SETTING A global survey of National Tuberculosis Program (NTP) directors. OBJECTIVES To assess the perceived mental health needs of persons with tuberculosis (TB), current practices, and receptivity to integrating evidence-based mental and substance use treatment into national TB guidelines. DESIGN Semi-structured survey of NTP directors from 26 countries of all income levels using a standardized questionnaire. RESULTS Of the 26 countries, 21 were classified as high incidence and/or burden countries for TB, TB and human immunodeficiency virus coinfection, and/or drug-resistant TB. Two NTPs included routine screening for any mental disorder, four assessed alcohol or drug use, and five had standard protocols for the co-management of disorders. If effective and low-cost integrated care models were available, 17 NTP directors felt that it was highly likely, and five somewhat likely, that their NTPs would integrate mental health treatment into national TB guidelines and services. The main perceived barriers to service integration were limited capacity, not recognizing mental health as a problem, insufficient resources, and TB-related social stigma. CONCLUSIONS NTPs currently do not address mental disorders as part of routine practice. Nevertheless, receptivity is high, which creates a ripe opportunity to integrate the management of TB and mental disorders into the policies and guidelines of NTPs worldwide. .

Artificial intelligence (AI) has the potential to improve breast cancer screening; however, prospective evidence of the safe implementation of AI into real clinical practice is limited. A commercially available AI system was implemented as an additional reader to standard double reading to flag cases for further arbitration review among screened women. Performance was assessed prospectively in three phases: a single-center pilot rollout, a wider multicenter pilot rollout and a full live rollout. The results showed that, compared to double reading, implementing the AI-assisted additional-reader process could achieve 0.7-1.6 additional cancer detection per 1,000 cases, with 0.16-0.30% additional recalls, 0-0.23% unnecessary recalls and a 0.1-1.9% increase in positive predictive value (PPV) after 7-11% additional human reads of AI-flagged cases (equating to 4-6% additional overall reading workload). The majority of cancerous cases detected by the AI-assisted additional-reader process were invasive (83.3%) and small-sized (≤10 mm, 47.0%). This evaluation suggests that using AI as an additional reader can improve the early detection of breast cancer with relevant prognostic features, with minimal to no unnecessary recalls. Although the AI-assisted additional-reader workflow requires additional reads, the higher PPV suggests that it can increase screening effectiveness.