Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 12, 2026Insights into ImagingOpen Access

Development of an expert-annotated chest X-ray dataset to support AI validation in tuberculosis diagnosis

View Full Paper
Ask AI
Bookmark
Share

Authors

WTWiwatana TanomkiatSTShiva Raj TimsinaTIThammasin Ingviya

Discussion

Loading...

Member takes

Overview

Randomized trial assesses diagnostic performance in tuberculosis, highlighting AI model validation potential.

Key Points

  • The aim is to evaluate inter-rater agreement and diagnostic performance of certified B readers in diagnosing tuberculosis from chest X-rays.
  • Analyzed 1097 chest X-rays from five institutions by six certified B readers.
  • Classified chest X-rays as unremarkable or abnormal, with a focus on tuberculosis-related abnormalities.
  • Used microbiological references for diagnosis and assessed inter-rater agreement using Fleiss’ kappa.
  • 69% of chest X-rays were abnormal and 31% were unremarkable.
  • 87% of abnormal chest X-rays were confirmed as tuberculosis by microbiological tests.
  • Sensitivity for tuberculosis findings ranged from 77.2% to 91.1%, with accuracy between 84.1% to 90.1%.

Cite This Study

Tanomkiat et al. (2026) studied this question.

synapsesocial.com/papers/6a5331ce4f7abc118adedb35https://doi.org/10.1186/s13244-026-02334-0
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Prospective Multi-Site Validation of AI to Detect Tuberculosis and Chest X-Ray Abnormalities2024 · 19 citations
  2. 2Diagnostic accuracy of AI-assisted chest radiographs in tuberculosis screening: A Ghanaian clinical study2026 · 3 citations
  3. 3Diagnostic Accuracy of Artificial Intelligence-assisted Chest X-ray Interpretation Tools for Screening of Tuberculosis: A Systematic Review and Meta-analysis2025 · 1 citations
  4. 4Validating the effectiveness of an AI algorithm for pulmonary tuberculosis screening using chest X-ray: Retrospective study and test accuracy with localizer images of the chest CT2026
  5. 5Development and Validation of Deep Learning–Based Infectivity Prediction in Pulmonary Tuberculosis Through Chest Radiography: Retrospective Study2024 · 6 citations