Search

Stages of tuberculosis disease can be delineated by radiology, microbiology, and symptoms, but transitions between these stages remain unclear. In a systematic review and meta-analysis of studies of individuals with untreated tuberculosis who underwent follow-up (34 cohorts from 24 studies, with a combined sample of 139 063), we aimed to quantify progression and regression across the tuberculosis disease spectrum by extracting summary estimates to align with disease transitions in a conceptual framework of the natural history of tuberculosis. Progression from microbiologically negative to positive disease (based on smear or culture tests) in participants with baseline radiographic evidence of tuberculosis occurred at an annualised rate of 10% (95% CI 6·2-13·3) in those with chest x-rays suggestive of active tuberculosis, and at a rate of 1% (0·3-1·8) in those with chest x-ray changes suggestive of inactive tuberculosis. Reversion from microbiologically positive to undetectable disease in prospective cohorts occurred at an annualised rate of 12% (6·8-18·0). A better understanding of the natural history of pulmonary tuberculosis, including the risk of progression in relation to radiological findings, could improve estimates of the global disease burden and inform the development of clinical guidelines and policies for treatment and prevention., Competing Interests: Declaration of interests We declare no competing interests., (Copyright © 2023 Elsevier Ltd. All rights reserved.)

Background: Healthcare-associated infections (HAIs) are the most frequent adverse events in healthcare and a global public health concern. Surveillance is the foundation for effective HAIs prevention and control. Manual surveillance is labor intensive, costly and lacks standardization. Artificial Intelligence (AI) and machine learning (ML) might support the development of HAI surveillance algorithms aimed at understanding HAIs risk factors, improve patient risk stratification, identification of transmission pathways, timely or real-time detection. Scant evidence is available on AI and ML implementation in the field of HAIs and no clear patterns emerges on its impact., Methods: We conducted a systematic review following the PRISMA guidelines to systematically retrieve, quantitatively pool and critically appraise the available evidence on the development, implementation, performance and impact of ML-based HAIs detection models., Results: Of 3445 identified citations, 27 studies were included in the review, the majority published in the US (n=15, 55.6%) and on surgical site infections (SSI, n=8, 29.6%). Only 1 randomized controlled trial was included. Within included studies, 17 (63%) ML approaches were classified as predictive and 10 (37%) as retrospective. Most of the studies compared ML algorithms' performance with non-ML logistic regression statistical algorithms, 18.5% compared different ML models' performance, 11.1% assessed ML algorithms' performance in comparison with clinical diagnosis scores, 11.1% with standard or automated surveillance models. Overall, there is moderate evidence that ML-based models perform equal or better as compared to non-ML approaches and that they reach relatively high-performance standards. However, heterogeneity amongst the studies is very high and did not dissipate significantly in subgroup analyses, by type of infection or type of outcome., Discussion: Available evidence mainly focuses on the development and testing of HAIs detection and prediction models, while their adoption and impact for research, healthcare quality improvement, or national surveillance purposes is still far from being explored., (Copyright © 2020 The Authors. Published by Elsevier Ltd.. All rights reserved.)