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

Abstract 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Prateek Munjal, Ahmed Al Mahrooqi, Ronnie Rajan, Andrew Jeremijenko, Iftikhar Ahmad, Muhammad Imran Akhtar, Marco A. F. Pimentel, Shadab Khan
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01832-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331558872252416
author Prateek Munjal
Ahmed Al Mahrooqi
Ronnie Rajan
Andrew Jeremijenko
Iftikhar Ahmad
Muhammad Imran Akhtar
Marco A. F. Pimentel
Shadab Khan
author_facet Prateek Munjal
Ahmed Al Mahrooqi
Ronnie Rajan
Andrew Jeremijenko
Iftikhar Ahmad
Muhammad Imran Akhtar
Marco A. F. Pimentel
Shadab Khan
author_sort Prateek Munjal
collection DOAJ
description Abstract 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.
format Article
id doaj-art-682fbeb040f34c97a109d60cd755a21b
institution Kabale University
issn 2398-6352
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-682fbeb040f34c97a109d60cd755a21b2025-08-20T03:46:29ZengNature Portfolionpj Digital Medicine2398-63522025-07-01811810.1038/s41746-025-01832-7Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRsPrateek Munjal0Ahmed Al Mahrooqi1Ronnie Rajan2Andrew Jeremijenko3Iftikhar Ahmad4Muhammad Imran Akhtar5Marco A. F. Pimentel6Shadab Khan7M42M42M42Capital Health Screening CentreCapital Health Screening CentreCapital Health Screening CentreM42M42Abstract 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.https://doi.org/10.1038/s41746-025-01832-7
spellingShingle Prateek Munjal
Ahmed Al Mahrooqi
Ronnie Rajan
Andrew Jeremijenko
Iftikhar Ahmad
Muhammad Imran Akhtar
Marco A. F. Pimentel
Shadab Khan
Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs
npj Digital Medicine
title Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs
title_full Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs
title_fullStr Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs
title_full_unstemmed Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs
title_short Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs
title_sort population scale cross sectional observational study for ai powered tb screening on one million cxrs
url https://doi.org/10.1038/s41746-025-01832-7
work_keys_str_mv AT prateekmunjal populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT ahmedalmahrooqi populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT ronnierajan populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT andrewjeremijenko populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT iftikharahmad populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT muhammadimranakhtar populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT marcoafpimentel populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs
AT shadabkhan populationscalecrosssectionalobservationalstudyforaipoweredtbscreeningononemillioncxrs