Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs.

Publication date: Jul 09, 2025

Traditional tuberculosis (TB) screening involves radiologists manually reviewing chest X-rays (CXR), which is time-consuming, error-prone, and limited by workforce shortages. Our AI model, AIRIS-TB (AI Radiology In Screening TB), aims to address these challenges by automating the reporting of all X-rays without any findings. AIRIS-TB was evaluated on over one million CXRs, achieving an AUC of 98. 51% and overall false negative rate (FNR) of 1. 57%, outperforming radiologists (1. 85%) while maintaining a 0% TB-FNR. By selectively deferring only cases with findings to radiologists, the model has the potential to automate up to 80% of routine CXR reporting. Subgroup analysis revealed insignificant performance disparities across age, sex, HIV status, and region of origin, with sputum tests for suspected TB showing a strong correlation with model predictions. This large-scale validation demonstrates AIRIS-TB’s safety and efficiency in high-volume TB screening programs, reducing radiologist workload without compromising diagnostic accuracy.

Open Access PDF

Concepts Keywords
Hiv Airis
Informatics Cross
Outperforming Cxr
Radiology Cxrs
Tb Findings
Fnr
Observational
Population
Radiologists
Rays
Reporting
Scale
Screening
Sectional
Tb

Semantics

Type Source Name
disease MESH tuberculosis
pathway KEGG Tuberculosis
disease MESH morbidity
drug DRUGBANK Coenzyme M
disease MESH pneumothorax
disease MESH scoliosis
disease MESH abnormalities
disease MESH fibrosis
disease MESH cardiomegaly
disease IDO process
disease IDO country
drug DRUGBANK Saquinavir
drug DRUGBANK Gold
drug DRUGBANK Methionine
drug DRUGBANK Trestolone
disease IDO site
disease MESH privacy
disease MESH pulmonary tuberculosis
disease MESH uncertainty
disease MESH Interstitial lung diseases
drug DRUGBANK Flunarizine
disease MESH pleural effusion
pathway REACTOME Reproduction

Original Article

(Visited 6 times, 1 visits today)

Leave a Comment

Your email address will not be published. Required fields are marked *