The co‑epidemic of silicosis and tuberculosis (TB) in South Africa's mining industry affects a large number of migrant workers and is compounded by limited access to chest X‑ray (CXR) screening. Although artificial intelligence (AI)‑based computer‑aided detection (CAD) systems for TB have demonstrated impressive accuracy against microbiological standards, validation among silica‑exposed populations has been limited. Moreover, well‑documented biases hinder CAD utility in diverse patient populations, potentially exacerbating existing healthcare inequities. In this article, we describe the challenges in developing CAD systems for TB and silicosis and present the potential benefits local public‑sector development initiatives can bring. Using a local dataset of 2000 CXRs from silica‑exposed Southern African mineworkers, alongside publicly available international datasets and pretrained CAD models, we present empirical evidence of CAD biases. Dimensionality reduction analysis produced visual mappings that demonstrate how local CXRs form a distinct cluster, separate from international images. We also found that, relative to TB, reducing image resolution disproportionately degraded silicosis detection. Further visualizations proved that accuracy metrics alone are insufficient measures of clinical reliability, possibly obscuring deployment failures. We conclude that local public‑sector CAD development offers a viable alternative to reliance on externally developed systems that likely exclude underserved populations. Addressing CAD deficiencies requires curating population‑representative datasets that capture local epidemiology and transparent, open‑source development practices that enable peer review and bias correction. Embedding technical and clinical expertise locally can transform AI‑based CAD from a potential instrument of digital colonialism into a mechanism that produces contextually appropriate diagnostics while advancing knowledge for equitable AI deployment worldwide.

Background: For much of the 20th century, the South African mining industry had a statutory compensation system for pneumoconiosis and tuberculosis characterized by gross racial inequality. This study examines the impact of inflation over the period 1973-2024 on the real value of miners' lung disease compensation, including the effect of the dropping of formal racial discrimination after 1993. Methods: Sources of information included legislation, government reports, notices, and Gazettes, and mining industry reports. Results: From 1973 to 1993, high rates of inflation hollowed out the value of compensation for all miners, greater in absolute terms for white miners. From 1994, inflation continued to erode both the real value of compensation payments, and, with the rise in earnings for all miners, the percentage of annual earnings covered by these payments. Until 2017 there were a few sporadic increases in statutory payment amounts, but a cap on "allowable earnings" used to calculate compensation severely limited any gain. Underlying factors include historic underfunding of the Compensation Fund via the statutory employer levy, administrative disarray in the state compensation agency, and unanticipated political, economic and epidemic disruptions. Recent years have seen a restoration of financial and administrative stability, with some degree of reversal of long-term trends. Conclusions: Although formal Apartheid racial discrimination ended in 1994, inflation, and until recently legislative stasis, continued to disadvantage all miners with compensatable occupational lung disease. The system is currently undergoing legislative reform-including proper funding of operations but also with limitation on civil liability against employers. The question therefore remains open as to whether a fair and equitable system of compensation for miners will be achieved and sustained.

Tuberculosis (TB) is a global problem affecting large numbers of workers exposed to respirable crystalline silica. Both silicosis and exposure to silica without silicosis increase the risk of active TB. While some studies have suggested that silicotuberculosis (silicosis plus TB) or silica exposure on its own are associated with unsuccessful TB treatment outcomes, the evidence is inconsistent. This systematic review and meta-analysis aimed to compare TB treatment outcomes in individuals with silicotuberculosis to those with TB alone, and similarly in those with TB plus silica exposure to those with TB alone. We conducted a systematic review of randomized and nonrandomized trials, and cohort and case-control studies published 1970–2024. Studies were sought which investigated TB treatment outcomes for silicotuberculosis or silica exposure alone via PubMed, Web of Science and Scopus. We conducted risk of bias assessments using ROBINS-E for observational studies of TB treatment (silicosis or silica as the “exposure”) and ROB 2 for randomized trials of different TB drug regimens. GRADE was used to assess overall certainty of evidence. Seven studies met the inclusion criteria, all restricted to comparing silicotuberculosis with TB alone or different drug regimens among those with silicotuberculosis. High/very high risk of bias or “some concerns” were noted in six – due to confounding, loss to follow-up, missing data, and/or concerns about exposure or outcome measurement. The pooled odds ratio (OR) for treatment failure/delayed conversion for individuals with silicotuberculosis versus those with TB alone was 1.79 (95

BACKGROUND:A causal association between occupational asbestos exposure and lung disease, including pneumoconiosis and mesothelioma, is well established. Elevated mortality among former asbestos miners is expected. However, large-scale South African studies examining all-cause mortality in this population are lacking. We assessed all-cause mortality among former asbestos miners recorded in the Asbestos and Kgalagadi Relief Trusts' Inyosi database. METHODS:All-cause standard mortality ratios (SMRs) and crude mortality rates (CMRs) were calculated for 11,343 ex-miners. Mortality predictors were modeled using Cox regression analysis, and mortality trends were assessed by examining annual all-cause CMRs and SMRs over the 20-year study period. RESULTS:The cohort's all-cause mortality exceeded that of the general population by 4% (SMR = 1.04; 95% CI: 1.01-1.07), with excess mortality confined to women (SMR = 1.17; 95% CI: 1.09-1.25). Increasing ILO radiographic profusion category strongly predicted mortality, with adjusted hazard ratios (aHRs) ranging from 1.13 (95% CI: 1.05-1.23) to 2.42 (95% CI: 1.58-3.71). Severely reduced lung function was also associated with increased risk, including forced expiratory volume in 1 s and forced vital capacity z-scores below -3.0 (aHR = 1.60; 95% CI: 1.41-1.81 and aHR = 1.26; 95% CI: 1.12-1.42, respectively). Additional predictors included body mass index less than 18.5 kg/m² (aHR = 1.46; 95% CI: 1.36-1.58) and previous smoking (aHR = 1.43; 95% CI: 1.35-1.53). SMRs declined over time. CONCLUSION:Radiological and spirometric indicators were key predictors of mortality. These findings support risk stratification and targeted interventions, particularly early management of respiratory complications and smoking cessation, to reduce mortality. The excess female mortality highlights the occupational hazards of aboveground asbestos activities, gender‑specific work practices, and insufficient control measures in this setting. Although standardized mortality was only modestly elevated, interpretation was limited by incomplete data.

Extractive operations are expanding in low- and middle-income countries (LMICs), resulting in a growing burden of silicosis. Given the need to promote knowledge and awareness of this disease, we are concerned by uncritical use of data reported by the Global Burden of Disease (GBD) project. We find that the outputs of the GBD for silicosis in LMICs conflict with recent available empirical data, including our research experience in mining cohorts, suggesting substantial underestimation in these countries. We attribute this, inter alia, to generic utilization of country vital statistics and misalignment of the models with industrial and occupational predictors of silicosis. Scarcity of data for model inputs and empirical silicosis estimates remains a serious barrier to accurate modelling. However, over-reliance on complex modelling tools can produce unintended consequences for public health policy and discourse. Collaborative global and country surveillance of silicosis is needed, aided by the expansion of newly available low-cost screening technology.

Silica exposure and silicosis are strongly associated with pulmonary tuberculosis (TB), with ex-miners from the South African gold mines carrying a large burden of both diseases. We present a case of lymph node silicosis and recurrent TB complicated by cavitation with aspergilloma requiring right upper lobectomy, in a 38-year-old ex-goldminer with only 19 months of silica exposure. While silicosis was detected histologically in the lymph nodes, radiological findings and histopathological lung parenchyma lesions were consistent with inactive TB. A worker’s compensation claim for silicotuberculosis was unsuccessful. The findings highlight the need to take into account the contribution of subradiological silicosis and/or a low silica exposure threshold to increased TB risk, and the persistence of such TB risk following exit from exposure. The case also demonstrates the need to differentiate between the radiological and pathological features of silicosis and TB, and the possible mechanistic role of lymph node silicosis in increasing TB risk. These considerations have relevance to the surveillance of silica-exposed workers in high TB settings and the potential to reduce TB risk through silica dust control.

BACKGROUND:Computer-aided detection (CAD) is emerging as an adjunct to the use of the chest X-ray (CXR) in screening for pulmonary tuberculosis (TB). CAD for silicosis, a fibrotic lung disease due to silica dust and a strong risk factor for TB, is at an earlier stage of development and, unlike TB, depends on expert human reading for validation. For all CAD systems, an important step is the choice of threshold for classifying images as positive or negative for the disease in question. The objective of this article is to present an analytic approach to the choice of threshold in using CAD systems for silicosis. METHODS:Drawing on receiver operating curve data from a published study on agreement between CAD and two expert readings of silicosis, two criteria for choosing the sensitivity/specificity combination were compared-the Youden Index and a minimum sensitivity of 90%. We explore the impact of criterion selection, silicosis definition, and reader on the choice and interpretation of threshold, as well as the influence of positive predictive value (PPV) derived from screen prevalence. We present a novel technique for using two CAD thresholds to distinguish images with a high likelihood of being of positive or negative from those characterized by uncertainty. RESULTS:The sample was 501 CXR images from ex-gold miners. Derived thresholds varied across the two criteria, as well as across silicosis definition and expert reader. Varying the notional disease prevalence produced large differences in PPV and, therefore, proportions of false positives. The implications of these variations affecting threshold choice are described for three use cases-annual screening of active miners, outreach screening of former miners, and adjudication of claims for silicosis compensation. CONCLUSION:In applying CAD to silicosis, users need to establish the use case, their preference for the sensitivity/specificity trade-off, and the silicosis definition, as well as considering the effect of disease prevalence. System developers need to take inter-reader variation in validation exercises into account and present this information transparently. A two-threshold model has potential utility in situations of high screening volume where there is a significant cost associated with referral for confirmation of diagnosis.

Background: From early in its history, gold mining in South Africa involved recruiting hundreds of thousands of workers from Malawi and other neighbouring countries to work in an environment conducive to high rates of tuberculosis and silicosis. Official recruitment from Malawi ended in the 1990s, depriving large numbers of these migrant miners of their livelihood, with limited or no access to employment-linked social benefits and services. Objectives: To describe barriers faced by Malawian migrant ex-gold miners in accessing social benefits related to occupational lung disease and related health services and medical examinations, and to identify needed actions. Methods: This study, conducted in the Blantyre region of Malawi, draws from field observations and interviews with 14 ex-gold miners who had worked on South African gold mines, supplemented by five key informant interviews. Data were analysed using a phenomenological and thematic analysis approach. Findings: Ex-migrant miners described precarious livelihoods and difficulty accessing employment-linked benefit examinations and health services. They are largely uncertain about their entitlements related to their past work in South Africa and the means for pursuing such rights. The division of responsibility within South Africa and between the governments of South Africa and Malawi has resulted in confusion and misinformation. Within Malawi, scarcity of funding, administrative hurdles and limited occupational lung disease expertise are barriers to expanding current services for ex-migrant miners as well as ex-miners from Malawian mines. Conclusions: A number of actions are needed: coordination between the Malawian government and South African agencies; integration of occupational health services, including for migrant ex-gold miners, into Malawi's public health system; education of ex-gold miners and their dependents about their rights and related processes and the provision of relief aid through local and external support. Financial involvement of the South African mining industry that profited from the services of migrant miners is required to alleviate the burden on publicly funded health systems.

An estimated 49·5 million small-scale miners worldwide are exposed to high concentrations of silica during their work. The substantial morbidity and mortality of silicosis and tuberculosis among workers exposed to such intensities have been documented. This Viewpoint raises concern at the failure to respond to a growing epidemic of lung disease (predominantly silicosis and tuberculosis) among small-scale miners. The Viewpoint is framed around four arguments: outlining the huge burden of lung disease among SSMs; critically examining these figures in the context of high silica exposures; illustrating the failure to support research; and examining historical, socioeconomic, and political factors influencing the epidemic. We then outline a strategy for response. An urgent and coordinated response is needed to address the devastating health effects of silicosis and tuberculosis in small-scale miners and their preventable workplace causes.

There are many examples of poor TB infection prevention and control (IPC) implementation in the academic literature, describing a high-risk environment for nosocomial spread of airborne diseases to patients and health workers. We developed a positive deviant organisational case study drawing on Weick’s theory of organisational sensemaking. We focused on a district hospital in the rural Eastern Cape, South Africa and used four primary care clinics as comparator sites. We interviewed 18 health workers to understand TB IPC implementation over time. We included follow-up interviews on interactions between TB and COVID-19 IPC. We found that TB IPC implementation at the district hospital was strengthened by continually adapting strategies based on synergistic interventions (e.g. TB triage and staff health services), changes in what value health workers attached to TB IPC and establishing organisational TB IPC norms. The COVID-19 pandemic severely tested organisational resilience and COVID-19 IPC measures competed instead of acted synergistically with TB. Yet there is the opportunity for applying COVID-19 IPC organisational narratives to TB IPC to support its use. Based on this positive deviant case we recommend viewing TB IPC implementation as a social process where health workers contribute to how evidence is interpreted and applied.

BACKGROUND:The World Health Organization recommends systematic chest X-ray (CXR) screening for tuberculosis (TB) in silica-exposed workers. However, evidence on the accuracy of CXR screening in such populations is lacking. AIMS:To measure the accuracy of CXR screening for active TB in silica-exposed miners, in a population with a high prevalence of silicosis, post-TB lung disease and HIV. METHODS:A secondary analysis of data from a miner screening programme in Lesotho was undertaken. We measured the performance of CXR (in participants with and without cough) for 'abnormalities suggestive of TB' against Xpert MTB/RIF (Xpert). The sample size was 2572 and positive Xpert prevalence was 3%. RESULTS:CXR alone had high sensitivity (0.93, 95% confidence interval [CI] 0.87-0.99), but low specificity (0.41, 95% CI 0.39-0.42). Requiring cough and a positive CXR increased specificity (0.79, 95% CI 0.77-0.81), resulting in reduced sensitivity (0.41, 95% CI 0.30-0.52). There was no difference in CXR accuracy by HIV status. However, specificity was markedly reduced in the presence of silicosis (from 0.70, 95% CI 0.68-0.72, to 0.03, 95% CI 0.02-0.04) or past TB history (from 0.59, 95% CI 0.56-0.62 to 0.27, 95% CI 0.25-0.29). Throughout, positive predictive value remained very low (5%) and negative predictive value very high (99%). CONCLUSIONS:CXR screening accurately identifies TB-negative CXRs in this population, but post-TB lung disease and silicosis would result in a high proportion of Xpert-negative referrals and an increased risk of unneeded empirical treatment. Adapted screening algorithms, practitioner training and digital access to previous mining CXRs are needed.

BACKGROUND:Tuberculosis (TB) is a stigmatised disease with intersectional associations with poverty, HIV, transmission risk and mortality. The use of visible TB infection prevention and control (IPC) measures, such as masks or isolation, can contribute to stigma. METHODS:To explore stigma in this condition, we conducted in-depth individual interviews with 18 health workers and 15 patients in the rural Eastern Cape of South Africa using a semi-structured interview guide and narrative approach. We used reflexive thematic analysis guided by line-by-line coding. We then interpreted these key findings using Link and Phelan's theoretical model of stigma, related this to stigma mitigation recommendations from participants and identified levels of intervention with the Health Stigma and Discrimination Framework. RESULTS:Participants shared narratives of how TB IPC measures can contribute to stigma, with some describing feeling 'less than human'. We found TB IPC measures sometimes exacerbated stigma, for example through introducing physical isolation that became prolonged or through a mask marking the person out as being ill with TB. In this context, stigma emerged from the narrow definition of what mask-wearing symbolises, in contrast with broader uses of masks as a preventative measure. Patient and health workers had contrasting perspectives on the implications of TB IPC-related stigma, with patients focussing on communal benefit, while health workers focussed on the negative impact on the health worker-patient relationship. Participant recommendations to mitigate TB IPC-related stigma included comprehensive information on TB IPC measures, respectful communication between health workers and patients, shifting the focus of TB IPC messages to communal safety (which could draw on ubuntu, a humanist framework) and using universal IPC precautions instead of measures targeted at someone with infectious TB. CONCLUSIONS:Health facilities may unwittingly perpetuate stigma through TB IPC implementation, but they also have the potential to reduce it. Evoking 'ubuntu' as an African humanist conceptual framework could provide a novel perspective to guide future TB IPC stigma mitigation interventions, including policy changes to universal IPC precautions.

Silicotuberculosis, the combination of silicosis and pulmonary tuberculosis (TB), remains a substantial clinical and public health problem in high TB burden countries with silica-exposed workforces. The objectives of this narrative review are to propose a definition of silicotuberculosis which includes post-tuberculous lung disease, to emphasise the importance of understanding how the two diseases modify each other, and to identify as yet unanswered questions relevant to clinical practice and disease control and mitigation. The unique aetiological relationship between silica exposure and TB is now firmly established, as is the accelerated impairment and mortality imposed by TB on individuals with silicosis. However, the rich clinical, pathology and laboratory literature on combined disease from the pre-TB treatment era appears to have been largely forgotten. The close clinical and pathological appearance of the two diseases continues to pose a challenge to imaging, diagnosis and pathological description, while inconsistent evidence regarding TB treatment and TB preventive treatment prevails. Many other topics raise questions to be answered, inter alia: the range of phenotypes of combined disease; the rates and determinants of disease progression; the role of computed tomography in identifying and characterising combined disease; appropriate screening practice; acceptable policies of management of workers that combine risk reduction with social security; and the workplace respirable silica concentration that protects against the excess TB attributable to inhaled silica.

Abstract Introduction In Southern Africa, a powerful legacy of social injustice has been the prevalence of occupational lung disease, particularly silicosis and tuberculosis (TB) in those who worked in South Africa’s gold mines. Although Artificial Intelligence (AI) is being increasingly applied for healthcare purposes, distrust about introducing “disruptive” technologies persists. Intrinsic and contextual factors also influence where and how such innovations are initiated. These require careful scrutiny to ensure that health equity is promoted. Methods We describe and appraise an AI application currently being developed, specifically the use of computer assisted detection (CAD) for TB and/or silicosis on chest x-rays, to support more efficient and equitable adjudication of compensation claims from former miners in southern Africa. Using a bio-ethical lens that considers the principles of beneficence, non-maleficence, autonomy and justice and adds explicability as a core principle, this study focuses on the apprehensions of users and stakeholders. Results Issues of concern include funding a sustainable health service delivery model in which CAD can be incorporated, CAD accuracy, possible biases in training of CAD systems, data privacy, impact on human skill development, transparency and accountability in CAD use, as well as intellectual property ownership. Discussion This paper discusses ways in which each of these potential obstacles to successful use of CAD could be mitigated. Conclusion From the outset, efforts to overcome technical implementation challenges must be considered to ensure ethical use. It is timely to take stock of barriers that might undermine the advancement of AI innovation on behalf of those who have been socially marginalized.

Objectives: Between the 1980s and 2000s, an epidemic of silicosis was identified in migrant black gold miners, many from neighbouring countries, who had worked in the South African gold mines. This study uses the newly available employment database of a large gold mining company to demonstrate how a sustained rise in employment duration in a new cohort of black migrant workers resulted from changes in recruitment policy, and it examines the implications for current surveillance and redress. Methods: Contract data of 300,774 workers from the employment database of a multi-mine gold mining company were analysed for 1973-2018. Piecewise linear regression was applied to determine trends in cumulative employment, including South African versus cross-border miners. The proportions with cumulative employment of at least 10, 15, or 20 years, typical thresholds for chronic silicosis, were also calculated. Results: Five calendar phases were identified between 1973 and 2018. During the second phase, 1985-2013, mean cumulative duration of employment rose fivefold, from 4 to 20 years. Cumulative employment continued to rise, although more slowly, before peaking in 2014 at 23.5 years and falling thereafter to 20.1 years in 2018. Over most of the 1973- 2018 period, miners from neighbouring countries had greater cumulative employment than South African miners. Overall, the proportion of miners exiting with at least 15 years of cumulative employment rose from 5% in 1988 to 75% in 2018. This report identifies a number of fundamental changes in labour recruitment policy in the gold mining industry in the 1970s which provide an explanation for the subsequent rise in cumulative exposure and associated silicosis risk. Conclusions: These new data support the hypothesis of a silicosis epidemic driven by increasing cumulative silica dust exposure in a new cohort of circular migrant workers from the 1970s. They inform current programmes to improve surveillance of this neglected population for silicosis and related disease and to provide medical examinations and compensation to a large number of former gold mines. The analysis highlights the lack of information on cumulative employment and silicosis risk among migrant miners in previous decades. The findings have global relevance to the plight of such migrant workers in hazardous occupations.

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.

factors for SARS-CoV-2 infection among HCWs as well as evaluate the effectiveness of SARS-CoV-2 infection prevention and control measures. It also includes a cross-sectional study in Gauteng to explore mental health of HCWs during the pandemic and identify areas for intervention; a quasi-experimental study of the role of information systems in strengthening occupational health services for healthcare workers; and global policy analyses including an analysis of a global survey of HCWs from 161 countries.

In the wake of a large burden of silicosis and tuberculosis among ex-miners from the South African gold mining industry, several programmes have been engaged in examining and compensating those at risk of these diseases. Availability of a database from one such programme, the Q(h)ubeka Trust, provided an opportunity to examine the accuracy of length of service in predicting compensable silicosis, and the concordance between self-reported employment and that officially recorded. Compensable silicosis was determined by expert panels, with ILO profusion ≥1/0 as the threshold for compensability. Age, officially recorded and self-reported years of service, and years since first and last service of 3146 claimants for compensable silicosis were analysed. Self-reported and recorded service were moderately correlated (R = 0.66, 95% confidence interval 0.64–0.68), with a Bland–Altman plot showing no systematic bias. There was reasonably high agreement with 75% of the differences being less than two years. Logistic regression and receiver operating characteristic curve analysis were used to test prediction of compensable silicosis. There was little predictive difference between length of service on its own and a model adjusting for length of service, age, and years since last exposure. Predictive accuracy was moderate, with significant potential misclassification. Twenty percent of claimants with compensable silicosis had a length of service <10 years; in almost all these claims, the interval between last exposure and the claim was 10 years or more. In conclusion, self-reported service length in the absence of an official service record could be accepted in claims with compatible clinical findings. Length of service offers, at best, moderate predictive capability for silicosis. Relatively short service compensable silicosis, when combined with at least 10 years since last exposure, was not uncommon.