Deep learning (DL) neural networks have only recently been employed to interpret chest radiography (CXR) to screen and triage people for pulmonary tuberculosis (TB). No published studies have compared multiple DL systems and populations. We conducted a retrospective evaluation of three DL systems (CAD4TB, Lunit INSIGHT, and qXR) for detecting TB-associated abnormalities in chest radiographs from outpatients in Nepal and Cameroon. All 1196 individuals received a Xpert MTB/RIF assay and a CXR read by two groups of radiologists and the DL systems. Xpert was used as the reference standard. The area under the curve of the three systems was similar: Lunit (0.94, 95% CI: 0.93–0.96), qXR (0.94, 95% CI: 0.92–0.97) and CAD4TB (0.92, 95% CI: 0.90–0.95). When matching the sensitivity of the radiologists, the specificities of the DL systems were significantly higher except for one. Using DL systems to read CXRs could reduce the number of Xpert MTB/RIF tests needed by 66% while maintaining sensitivity at 95% or better. Using a universal cutoff score resulted different performance in each site, highlighting the need to select scores based on the population screened. These DL systems should be considered by TB programs where human resources are constrained, and automated technology is available.

The Xpert MTB/RIF assay has garnered significant interest as a sensitive and rapid diagnostic tool to improve detection of sensitive and drug resistant tuberculosis. However, most existing literature has described the performance of MTB/RIF testing only in study conditions; little information is available on its use in routine case finding. TB REACH is a multi-country initiative focusing on innovative ways to improve case notification.

Globally, the incidence of tuberculosis (TB) is declining very slowly, and the noncommunicable disease (NCD) burden for many countries is steadily increasing. Several NCDs, such as diabetes mellitus, alcohol use disorders and smoking-related conditions, are responsible for a significant proportion of TB cases globally, and in the European region, represent a larger attributable fraction for TB disease than HIV. Concrete steps are needed to address NCDs and their risk factors. We reviewed published studies involving TB and NCDs, and present a review and discussion of how they are linked, the implications for case detection and management, and how prevention efforts may be strengthened by integration of services. These NCDs put patients at increased risk for developing TB and at risk for poor treatment outcomes. However, they also present an opportunity to provide better care through increased case-detection activities, improved clinical management and better access to care for both TB and NCDs. Hastening the global decline in TB incidence may be assisted by strengthening these types of activities.

With nearly one billion migrants worldwide, migration is both a dynamic and a divisive phenomenon facing the world today. Migrants are a heterogeneous group, and the conditions surrounding migration pathways often pose risks to the physical, mental and social well-being of migrants, with certain subgroups being more vulnerable than others. Several determinants of health and tuberculosis (TB) interplay to increase the vulnerability of migrants to tuberculous infection, TB disease and poor treatment outcomes, making them a key population for TB. This article is the first in the State-of-the-Art series of the International Journal of Tuberculosis and Lung Disease on TB and migration. It provides an overview of migration trends, migration pathways and social determinants, and impact on TB. This article outlines a framework for the prevention and reduction of the TB burden among migrants, adapted from the World Health Organization's End TB Strategy, and in accordance with the Stop TB Partnership's Global Plan and the Sustainable Development Goals (SDGs) agenda. The framework highlights the need for migrant-inclusive national TB plans, and calls for action across all three pillars of the End TB Strategy for migrant-sensitive care and prevention, bold intersectoral policies and systems supportive of migrants, and operational research. More research is needed on the TB burden and challenges faced by migrants and on the feasibility and effectiveness of approaches proposed here and the scaling up of models already underway. Political commitment at the highest national and international levels will be critical to intensify action for promoting the health of migrants on the road to achieving the end TB targets.