs has prompted farmers to increase pig production to meet the growing demand. However, while the number of pigs is increasing, that of farm workers has been declining, making it challenging to perform various farm tasks, the most important among them being managing the pigs' health and welfare. This study proposes a pattern mining-based pig behavior analysis system to provide visualized information and behavioral patterns, assisting farmers in effectively monitoring and assessing pigs' health and welfare. The system consists of four modules: (1) data acquisition module for collecting pigs video; (2) detection and tracking module for localizing and uniquely identifying pigs, using tracking information to crop pig images; (3) pig behavior recognition module for recognizing pig behaviors from sequences of cropped images; and (4) pig behavior analysis module for providing visualized information and behavioral patterns to effectively help farmers understand and manage pigs. In the second module, we utilize ByteTrack, which comprises YOLOx as the detector and the BYTE algorithm as the tracker, while MnasNet and LSTM serve as appearance features and temporal information extractors in the third module. The experimental results show that the system achieved a multi-object tracking accuracy of 0.971 for tracking and an F1 score of 0.931 for behavior recognition, while also highlighting the effectiveness of visualization and pattern mining in helping farmers comprehend and manage pigs' health and welfare.

Behavior-Based Video Summarization System for Dog Health and Welfare Monitoring.

The popularity of dogs has been increasing owing to factors such as the physical and mental health benefits associated with raising them. While owners care about their dogs' health and welfare, it is difficult for them to assess these, and frequent veterinary checkups represent a growing financial burden. In this study, we propose a behavior-based video summarization and visualization system for monitoring a dog's behavioral patterns to help assess its health and welfare. The system proceeds in four modules: (1) a video data collection and preprocessing module; (2) an object detection-based module for retrieving image sequences where the dog is alone and cropping them to reduce background noise; (3) a dog behavior recognition module using two-stream EfficientNetV2 to extract appearance and motion features from the cropped images and their respective optical flow, followed by a long short-term memory (LSTM) model to recognize the dog's behaviors; and (4) a summarization and visualization module to provide effective visual summaries of the dog's location and behavior information to help assess and understand its health and welfare. The experimental results show that the system achieved an average F1 score of 0.955 for behavior recognition, with an execution time allowing real-time processing, while the summarization and visualization results demonstrate how the system can help owners assess and understand their dog's health and welfare.

The Role of Erythrocyte Membrane Protein Band 4.1-like 3 in Idiopathic Pulmonary Fibrosis.

Novel genetic and epigenetic factors involved in the development and prognosis of idiopathic pulmonary fibrosis (IPF) have been identified. We previously observed that erythrocyte membrane protein band 4.1-like 3 (EPB41L3) increased in the lung fibroblasts of IPF patients. Thus, we investigated the role of EPB41L3 in IPF by comparing the EPB41L3 mRNA and protein expression of lung fibroblast between patients with IPF and controls. We also investigated the regulation of epithelial-mesenchymal transition (EMT) in an epithelial cell line (A549) and fibroblast-to-myofibroblast transition (FMT) in a fibroblast cell line (MRC5) by overexpressing and silencing EPB41L3. EPB41L3 mRNA and protein levels, as measured using RT-PCR, real-time PCR, and Western blot, were significantly higher in fibroblasts derived from 14 IPF patients than in those from 10 controls. The mRNA and protein expression of EPB41L3 was upregulated during transforming growth factor-ß-induced EMT and FMT. Overexpression of EPB41L3 in A549 cells using lenti-EPB41L3 transfection suppressed the mRNA and protein expression of N-cadherin and COL1A1. Treatment with EPB41L3 siRNA upregulated the mRNA and protein expression of N-cadherin. Overexpression of EPB41L3 in MRC5 cells using lenti-EPB41L3 transfection suppressed the mRNA and protein expression of fibronectin and α-SMA. Finally, treatment with EPB41L3 siRNA upregulated the mRNA and protein expression of FN1, COL1A1, and VIM. In conclusion, these data strongly support an inhibitory effect of EPB41L3 on the process of fibrosis and suggest the therapeutic potential of EPB41L3 as an anti-fibrotic mediator.

Association of ATP8B3 gene polymorphisms with aspirin-exacerbated respiratory disease in asthmatics.

BACKGROUND: Aspirin-exacerbated respiratory disease (AERD), an asthma phenotype, often presents with severe manifestations and it remains widely underdiagnosed because of insufficient awareness of the relationship between the ingestion of nonsteroidal anti-inflammatory drugs, including acetylsalicylic acid (ASA), and asthma exacerbation. Our previous genome-wide association study demonstrated an association between a single nucleotide polymorphism (SNP) of the ATP8B3 gene and the risk of AERD. This study examined AERD-related SNPs of the ATP8B3 gene in a large population. METHODS: Twenty-five SNPs of ATP8B3 were genotyped with the GoldenGate assay using VeraCode microbeads in 141 asthmatics with AERD and 995 Aspirin-tolerant asthma (ATA). The genotype distribution was analyzed using logistic regression models. The declines in forced expiratory volume in 1 second (FEV1)following an ASA challenge were compared among the genotypes and haplotypes using a type III generalized linear model. RESULTS: The minor allele frequencies (MAFs) of rs10421558 A>G in the 5'UTR and rs10403288 G>A in the intron were significantly lower in the AERD than the ATA [34.0% vs. 43.8%, OR = 0.66 (0.62-0.92), Pcorr = 0.03 and 28.4% vs. 35.4%, OR = 0.62 (0.59-0.89), Pcorr = 0.016, respectively]. BL1ht5 was significantly higher in the AERD [7.6% vs. 1.6%, OR = 12.23 (0.2-0.51), P = 4.7 × 10 -4 , Pcorr = 0.001]. Among them, rs10421558 A>G and BL1ht5 were associated with the percent decline in FEV1 on the oral ASA challenge test. CONCLUSION: The minor allele of rs10421558 A>G in the 5'UTR may protect against the development of AERD via the increased production of ATP8B3.

Genome-wide DNA methylation profile of peripheral blood lymphocytes from subjects with nonsteroidal anti-inflammatory drug-induced respiratory diseases.

BACKGROUND: Significant changes in CpG methylation have been identified in nasal polyps, which are the main targets of nonsteroidal anti-inflammatory drug-exacerbated respiratory disease (NERD); however, these polyps are composed of various cellular components. In the present study, whole-genome CpG methylation in peripheral blood lymphocytes (PBLs) was analyzed to define the epigenetic changes in lymphocytes, which are the primary immune cells involved in NERD. MATERIALS AND METHODS: Genomic DNA from peripheral blood mononuclear cells from 27 NERD and 24 aspirin-tolerant asthma (ATA) was subjected to bisulfate conversion and a methylation array. Quantitative CpG methylation, the ß-values as a quantitative measure of DNA methylation, in lymphocytes were calculated after adjustments for cellular composition. RESULTS: Fifty-six hypermethylated and three hypomethylated differentially methylated CpGs (DMCs) in PBLs in the NERD compared with ATA. The top 10 CpG loci predicted the methylation risk score, with a positive predictive value of 91.3%, a negative predictive value of 81.5% and an accuracy of 84.3%. As demonstrated in the nasal polyps, 30 DMCs were predicted to bind to the following 10 transcription factors, ranked in descending order: AP-2alphaA, TFII-1, STAT4, FOXP3, GR, c-Est-1, E2F-1, XBP1, ENKTF-1 and NF-1. Gene ontology analysis identified 13 categories such as regulation of T-helper 17 cell differentiation, including SMAD7 and NFKBIZ. PBLs in NERD contained no DMCs in genes associated with the prostaglandin and leukotriene pathways, which were found in ATA. CONCLUSION: PBLs in NERD form a unique pattern of DNA CpG methylation, and the combined analysis may provide predictive values for NERD.

Association of genetic variants of oxidative stress responsive kinase 1 (OXSR1) with asthma exacerbations in non-smoking asthmatics.

BACKGROUND: Asthma exacerbation threatens patient's life. Several genetic studies have been conducted to determine the risk factors for asthma exacerbation, but this information is still lacking. We aimed to determine whether genetic variants of Oxidative Stress Responsive Kinase 1 (OXSR1), a gene with functions of salt transport, immune response, and oxidative stress, are associated with exacerbation of asthma. METHODS: Clinical data were obtained from 1454 asthmatics and single nucleotide polymorphisms (SNPs) of OXSR1 were genotyped. Genetic associations with annual exacerbation rate were analyzed depending on smoking status. RESULTS: Eleven SNPs were selected using Asian data in the International HapMap database. The common allele of rs1384006 C > T of OXSR1 showed a significantly higher annual exacerbation rate than the rare allele in non-smoking asthmatics (CC vs. CT vs. TT: 0.43 ± 0.04 vs. 0.28 ± 0.03 vs. 0.31 ± 0.09, P = 0.004, Pcorr = 0.039). The frequent exacerbators had a significantly higher frequency of the common allele of rs1384006 C > T than did the infrequent exacerbators (74.4% vs. 55.2%, P = 0.004, Pcorr = 0.038). CONCLUSION: The common allele of rs1384006 C > T of OXSR1 was associated with the asthma exacerbation rate and a higher risk of being a frequent exacerbator, indicating that non-smoking asthmatics who carry common alleles may be vulnerable to asthma exacerbations.

GAN-Based Video Denoising with Attention Mechanism for Field-Applicable Pig Detection System.

Infrared cameras allow non-invasive and 24 h continuous monitoring. Thus, they are widely used in automatic pig monitoring, which is essential to maintain the profitability and sustainability of intensive pig farms. However, in practice, impurities such as insect secretions continuously pollute camera lenses. This causes problems with IR reflections, which can seriously affect pig detection performance. In this study, we propose a noise-robust, real-time pig detection system that can improve accuracy in pig farms where infrared cameras suffer from the IR reflection problem. The system consists of a data collector to collect infrared images, a preprocessor to transform noisy images into clean images, and a detector to detect pigs. The preprocessor embeds a multi-scale spatial attention module in U-net and generative adversarial network (GAN) models, enabling the model to pay more attention to the noisy area. The GAN model was trained on paired sets of clean data and data with simulated noise. It can operate in a real-time and end-to-end manner. Experimental results show that the proposed preprocessor was able to significantly improve the average precision of pig detection from 0.766 to 0.906, with an additional execution time of only 4.8 ms on a PC environment.

Multi-level Hierarchical Complex Behavior Monitoring System for Dog Psychological Separation Anxiety Symptoms.

An increasing number of people own dogs due to the emotional benefits they bring to their owners. However, many owners are forced to leave their dogs at home alone, increasing the risk of developing psychological disorders such as separation anxiety, typically accompanied by complex behavioral symptoms including excessive vocalization and destructive behavior. Hence, this work proposes a multi-level hierarchical early detection system for psychological Separation Anxiety (SA) symptoms detection that automatically monitors home-alone dogs starting from the most fundamental postures, followed by atomic behaviors, and then detecting separation anxiety-related complex behaviors. Stacked Long Short-Term Memory (LSTM) is utilized at the lowest level to recognize postures using time-series data from wearable sensors. Then, the recognized postures are input into a Complex Event Processing (CEP) engine that relies on knowledge rules employing fuzzy logic (Fuzzy-CEP) for atomic behaviors level and higher complex behaviors level identification. The proposed method is evaluated utilizing data collected from eight dogs recruited based on clinical inclusion criteria. The experimental results show that our system achieves approximately an F1-score of 0.86, proving its efficiency in separation anxiety symptomatic complex behavior monitoring of a home-alone dog.

Erratum to "Effects of Ammonium Chloride on Ozone-induced Airway Inflammation: the Role of Slc26a4 in the Lungs of Mice".

This corrects the article on p. e272 in vol. 35, PMID: 32808511.

Airway G-CSF identifies neutrophilic inflammation and contributes to asthma progression.

Stratification of asthmatic patients based on relevant biomarkers enables the prediction of responsiveness against immune-targeted therapies in patients with asthma. Individualised therapy in patients with eosinophilic asthma has yielded improved clinical outcomes; similar approaches in patients with neutrophilic asthma have yet to be developed. We determined whether colony-stimulating factors (CSFs) in the airway reflect the inflammatory phenotypes of asthma and contribute to disease progression of neutrophilic asthma.We analysed three different mouse models of asthma and assessed cytokine profiles in sputum from human patients with asthma stratified according to inflammatory phenotype. In addition, we evaluated the therapeutic efficacy of various cytokine blockades in a mouse model of neutrophilic asthma.Among the CSFs, airway granulocyte CSF (G-CSF) contributes to airway neutrophilia by promoting neutrophil development in bone marrow and thereby distinguishes neutrophilic inflammation from eosinophilic inflammation in mouse models of asthma. G-CSF is produced by concurrent stimulation of the lung epithelium with interleukin (IL)-17A and tumour necrosis factor (TNF)-α; therefore, dual blockade of upstream stimuli using monoclonal antibodies or genetic deficiency of the cytokines in IL-17A×TNF-α double-knockout mice reduced the serum level of G-CSF, leading to alleviation of neutrophilic inflammation in the airway. In humans, the sputum level of G-CSF can be used to stratify patients with asthma with neutrophil-dominated inflammation.Our results indicated that myelopoiesis-promoting G-CSF and cytokines as the upstream inducing factors are potential diagnostic and therapeutic targets in patients with neutrophilic asthma.

Effects of air pollution on moderate and severe asthma exacerbations.

Background: Few studies have evaluated the impact of air pollution levels on the severity of exacerbations. Thus, we compared the relative risks posed by air pollutant levels on moderate and severe exacerbations.Methods: Exacerbation episodes of 618 from 143 adult asthmatics were retrospectively collected between 2005 and 2015 in a tertiary hospital of Korea. Air pollution GPS data for the location closest to each patient's home were obtained from the national ambient monitoring station. The relative impacts of air pollutants on asthma exacerbations were evaluated via a time-trend controlled symmetrical, bidirectional, case-crossover design using conditional logistic regression models on the day of the exacerbation (T-0) and up to 3 days before the exacerbation (T-1-T-3).Results: Overall asthma exacerbation were associated with O3 levels in summer and winter (OR: 1.012[1.003-1.02] and 1.009[1.003-1.016]), SO2 levels in spring and summer (OR: 1.009[1-1.018] and 1.02[1.006-1.035]) and NO2 levels in winter (OR: 1.007[1.003-1.011]). Analyses of the temporal relationship between O3 concentrations and exacerbations demonstrated that 63.2% of episodes in the summer occurred when the O3 concentrations on T-1 were significantly higher than those on control days, while 51% of exacerbation episodes in the winter occurred. Severe and moderate exacerbations were similarly associated with O3 levels in winter (OR: 1.012 [1.003-1.02] vs. 1.01 [0.999-1.021], p > 0.05) and in summer (OR: 1.006 [1.002-1.009] vs. 1.009 [1.003-1.016], p > 0.05).Conclusions: Asthma exacerbations may be associated with the seasonal elevation of O3, SO2 and NO2 levels in summer and winter with the similar relative risk between moderate and severe exacerbations.

Associations between TMEM196 polymorphisms and NSAID-exacerbated respiratory disease in asthma.

BACKGROUND: We previously found differences in the minor allele frequency (MAF) of single-nucleotide polymorphisms (SNPs) in transmembrane protein 196 (TMEM196) between 995 patients with aspirin-tolerant asthma (ATA) and 141 asthmatic patients with NSAID-exacerbated respiratory disease (NERD). In this study, we statistically analyzed the distributions of the genotypes and haplotypes of these SNPs to determine the exact association between TMEM196 genetic variants and the risk for NERD. MATERIALS AND METHODS: Lewontin's D' and r values were used to measure linkage disequilibrium between the biallelic loci having MAFs more than 0.05, and haplotypes were inferred using the PHASE algorithm (version 2.0). The genotype distribution was analyzed by logistic regression models using age of onset, smoking status (nonsmoker=0, ex-smoker=1, smoker=2), and BMI as covariates. Regression analysis of the association between SNPs and the risk of NERD was analyzed using SPSS version 12.0 and PLINK version 1.9. RESULTS: The MAF of rs9886152 C>T was significantly lower in NERD than in ATA [24.8 vs. 34.0%, odds ratio=0.64 (0.48-0.85), P=2.07×10, Pcorr=0.048]. The rate of the rs9886152 C>T minor allele was significantly lower in NERD than in ATA [44.0 vs. 56.4% in the codominant model, P=0.002, Pcorr=0.049, odds ratio=0.64 (0.48-0.85)]. An additional three SNPs (rs9639334 A>G, rs9638765 A>G, and rs2097811 G>A) showed similar associations with the risk of NERD. NERD patients had lower frequencies of the rs9639334 A>G minor allele (51.1 vs. 64.4%, P=0.002, Pcorr=0.043), rs9638765 A>G (49.7 vs. 64.2%, P=0.001, Pcorr=0.017), and rs2097811 G>A (51.1 vs. 64.5%, P=0.002, Pcorr=0.04) compared with ATA patients. Patients homozygous for the minor alleles of the four SNPs showed significantly less of an aspirin-induced decrease in forced expiratory volume in one second compared with those homozygous for the common alleles (P=0.003-0.012). CONCLUSION: The minor alleles of the four SNPs in TMEM196 may exert a protective effect against the development of NERD and may be useful genetic markers to predict the risk of NERD.

Gene profile of fibroblasts identify relation of CCL8 with idiopathic pulmonary fibrosis.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is characterized by the complex interaction of cells involved in chronic inflammation and fibrosis. Global gene expression of a homogenous cell population will identify novel candidate genes. METHODS: Gene expression of fibroblasts derived from lung tissues (8 IPF and 4 controls) was profiled, and ontology and functional pathway were analyzed in the genes exhibiting >2 absolute fold changes with p-values < 0.05. CCL8 mRNA and protein levels were quantified using real-time PCR and ELISA. CCL8 localization was evaluated by immunofluorescence staining. RESULTS: One hundred seventy eight genes differentially expressed and 15 genes exhibited >10-fold change. Among them, 13 were novel in relation with IPF. CCL8 expression was 22.8-fold higher in IPF fibroblasts. The levels of CCL8 mRNA and protein were 3 and 9-fold higher in 14 IPF fibroblasts than those in 10 control fibroblasts by real-time PCR and ELISA (p = 0.022 and p = 0.026, respectively). The CCL8 concentrations in BAL fluid was significantly higher in 86 patients with IPF than those in 41 controls, and other interstitial lung diseases including non-specific interstitial pneumonia (n = 22), hypersensitivity pneumonitis (n = 20) and sarcoidosis (n = 19) (p < 0.005, respectively). Cut-off values of 2.29 pg/mL and 0.43 pg/mL possessed 80.2 and 70.7% accuracy for the discrimination of IPF from NC and the other lung diseases, respectively. IPF subjects with CCL8 levels >28.61 pg/mL showed shorter survival compared to those with lower levels (p = 0.012). CCL8 was expressed by α-SMA-positive cells in the interstitium of IPF. CONCLUSIONS: Transcriptome analysis identified several novel IPF-related genes. Among them, CCL8 is a candidate molecule for the differential diagnosis and prediction of survival.

Upregulation of interleukin-33 and thymic stromal lymphopoietin levels in the lungs of idiopathic pulmonary fibrosis.

BACKGROUND: Innate T helper type 2 (Th2) immune responses mediated by interleukin (IL)-33, thymic stromal lymphopoietin (TSLP), and IL-25 have been shown to play an important role in pulmonary fibrosis of animal models; however, their clinical implications remain poorly understood. METHODS: TSLP, IL-25, and IL-33 concentrations were measured in bronchoalveolar lavage fluids obtained from normal controls (NCs; n = 40) and from patients with idiopathic pulmonary fibrosis (IPF; n = 100), non-specific interstitial pneumonia (NSIP; n = 22), hypersensitivity pneumonitis (HP; n = 20), and sarcoidosis (n = 19). RESULTS: The TSLP and IL-33 levels were significantly higher in patients with IPF relative to the NCs (p = 0.01 and p = 0.0001, respectively), NSIP (p = 4.95E - 7 and p = 0.0002, respectively), HP (p = 0.00003 and p = 0.000005, respectively), and sarcoidosis groups (p = 0.003 and p = 0.0001, respectively). However, the IL-25 levels were not significantly different between NC and IPF group (p = 0.432). Receiver operating characteristic curves of the TSLP and IL-33 levels revealed clear differences between the IPF and NC groups (AUC = 0.655 and 0.706, respectively), as well as between the IPF and the other lung disease groups (AUC = 0.786 and 0.781, respectively). Cut-off values of 3.52 pg/µg TSLP and 3.77 pg/µg IL-33 were shown to differentiate between the IPF and NC groups with 99.2 and 94.3% accuracy. Cut-off values of 4.66 pg/µg TSLP and 2.52 pg/µg IL-33 possessed 99.4 and 93.2% accuracy for differentiating among the IPF and other interstitial lung disease groups. CONCLUSIONS: Innate immune responses may be associated with the development of IPF. Furthermore, the IL-33 and TSLP levels in BAL fluids may be useful for differentiating IPF from other chronic interstitial lung diseases.

Automatic Recognition of Aggressive Behavior in Pigs Using a Kinect Depth Sensor.

Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. In this study, we developed a non-invasive, inexpensive, automatic monitoring prototype system that uses a Kinect depth sensor to recognize aggressive behavior in a commercial pigpen. The method begins by extracting activity features from the Kinect depth information obtained in a pigsty. The detection and classification module, which employs two binary-classifier support vector machines in a hierarchical manner, detects aggressive activity, and classifies it into aggressive sub-types such as head-to-head (or body) knocking and chasing. Our experimental results showed that this method is effective for detecting aggressive pig behaviors in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (detection and classification accuracies over 95.7% and 90.2%, respectively), either as a standalone solution or to complement existing methods.

Fault Detection and Diagnosis of Railway Point Machines by Sound Analysis.

Railway point devices act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Point failure can significantly affect railway operations, with potentially disastrous consequences. Therefore, early detection of anomalies is critical for monitoring and managing the condition of rail infrastructure. We present a data mining solution that utilizes audio data to efficiently detect and diagnose faults in railway condition monitoring systems. The system enables extracting mel-frequency cepstrum coefficients (MFCCs) from audio data with reduced feature dimensions using attribute subset selection, and employs support vector machines (SVMs) for early detection and classification of anomalies. Experimental results show that the system enables cost-effective detection and diagnosis of faults using a cheap microphone, with accuracy exceeding 94.1% whether used alone or in combination with other known methods.

Stress detection and classification of laying hens by sound analysis.

Stress adversely affects the wellbeing of commercial chickens, and comes with an economic cost to the industry that cannot be ignored. In this paper, we first develop an inexpensive and non-invasive, automatic online-monitoring prototype that uses sound data to notify producers of a stressful situation in a commercial poultry facility. The proposed system is structured hierarchically with three binary-classifier support vector machines. First, it selects an optimal acoustic feature subset from the sound emitted by the laying hens. The detection and classification module detects the stress from changes in the sound and classifies it into subsidiary sound types, such as physical stress from changes in temperature, and mental stress from fear. Finally, an experimental evaluation was performed using real sound data from an audio-surveillance system. The accuracy in detecting stress approached 96.2%, and the classification model was validated, confirming that the average classification accuracy was 96.7%, and that its recall and precision measures were satisfactory.