Pneumoconioses Radiographs in a Large Population of U.S. Coal Workers: Variability in A Reader and B Reader Classifications by Using the International Labour Office Classification

Deep Learning Models of Multi-Scale Lesion Perception Attention Networks for Diagnosis and Staging of Pneumoconiosis: A Comparative Study with Radiologists

Accurate prediction of pneumoconiosis is essential for individualized early prevention and treatment. However, the different manifestations and high heterogeneity among radiologists make it difficult to diagnose and stage pneumoconiosis accurately. Here, based on DR images collected from two centers, a novel deep learning model, namely Multi-scale Lesion-aware Attention Networks (MLANet), is proposed for diagnosis of pneumoconiosis, staging of pneumoconiosis, and screening of stage I pneumoconiosis. A series of indicators including area under the receiver operating characteristic curve, accuracy, recall, precision, and F1 score were used to comprehensively evaluate the performance of the model. The results show that the MLANet model can effectively improve the consistency and efficiency of pneumoconiosis diagnosis. The accuracy of the MLANet model for pneumoconiosis diagnosis on the internal test set, external validation set, and prospective test set reached 97.87%, 98.03%, and 95.40%, respectively, which was close to the level of qualified radiologists. Moreover, the model can effectively screen stage I pneumoconiosis with an accuracy of 97.16%, a recall of 98.25, a precision of 93.42%, and an F1 score of 95.59%, respectively. The built model performs better than the other four classification models. It is expected to be applied in clinical work to realize the automated diagnosis of pneumoconiosis digital chest radiographs, which is of great significance for individualized early prevention and treatment.

Artificial Intelligence in Quantitative Chest Imaging Analysis for Occupational Lung Disease

Occupational lung disease manifests complex radiologic findings which have long been a challenge for computer-assisted diagnosis (CAD). This journey started in the 1970s when texture analysis was developed and applied to diffuse lung disease. Pneumoconiosis appears on radiography as a combination of small opacities, large opacities, and pleural shadows. The International Labor Organization International Classification of Radiograph of Pneumoconioses has been the main tool used to describe pneumoconioses and is an ideal system that can be adapted for CAD using artificial intelligence (AI). AI includes machine learning which utilizes deep learning or an artificial neural network. This in turn includes a convolutional neural network. The tasks of CAD are systematically described as classification, detection, and segmentation of the target lesions. Alex-net, VGG16, and U-Net are among the most common algorithms used in the development of systems for the diagnosis of diffuse lung disease, including occupational lung disease. We describe the long journey in the pursuit of CAD of pneumoconioses including our recent proposal of a new expert system.

Inter-observer agreement and accuracy in classifying radiographs for pneumoconiosis among Asian physicians taking AIR Pneumo certification examination

This study examined inter-observer agreement and diagnostic accuracy in classifying radiographs for pneumoconiosis among Asian physicians taking the AIR Pneumo examination. We compared agreement and diagnostic accuracy for parenchymal and pleural lesions across residing countries, specialty training, and work experience using data on 93 physicians. Physicians demonstrated fair to good agreement with kappa values 0.30 (95% CI: 0.20-0.40), 0.29 (95% CI: 0.23-0.36), 0.59 (95% CI: 0.52-0.67), and 0.65 (95% CI: 0.55-0.74) in classifying pleural plaques, small opacity shapes, small opacity profusion, and large opacities, respectively. Kappa values among Asian countries ranging from 0.25 to 0.55 (pleural plaques), 0.47 to 0.73 (small opacity profusion), and 0.55 to 0.69 (large opacity size). The median Youden's J index (interquartile range) for classifying pleural plaque, small opacity, and large opacity was 61.1 (25.5), 76.8 (29.3), and 88.9 (23.3), respectively. Radiologists and recent graduates showed superior performance than other groups regarding agreement and accuracy in classifying all types of lesions. In conclusion, Asian physicians taking the AIR Pneumo examination were better at classifying parenchymal lesions than pleural plaques using the ILO classification. The degree of agreement and accuracy was different among countries and was associated with background specialty training.

Pitfalls of using the ILO classification for silicosis compensation claims

BACKGROUND

The International Labour Organization (ILO) Classification of Radiographs of Pneumoconioses is used as the primary tool to determine compensation for pneumoconiosis in Turkey.

AIMS

We aimed to evaluate how the ILO classification applied, but obtaining chest radiographs in the workplace for screening until the completion of compensation claim files by the referral centres, based on the ILO reading.

METHODS

The study included 320 digital chest radiographs previously taken for screening from eight different ceramic factories and having finalised claim files by referral centres. We used an expert reference panel consisting of five ILO readers to re-evaluate all the radiographs independently using ILO standard films and reached a conclusion based on the agreement among at least three readers. The evaluation primarily included technical quality and silicosis diagnosis with an ILO 1/0 or above small profusion. The results were compared with previous findings.

RESULTS

Sixty-three (20%) chest radiographs were unacceptable for classification purposes according to the ILO technical quality grades. Among the remaining 257 chest radiographs, we diagnosed 103 with silicosis (40%), while the referral centres diagnosed 182 (71%). A discrepancy was found between our results and previous evaluations. We diagnosed silicosis in 50% and 17% of the previous silicosis and normal evaluations, respectively.

CONCLUSIONS

Our findings suggest that the use of the ILO classification for compensation claims may be problematic due to the way of its implementation in Turkey in addition to its subjectivity.

Association Between Financial Conflicts of Interest and ILO Classifications for Black Lung Disease

RATIONALE

The US Department of Labor administers the Federal Black Lung Program (FBLP), an administrative system charged with managing claims by coal miners for workers' compensation for totally disabling coal mine dust lung disease. Specific case reports have raised concern that financial conflicts of interest (COI) may systematically bias physicians when they are classifying chest x-rays (CXRs) for the absence, presence and severity of pneumoconiosis.

OBJECTIVE

To evaluate the direction and magnitude of association between financial COI of physicians participating in the FBLP and international standards for the classification of radiographs of pneumoconiosis.

METHODS

An epidemiologic assessment of black lung claims filed to the FBLP, 2000-2013, was conducted to determine physician classifications of radiographs. FBLP court decisions for years 2002-2019 (n=7,656) were used to evaluate financial COI of each physician. The main outcome measures used were classifications of radiographs for the absence of pneumoconiosis (small opacity classifications of 0/0 or 0/1), simple pneumoconiosis (small opacity classifications of 1/0 through 3/+) and Progressive Massive Fibrosis (PMF; large opacities with classifications of A, B or C).

RESULTS

Out of 63,780 radiograph classifications made by 264 physicians, 31.4% were read positive for simple pneumoconiosis and 3.6% were read as having progressive massive fibrosis (PMF). There were 52 physicians who classified CXRs as having no evidence of pneumoconiosis in 99%+ of their readings, and 18 physicians who classified CXRs as positive for simple pneumoconiosis in 99%+ of their readings. The adjusted odds of a negative classification of pneumoconiosis was 1.46 (CI95%: 1.44, 1.47) per 10% increase in the proportion of court records demonstrating that a physician was hired by the employer. Per 10% increase in court records indicating a physician was hired by the miner-claimant, the adjusted odds ratio for classifying simple pneumoconiosis was 1.51 (CI95%: 1.49, 1.52) and for finding PMF was 1.28 (CI95%: 1.26, 1.30).

CONCLUSIONS

There was a strong association between source of payment and radiograph classification suggesting the importance of eliminating financial COI in what should be an objective determination of eligibility for Black Lung workers' compensation benefits.

Coal Workers' Pneumoconiosis and Other Mining-Related Lung Disease: New Manifestations of Illness in an Age-Old Occupation

Coal workers' pneumoconiosis (CWP) and other mining-related lung diseases are entirely preventable, yet continue to occur. While greater attention has been given to CWP and silicosis, mining exposures cause a broad spectrum of respiratory disease, including chronic bronchitis, emphysema, and pulmonary fibrosis. Physicians must obtain a detailed occupational and exposure history from miners in order to make an accurate diagnosis and determine the risk of disease progression. Mining-related lung diseases are incurable and difficult to treat. Therefore, primary prevention by limiting dust exposure and secondary prevention through chest imaging and physiologic screening should be the primary focus of disease control.

Respiratory surveillance for coal mine dust and artificial stone exposed workers in Australia and New Zealand: A position statement from the Thoracic Society of Australia and New Zealand

Coal mine lung dust disease (CMDLD) and artificial stone (AS) silicosis are preventable diseases which have occurred in serious outbreaks in Australia recently. This has prompted a TSANZ review of Australia's approach to respiratory periodic health surveillance. While regulating respirable dust exposure remains the foundation of primary and secondary prevention, identification of workers with early disease assists with control of further exposure, and with the aims of preserving lung function and decreasing respiratory morbidity in those affected. Prompt detection of an abnormality also allows for ongoing respiratory specialist clinical management. This review outlines a medical framework for improvements in respiratory surveillance to detect CMDLD and AS silicosis in Australia. This includes appropriate referral, improved data collection and interpretation, enhanced surveillance, the establishment of a nationwide Occupational Lung Disease Registry and an independent advisory group. These measures are designed to improve health outcomes for workers in the coal mining, AS and other dust-exposed and mining industries.

Pneumoconiosis progression patterns in US coal miner participants of a job transfer programme designed to prevent progression of disease

OBJECTIVES

Pneumoconiosis prevalence and severity among US coal miners has been increasing for the past 20 years. An examination of the current approaches to primary and secondary prevention efforts is warranted. One method of secondary prevention is the Mine Safety and Health Administration-administered part 90 option programme where US coal miners with radiographic evidence of pneumoconiosis can exercise their right to be placed in a less dusty area of the mine. This study focuses on characterising the progression of disease among US coal miners who participated in the National Institute for Occupational Safety and Health-administered Coal Workers' Health Surveillance Programme (CWHSP) and exercised their part 90 job transfer option.

METHODS

Chest radiograph classifications of working underground coal miners who exercised their part 90 job transfer option during 1 January 1986 to 21 November 2016 and participated in the CWHSP during 1 January 1981 to 19 March 2019 were analysed.

RESULTS

513 miners exercised their part 90 option and participated in the CWHSP at least once during this time period. Of the 149 miners with ≥2 radiographs available, 48 (32%) showed progression after exercising part 90 and had more severe disease prior to exercising, compared with miners who did not progress (severity score of 2.8 vs 1.7, p=0.0002).

CONCLUSION

The part 90 job transfer option programme is not routinely used as intended to prevent progression of pneumoconiosis among US coal miners. The one-third of miners who participated in part 90 and continued to progress, exercised their part 90 option at a later stage of disease compared with non-progressors.

The National Institute for Occupational Safety and Health B Reader Certification Program-An Update Report (1987 to 2018) and Future Directions

OBJECTIVE

The National Institute for Occupational Safety and Health (NIOSH) B Reader Program provides the opportunity for physicians to demonstrate proficiency in the International Labour Office (ILO) system for classifying radiographs of pneumoconioses. We summarize trends in participation and examinee attributes and performance during 1987 to 2018.

METHODS

Since 1987, NIOSH has maintained details of examinees and examinations. Attributes of examinees and their examination performance were summarized. Simple linear regression was used in trend analysis of passing rates over time.

RESULTS

The mean passing rate for certification and recertification for the study period was 40.4% and 82.6%, respectively. Since the mid-1990s, the number of B Readers has declined and the mean age and years certified have increased.

CONCLUSIONS

To address the declining B Reader population, NIOSH is currently taking steps to modernize the program and offer more opportunities for training and testing.

Current Review of Pneumoconiosis Among US Coal Miners

PURPOSE OF REVIEW

This review summarizes recent research on pneumoconiosis in coal workers following the identification of the resurgence of this disease among US coal miners in the early 2000s. We describe the impact of this research and how this has led to increased public attention, benefitting affected miners.

RECENT FINDINGS

The latest research shows that the prevalence of pneumoconiosis, including progressive massive fibrosis, continues to increase, especially in central Appalachia. Contributing factors may include mining of thin coal seams or cutting rock to access coal, which may expose miners to coal mine dust with a higher content of silica and silicates than in the past. The impact of recently implemented changes, such as the reduced occupational exposure limit for respirable coal mine dust and the introduction of continuous personal dust monitors, will likely take years to appropriately evaluate.

Radiographic features of importance in the National Institute for Occupational Safety and Health-administered Coal Workers' Health Surveillance Program: characterising the use of the 'other symbols'

OBJECTIVE

The National Institute for Occupation Safety and Health-administered Coal Workers' Health Surveillance Program (CWHSP) provides radiographic pneumoconiosis screening for US coal miners. Radiographs are classified by readers according to International Labour Office criteria. In addition to pneumoconiotic parenchymal and pleural lung abnormalities, readers document radiographic features of importance (other symbols). Other symbols are not meant to imply a diagnosis or interpretation but are relevant as they provide information beyond a pneumoconiosis classification for features related to dust exposure and other aetiologies. Our objective was to summarise other symbol data from 48 years of CWHSP participants.

METHODS

Chest radiograph classifications obtained from CWHSP participants between July 1968 and July 2016 were analysed. Any 'other symbol' indication from any of the readings were counted. Frequencies were tabulated by individual reader and those identified by any reader.

RESULTS

Of the 469 922 radiographs included in this study, nearly 15% had at least one reader identify a radiographic feature of importance. The most commonly identified other symbol was cancer (excluding mesothelioma) (6.83%), followed by emphysema (1.68%). Some features were rarely identified over the 48 years of data collection such as rheumatoid pneumoconiosis (n=46), pneumothorax (n=32), mesothelioma (n=12) and rounded atelectasis (n=4).

CONCLUSIONS

This is the largest study to date describing radiographic features of importance as part of routine chest radiographic surveillance. While these symbols are not diagnostic they can be used to describe features associated with dust exposure. One of the most commonly identified radiographic features in our population is emphysema which is associated with respirable dust exposure. These results can be compared with other dust exposed populations.