Difficulties in distinguishing silicosis and pulmonary tuberculosis in silica-exposed gold miners: A report of four cases.

Silicosis and tuberculosis (TB) are both global health concerns, with high prevalence among miners from the South African gold mines. Although knowledge has accumulated about these two conditions as distinct diseases since the early 20th century, and despite progress in technology with multiple diagnostic tools and treatment options available for TB, the challenge of distinguishing and therefore efficiently managing these two conditions in this population remains as current as it was 100 years ago. To illustrate the diagnostic and health service problems of distinguishing TB and silicosis clinically and radiologically in former gold miners from the South African mines living in resource-poor areas, we discuss four cases reviewed for this report by a panel of experts. For each case, occupational history, past and current medical history, physical examination, radiological and laboratory findings are described. Common themes are: (1) poor agreement between radiological and clinical presentation; (2) poor agreement between radiology findings and detection of active TB on sputum Xpert MTB/RIF testing; and (3) difficulty in distinguishing the clinical and radiological presentations of silicosis and tuberculosis. Possible consequences at the population level are undertreatment or overtreatment of TB, and underdiagnosis or overdiagnosis of silicosis. There is a need for training of practitioners who are screening or attending to former gold miners in the clinical and radiological features of combined disease, using a curated database of miners' chest X-ray images. Investment in protocols for management of both acute and chronic silicotuberculosis in ex-miners is needed, as is clinical, epidemiologic, and operations research.

Accuracy of Computer-Aided Detection of Occupational Lung Disease: Silicosis and Pulmonary Tuberculosis in Ex-Miners from the South African Gold Mines.

BACKGROUND: Computer-aided detection (CAD) of pulmonary tuberculosis (TB) and silicosis among ex-miners from the South African gold mines has the potential to ease the backlog of lung examinations in clinical screening and medical adjudication for miners' compensation. This study aimed to determine whether CAD systems developed to date primarily for TB were able to identify TB (without distinction between prior and active disease) and silicosis (or "other abnormality") in this population. METHODS: A total of 501 chest X-rays (CXRs) from a screening programme were submitted to two commercial CAD systems for detection of "any abnormality", TB (any) and silicosis. The outcomes were tested against the readings of occupational medicine specialists with experience in reading miners' CXRs. Accuracy of CAD against the readers was calculated as the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Sensitivity and specificity were derived using a threshold requiring at least 90% sensitivity. RESULTS: One system was able to detect silicosis and/or TB with high AUCs (>0.85) against both readers, and specificity > 70% in most of the comparisons. The other system was able to detect "any abnormality" and TB with high AUCs, but with specificity < 70%. CONCLUSION: CAD systems have the potential to come close to expert readers in the identification of TB and silicosis in this population. The findings underscore the need for CAD systems to be developed and validated in specific use-case settings.