ArticleFrontiers in public health2025
Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations.
Article in Frontiers in public health, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
2 citing papers in PubMed.
- Diagnostic accuracy of AI-assisted chest radiographs in tuberculosis screening: A Ghanaian clinical study.PloS one · 2026Article
- Interdisciplinary insights into public health challenges: A synthesis of research presented at the 2025 African Voices for Research Virtual Conference.Journal of public health in Africa · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
17 authors.
Funding
Abstract
Introduction: Despite advances in diagnostic technologies for tuberculosis (TB), global control of this disease requires improved technologies for active case finding in selected vulnerable populations. The integration of artificial intelligence (AI) into imaging modalities has been anticipated to assume a pivotal position in conjunction with traditional bacteriological diagnostic approaches, especially in the active diagnosis of vulnerable groups. Methods: The study was conducted as a prospective investigation spanning from November 2019 to October 2023, in Romania's national TB screening project. From total of 92,368 tested participants, 404 patients were included in the study, with 202 individuals diagnosed with TB and 202 individuals serving as controls. The initial interpretation of radiological images was performed by AI X-Vision software and patients with suspicious findings were confirmed to have TB using GeneXpert testing. The objective of this study is to discover a threshold at which the AI score can accurately assess the risk of TB, regardless of the patient's medical background. Results: The study involved a number of 404 people, among whom 202 were diagnosed with TB out of a total of 92,368 participants, and the remaining 202 patients represent the control group. The current study highlighted, at an AI threshold value of 0.4, that 89% of the screened people benefited from a correct assessment using the AI associated with the radiological examination. ROC curve analysis indicates an AUC of 0.923 (95% CI:0.893-0.947; significance level Conclusion: Our study brings to the fore the significance of integrating AI software X-vision with bacteriological diagnosis in detecting TB among vulnerable groups in Romania. This underscores the imperative at the global level to develop solutions in the prompt diagnosis of TB, particularly within vulnerable groups.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.