Beyond accuracy: evaluating the operational feasibility and diagnostic yield of CAD4TB vs. Timika score for scalable TB screening in low-resource settings - Summary - MDSpire

Beyond accuracy: evaluating the operational feasibility and diagnostic yield of CAD4TB vs. Timika score for scalable TB screening in low-resource settings

  • By

  • Reyhan Eddy Yunus

  • Arierta Pujitresnani

  • Syarifaha Ihsan

  • Kahlil Gibran

  • Muhammad Reynalzi Yugo

  • Dean Handimulya Djumaryo

  • Prasandhya Astagiri Yusuf

  • Eric Daniel Tenda

  • May 29, 2026

  • 0 min

Share

Objective:

To evaluate the diagnostic performance of CAD4TB in screening Indonesian patients suspected of tuberculosis using chest x-ray images, comparing its efficacy to the Timika score assessed by experts.

Key Findings:
  • CAD4TB demonstrated an AUC of 0.778 (95% CI 0.712–0.844) compared to AFB results.
  • With a ≤7-day interval between CXR and AFB data, CAD4TB showed an AUC of 0.767 (95% CI 0.668–0.866).
  • The Timika score had an AUC of 0.726 (95% CI 0.632–0.820).
  • CAD4TB exhibited superior specificity (71.43% vs. 57.64%, p < 0.001) while maintaining a fixed sensitivity of 73.91%.
Interpretation:

Limitations:
  • Study conducted at a single center, limiting generalizability.
  • Only initial evaluations included; no follow-up data analyzed.
  • Exclusion of pregnant women and patients with poor CXR image quality.
Conclusion:

Original Source(s)

Related Content