Deep learning-based algorithm for classifying high-resolution computed tomography features in coal workers' pneumoconiosis

BACKGROUND

Coal workers' pneumoconiosis is a chronic occupational lung disease with considerable pulmonary complications, including irreversible lung diseases that are too complex to accurately identify via chest X-rays. The classification of clinical imaging features from high-resolution computed tomography might become a powerful clinical tool for diagnosing pneumoconiosis in the future.

METHODS

All chest high-resolution computed tomography (HRCT) medical images presented in this work were obtained from 217 coal workers' pneumoconiosis (CWP) patients and dust-exposed workers. We segmented regions of interest according to the diagnostic results, which were evaluated by radiologists. These regions were then classified regions into four categories. We employed an efficient deep learning model and various image augmentation techniques (DenseNet-ECA). The classification performance of the different deep learning models was assessed, and receiver operating characteristic (ROC) curves and accuracy (ACC) were used to determine the optimal algorithm for classifying CWP clinical imaging features obtained from HRCT images.

RESULTS

Four primary clinical imaging features in HRCT images, with a total of more than 1700 regions of interest (ROIs), were annotated, augmented, and used as a training set for tenfold cross-validation to generate the model. We selected DenseNet-Attention Net as the optimal model through assessing the performance of different classification algorithms, which yielded an average area under the ROC curve (AUC) of 0.98, and all clinical imaging features were classified with an AUC greater than 0.92. For the individual classifications, the AUCs were as follows: small miliary opacities, 0.99; nodular opacities, 1.0; interstitial changes, 0.92; and emphysema, 1.0.

CONCLUSION

We successfully applied a data augmentation strategy to develop a deep learning model by combining DenseNet with ECA-Net. We used our novel model to automatically classify CWP clinical imaging features from 2D HRCT images. This successful application of a deep learning-data augmentation algorithm can help clinical radiologists by providing reliable diagnostic information for classification.

TRIAL REGISTRATION

Chinese Clinical Trial Registry, ChiCTR2100050379. Registered on 27 August 2021, https://www.chictr.org.cn/bin/project/edit?pid=132619 .

Candidate gene polymorphisms associated with silicosis and coal workers' pneumoconiosis: a systematic review and meta-analysis

BACKGROUND

Silicosis and coal worker's pneumoconiosis primarily result from exposure to silica and coal dust. Despite similar exposure levels, individuals exhibit varying responses. This study aimed to address these gaps to explore the genetic factors influencing the development, severity, and associated complications.

METHODS

A systematic literature search was performed across four databases-PubMed, Embase, Web of Science, and Cochrane Library-until July, 2023. Qualitative and quantitative analyses were applied to identify candidate genes.

RESULTS

This study involved 83 articles and encompassed 545 individual studies, reviewing a total of 378 gene loci. After rigorous evaluation, we selected 8 candidate genes (TNFα-308, TNFα-238, GSTT1, IL-1α + 4845, IL-1β-511, IL-1β + 3953, IL-1RA + 2018, and IL-6-174) for meta-analysis. The analysis revealed that allele A of TNFα-308, allele A of TNFα-238, and allele C of IL-1RA + 2018 were identified as risk factors for the development of diseases.

CONCLUSIONS

This study established associations between specific genetic polymorphisms (TNFα-308, TNFα-238, and IL-1RA + 2018) and susceptibility to silicosis and coal worker's pneumoconiosis.

Efficient clinical data analysis for prediction of coal workers' pneumoconiosis using machine learning algorithms

PURPOSE

The purpose of this study is to propose an efficient coal workers' pneumoconiosis (CWP) clinical prediction system and put it into clinical use for clinical diagnosis of pneumoconiosis.

METHODS

Patients with CWP and dust-exposed workers who were enrolled from August 2021 to December 2021 were included in this study. Firstly, we chose the embedded method through using three feature selection approaches to perform the prediction analysis. Then, we performed the machine learning algorithms as the model backbone and combined them with three feature selection methods, respectively, to determine the optimal predictive model for CWP.

RESULTS

Through applying three feature selection approaches based on machine learning algorithms, it was found that AaDO₂ and some pulmonary function indicators played an important role in prediction for identifying CWP of early stage. The support vector machine (SVM) algorithm was proved as the optimal machine learning model for predicting CWP, with the ROC curves obtained from three feature selection methods using SVM algorithm whose AUC values of 97.78%, 93.7%, and 95.56%, respectively.

CONCLUSION

We developed the optimal model (SVM algorithm) through comparisons and analyses among the performances of different models for the prediction of CWP as a clinical application.

Genetic susceptibility in pneumoconiosis in China: a systematic review

OBJECTIVE

Pneumoconiosis, encompassing coal workers' pneumoconiosis (CWP), silicosis and asbestosis, is one of the most common occupational diseases in China. Previous studies revealed significant associations between genetic variations and pneumoconiosis risk among individuals in different countries. With the known variability of genetic makeup between ethnicities, susceptibility to pneumoconiosis due to genetic differences is likely to be ethnicity-specific. The present review aimed at providing a comprehensive overview on the association between genetic polymorphisms and susceptibility of pneumoconiosis, specifically among people in China.

METHODS

The literature search was performed in seven English and Chinese databases using keywords related to the review aim. An appraisal of the methodological quality of the included studies was conducted using the assessment tool derived from the Strengthening the Reporting of Genetic Association Studies (STREGA) statement.

RESULTS

Forty-five studies were included in this review. Genotypes of specific genes which are associated with the risk of CWP, silicosis and asbestosis were reported. Our findings showed that genes encoding inflammatory cytokines have been examined extensively, and they demonstrated an association between these genes and pneumoconiosis risk. Gene-environment interactions in pneumoconiosis susceptibility were also reported by a number of studies.

CONCLUSIONS

This review summarised the evidence demonstrating the association between genetic polymorphisms and pneumoconiosis susceptibility among people in China, and that various genotypes could modify their risk to develop pneumoconiosis. The findings prompt that identification of individuals at high pneumoconiosis risk through genetic screening and strategies limiting their exposure to dust could be a potential strategy for the control of this occupational disease in China.

Transcriptome-wide association study identifies PSMB9 as a susceptibility gene for coal workers' pneumoconiosis

Coal workers' pneumoconiosis (CWP) is a type of typical occupational lung disease caused by prolonged inhalation of coal mine dust. The individuals' different genetic background may underlie their different susceptibility to develop pneumoconiosis, even under the same exposure level. This study aimed to identify susceptibility genes associated with CWP. Based on our previous genome-wide association study (GWAS, 202 CWP cases vs. 198 controls) and gene expression data obtained by analyzing human lungs and whole blood from the Genotype-Tissue Expression (GTEx) Portal, a transcriptome-wide association study (TWAS) was applied to identify CWP risk-related genes. Luciferase report gene assay, qRT-PCR, Western blot, immunofluorescence assay, and TUNEL assay were conducted to explore the potential role of the candidate gene in CWP. Proteasome 20S subunit beta 9 (PSMB9) was identified as a strong risk-related gene of CWP in both lungs and whole blood (Lungs: P_TWAS  = 4.22 × 10^-4 ; Whole blood: P_TWAS  = 2.11 × 10^-4 ). Single nucleotide polymorphisms (SNPs) rs2071480 and rs1351383, which locate in the promoter region and the first intron of the PSMB9 gene, were in high linkage disequilibrium (LD, r²  = 0.98) with the best GWAS SNP rs4713600 (G>T, OR = 0.55, 95% CI: 0.42-0.74, P = 6.86 × 10^-5 ). Both rs2071480 and rs1351383 significantly enhanced the transcriptional activity of PSMB9. Functional experiments revealed that silica exposure remarkably reduced the PSMB9 expression and caused cell apoptosis, while overexpression of PSMB9 markedly abolished silica-induced cell apoptosis. We here identified PSMB9 as a novel susceptibility gene for CWP and provided important insights into the further exploration of the CWP pathogenesis.

LncRNA MEG3 ameliorates NiO nanoparticles-induced pulmonary inflammatory damage via suppressing the p38 mitogen activated protein kinases pathway

The lung inflammatory damage could result from the nickel oxide nanoparticles (NiO NPs), in which the underlying mechanism is still unclear. This article explored the roles of long noncoding RNA maternally expressed gene 3 (lncRNA MEG3) and p38 mitogen activated protein kinases (p38 MAPK) pathway in pulmonary inflammatory injury induced by NiO NPs. Wistar rats were treated with NiO NPs suspensions (0.015, 0.06, and 0.24 mg/kg) by intratracheal instillation twice-weekly for 9 weeks. Meanwhile, A549 cells were treated with NiO NPs suspensions (25, 50, and 100 μg/ml) for 24 h. It can be concluded that the NiO NPs did trigger pulmonary inflammatory damage, which was confirmed by the histopathological examination, abnormal changes of inflammatory cells and inflammatory cytokines (IL-1β, IL-6, TGF-β1, TNF-α, IFN-γ, IL-10, CXCL-1 and CXCL-2) in bronchoalveolar lavage fluid (BALF), pulmonary tissue and cell culture supernatant. Furthermore, NiO NPs activated the p38 MAPK pathway and downregulated MEG3 in vivo and in vitro. However, p38 MAPK pathway inhibitor (10 μM SB203580) reversed the alterations in the expression levels of inflammatory cytokines induced by NiO NPs. Meanwhile, over-expressed MEG3 significantly suppressed NiO NPs-induced p38 MAPK pathway activation and inflammatory cytokines changes. Overall, the above results proved that over-expression of lncRNA MEG3 reduced NiO NPs-induced inflammatory damage by preventing the activation of p38 MAPK pathway.

Associations of SMAD4 rs10502913 and NLRP3 rs1539019 Polymorphisms with Risk of Coal Workers’ Pneumoconiosis Susceptibility in Chinese Han Population

Purpose

CWP is an untreatable but preventable fibrotic lung disease caused by the chronic inhalation of coal dust. Genetic factors such as polymorphisms play an important role in the development of CWP. The present study investigated the association between the polymorphisms of SMAD4 and NLRP3 and CWP risk in a Chinese Han population.

Patients and Methods

SMAD4 rs10502913 and NLRP3rs1539019 polymorphisms were examined in 292 CWP subjects and 315 coal dust-exposed controls. The genotypes were analyzed using direct sequencing. The allele and genotype proportion between the cases and controls were compared using the chi-square test.

Results

The AG and GG genotypes of SMAD4 rs10502913 were not associated with altered CWP risk compared with AA genotype (adjusted OR = 1.535 and 1.426, 95% CI = 0.785–3.000 and 0.732–2.781, p = 0.210 and 0.297, respectively). Also, the NLRP3 rs1539019 heterozygous and homozygous variants CA and CC genotypes were not associated with the risk of CWP compared with the AA genotype (adjusted OR = 0.985 and 1.127, 95% CI = 0.652–1.489 and 0.713–1.782, p = 0.944 and 0.608, respectively). In addition, there was no interaction between SMAD4 rs10502913 and NLRP3 rs1539019 genotypes and smoking status on CWP risk in the stratified analyses.

Conclusion

In this present study, SMAD4 rs10502913 and NLRP3 rs1539019 genotypes were not associated with altered CWP risk in the Chinese Han population. Large sample sizes and multicenter studies are needed to elucidate these results in the future.

Identification of Genetic Susceptibility Factors Associated with Canine Gastric Dilatation-Volvulus

Canine gastric dilatation-volvulus (GDV) is a common life-threatening condition occurring primarily in large and giant breeds with a 3.9% to 36.7% lifetime risk. The genetic correlates of GDV have not previously been systematically explored. We undertook an inter-breed genome-wide association analysis (GWAS) of 253 dogs from ten breeds including 106 healthy dogs and 147 dogs with at least one GDV episode. SNP array genotyping followed by imputation was conducted on 241 samples to identify GDV-associated single-nucleotide polymorphisms (SNPs) and copy number variations (CNVs). A subset of 33 dogs (15 healthy dogs and 18 GDV patients from the three most represented breeds) was characterized by whole genome sequencing (WGS). After genome-wide Bonferroni correction, we identified a significant putatively protective intergenic SNP (rs851737064) across all breeds. The signal was most significant in Collies, German Shorthaired Pointers, and Great Danes. Subsequent focused analysis across these three breeds identified 12 significant additional putatively protective or deleterious SNPs. Notable significant SNPs included those occurring in genes involved in gastric tone and motility including VHL, NALCN, and PRKCZ. These data provide important new clues to canine GDV risk factors and facilitate generation of hypotheses regarding the genetic and molecular underpinnings this syndrome.

Respiratory traits and coal workers' pneumoconiosis: Mendelian randomisation and association analysis

OBJECTIVES

Susceptibility loci of idiopathic pulmonary fibrosis and chronic obstructive pulmonary disease were also significantly associated with the predisposition of coal worker's pneumoconiosis (CWP) in recent studies. However, only a few genes and loci were targeted in previous studies.

METHODS

To systematically evaluate the genetic associations between CWP and other respiratory traits, we reviewed the reported genome-wide association study loci of five respiratory traits and then conducted a Mendelian randomisation study and a two-stage genetic association study.

RESULTS

Interestingly, we found that for each SD unit, higher lung function was associated with a 66% lower risk of CWP (OR=0.34, 95% CI: 0.15 to 0.77, p=0.010) using conventional Mendelian randomisation analysis (inverse variance weighted method). Moreover, we found susceptibility loci of interstitial lung disease (rs2609255, OR=1.29, p=1.61×10^-4) and lung function (rs4651005, OR=1.39, p=1.62×10^-3; rs985256, OR=0.73, p=8.24×10^-4 and rs6539952, OR=1.28, p=4.32×10^-4) were also significantly associated with the risk of CWP. Functional annotation showed these variants were significantly associated with the expression of FAM13A (rs2609255, p=7.4 ×10^-4), ANGPTL1 (rs4651005, p=5.4 ×10^-7), SPATS2L (rs985256, p=1.1 ×10^-5) and RP11-463O9.9 (rs6539952, p=7.1 ×10^-6) in normal lung tissues, which were related to autophagy pathway simultaneously according to enrichment analysis.

CONCLUSIONS

These results provided a deeper understanding of the genetic predisposition basis of CWP.

Is individual genetic susceptibility a link between silica exposure and development or severity of silicosis? A systematic review

BACKGROUND

Silicosis is a lung disease of fibrotic nature resulting from the inhalation and deposition of dust containing crystalline silica. Subjects exposed to the same environmental factors may show distinct radiological manifestations, and since silicosis is known as a multifactorial disease, it is plausible that individual genetic susceptibility may play a role in the pathology. This review of the literature aims to provide an assessment of the present data on the genetic association studies in silicosis and describe the genes that potentially might influence silicosis susceptibility in silica-exposed individuals.

METHODS

We accessed the database of PubMed for articles published in English about interindividual genetic susceptibility to silicosis using terms related to the subject matter.

RESULTS

Following the evaluation process, 28 studies were included in this systematic review, including 23 original studies and 5 meta-analyses.

CONCLUSIONS

Regardless of the advances in the knowledge of the importance of gene variations in silicosis, more studies need to be performed, in particular, special polygenic and genome-wide investigations.

Associations of VDR gene polymorphisms with risk of coal workers' pneumoconiosis in Chinese Han population

Some studies showed that the polymorphisms of vitamin D receptor (VDR) gene were associated with pulmonary diseases. However, the relationship between the VDR variations and susceptibility to coal worker's pneumoconiosis (CWP) remains unclear. The study aimed to determine the associations between VDR polymorphisms and susceptibility to CWP in Chinese Han population. The study involved 340 CWP patients and 312 healthy controls. The VDR polymorphisms were determined by DNA sequencing, and serum 25(OH)2D levels were detected by Ultra High-Performance Liquid Chromatography-Tandem Mass Spectrometry. The results showed that the VDR gene ApaI T allele increased the risk of CWP (OR = 1.486, 95% CI = 1.125-1.963, P = 0.006) and ApaI GT genotype as well as TT genotype increased the risk of CWP (GT vs. GG, OR = 1.461, 95% CI = 1.048-2.038, P = 0.025; TT vs. GG, OR = 2.673, 95% CI = 1.017-7.025, P = 0.039). Five haplotypes were identified and we found that the TGGT haplotype was associated with a lower risk of CWP (OR = 0.755, 95% CI = 0.603-0.946, P = 0.014). Meanwhile, multifactor dimensionality reduction analysis showed that the interaction between ApaI and exposure was the strongest, followed by TaqI and then BsmI. The study also found that the serum 25(OH)2D mean levels of the case group were significantly lower than that of the control group, and the serum 25(OH)2D mean levels of ApaI homozygous mutant and heterozygous mutant subjects were lower than that of the wild homozygosity, respectively (P < 0.001). The results suggested that ApaI T allele and GT or TT genotype and lower 25(OH)2D levels were increased the risk of CWP in Chinese Han population.

Associations of HMGB1 gene polymorphisms with risk of coal workers' pneumoconiosis susceptibility in Chinese Han population

Background: High-mobility group box 1 (HMGB1) protein plays an important pathogenic role in various diseases such as pulmonary fibrosis. However, the relationship between variation of HMGB1 gene and susceptibility to coal worker's pneumoconiosis (CWP) remains unclear. The objective of the study was to determine the association between HMGB1 polymorphisms and CWP in Chinese Han population.Methods: The genotypes of HMGB1 gene rs1045411, rs2249825, rs1412125 and rs1360485 in 340 CWP patients and 312 healthy controls were determined and serum HMGB1 levels were detected.Results: Our finding showed that the HMGB1 rs1360485 G allele increased the risk of CWP in comparison with A allele (P = 0.005). HMGB1 rs1360485 GG genotype as well as AG+GG genotype increased the risk of CWP in comparison with AA genotype (P = 0.010, P = 0.025, respectively). Four haplotypes were identified and we found that the GCTA haplotype was associated with resistance to CWP (P = 0.005), while GCTG haplotype was associated with risk to CWP (P<0.001). Meanwhile, multifactor dimensionality reduction (MDR) analysis showed that the interaction between rs1360485 and exposure had the strongest, followed by rs2249825 and rs1412125. This study also found that the serum HMGB1 levels of the case group were significantly higher than that of the control group, and the serum HMGB1 levels of homozygous subjects with rs1360485 mutant were higher than that of the heterozygous wild type, respectively (P<0.001). Meanwhile, the levels of HMGB1 with GCTA haplotype was lower than with GCTG haplotype (P<0.001)Conclusion: Our findings indicated that HMGB1 gene rs1360485 polymorphism was associated with the susceptibility to CWP in Chinese Han population.

Recent Progress in Polymer-Containing Soft Matters for Safe Mining of Coal

Safe mining is the premise and guarantee of sustainable development of coal energy. Due to the combination of excellent properties of polymers and traditional soft matters, polymer-containing soft matters are playing an increasingly important role in mine disaster and hazard control. To summarize the valuable work in recent years and provide reference and inspiration for researchers in this field, this paper reviewed the recent research progress in polymer-containing soft matters with respect to mine dust control, mine fire control, mine gas control and mine roadway support. From the perspective role of polymers in a material system, we classify mine polymer-containing soft matters into two categories. The first is polymer additive materials, in which polymers are used as additives to modify fluid-like soft matters, such as dust-reducing agents (surfactant solution) and dust-suppressing foams. The second is polymer-based materials, in which polymers are used as a main component to form high performance solid-like soft matters, such as fire prevention gels, foam gels, gas hole sealing material and resin anchorage agent. The preparation principle, properties and application of these soft matters are comprehensively reviewed. Furthermore, future research directions are also suggested.

Prediction of the length of service at the onset of coal workers' pneumoconiosis based on neural network

Three environmental parameters, i.e. dust concentrations, dust dispersion, and free silica content, were introduced into the traditional indices of the neural network model in order to construct a new prediction index and explore a new method for preventing the incidence of pneumoconiosis with intelligent accuracy and universality. Data of the pneumoconiosis patients from Huabei Mining Group (HBMG) of China from 1980 to 2017 were collected. SPSS22.0 was used to develop the combined models based on Back Propagation (BP) neural network model, Radial Basis Function (RBF) neural network model, and Multiple Linear Regression (MLR) model. The paired sample t-test was performed between the real and predicted values. According to this model, it was predicted that 382 coal workers in HBMG were likely to suffer from pneumoconiosis in 2022 and the incidence rate was 4.48%. It is necessary to take prevention measures and transfer these workers from their current positions. In four combined models, the BP-MLR combined model achieved the optimal error parameters and the most accurate prediction. This study provided a scientific basis for effective control and prevention of the incidence of the pneumoconiosis.

Functional variant of the carboxypeptidase M (CPM) gene may affect silica-related pneumoconiosis susceptibility by its expression: a multistage case-control study

Objectives

In a genome-wide association study, we discovered chromosome 12q15 (defined as rs73329476) as a silica-related pneumoconiosis susceptibility region. However, the causal variants in this region have not yet been reported.

Methods

We systematically screened eight potentially functional single-neucleotide polymorphism (SNPs) in the genes near rs73329476 (carboxypeptidase M (CPM) and cleavage and polyadenylation specific factor 6 (CPSF6)) in a case–control study including 177 cases with silicosis and 204 healthy controls, matched to cases with years of silica dust exposure. We evaluated the associations between these eight SNPs and the development of silicosis. Luciferase reporter gene assays were performed to test the effects of selected SNP on the activity of CPM in the promoter. In addition, a two-stage case–control study was performed to investigate the expression differences of the two genes in peripheral blood leucocytes from a total of 64 cases with silicosis and 64 healthy controls with similar years of silica dust exposure as the cases.

Results

We found a strong association between the mutant rs12812500 G allele and the susceptibility of silicosis (OR=1.45, 95% CI 1.03 to 2.04, p=0.034), while luciferase reporter gene assays indicated that the mutant G allele of rs12812500 is strongly associated with increased luciferase levels compared with the wild-type C allele (p<0.01). Moreover, the mRNA (peripheral blood leucocytes) expression of the CPM gene was significantly higher in subjects with silicosis compared with healthy controls.

Conclusions

The rs12812500 variant of the CPM gene may increase silicosis susceptibility by affecting the expression of CPM, which may contribute to silicosis susceptibility with biological plausibility.