Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
September 10, 2025BMC Global and Public HealthOpen Access

Performance of chest X-ray with computer-aided detection powered by deep learning-based artificial intelligence for tuberculosis presumptive identification during case finding in the Philippines

View Full Paper
Ask AI
Bookmark
Share

Authors

NMNuria Ponce MárquezECErwin John T CarpioMSMônica Maria Lins Santiago

Discussion

Loading...

Member takes

Overview

Retrospective analysis demonstrates high sensitivity and low specificity for AI-powered TB screening, highlighting challenges.

Key Points

  • The AI-CAD model exhibited high pseudo-sensitivity of 95.6% while showing low pseudo-specificity at 28.1%.
  • Analysis involved 5740 individuals, using chest X-ray metrics and WHO-recommended tests to evaluate TB detection efficiency.
  • Threshold adjustments in AI-CAD significantly impacted positive predictive value and case detection rates across varying settings.
  • Integration of AI in TB screening could enhance elimination efforts if calibrated to local resource availability and prevalence.

Cite This Study

Márquez et al. (2025) studied this question.

synapsesocial.com/papers/68c1ce7b54b1d3bfb60f5dffhttps://doi.org/10.1186/s44263-025-00198-y
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. 1What is an ROC curve?2017 · 554 citations
  2. 2The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets2015 · 5,181 citations
  3. 3The rise of artificial intelligence reading of chest X-rays for enhanced TB diagnosis and elimination2023 · 61 citations
  4. 4Deep learning assistance for tuberculosis diagnosis with chest radiography in low-resource settings2021 · 33 citations
  5. 5Understanding diagnostic tests 2: likelihood ratios, pre‐ and post‐test probabilities and their use in clinical practice2007 · 445 citations