Reimagining TB Detection in Southeast Asia Through AI Innovation

          Asean4TB, 2025 — Artificial intelligence (AI) is rapidly transforming how countries detect and manage tuberculosis (TB), offering new tools to close persistent diagnostic gaps across Southeast Asia. Many ASEAN nations continue to face high TB burdens, limited diagnostic capacity, and inconsistent access to screening—challenges highlighted in the Global Tuberculosis Report 2025, which notes that early detection remains one of the region’s most significant hurdles. In high-burden settings where health systems are overstretched, AI-assisted technologies offer a promising pathway to accelerate identification and treatment of TB cases.

        AI-powered computer-aided detection (AI-CAD) for chest X-ray stands out as one of the most impactful innovations. With WHO recommending CAD as an alternative to human readers for TB screening and triage in adults, the technology is particularly relevant for ASEAN countries where radiologists are concentrated in urban centers. Early evaluations from Indonesia, Viet Nam, and the Philippines show that modern AI-CAD systems can achieve diagnostic performance comparable to expert readers and substantially improve TB case detection in high-burden settings. In Thailand, AI is being progressively adopted within public health radiology workflows, reflecting strong national interest in integrating AI-assisted interpretation even as further accuracy studies are underway. Together, these early experiences illustrate the growing momentum for AI-assisted screening across ASEAN’s diverse health systems.

          As ASEAN countries move from pilot deployments to broader implementation, success depends on how well AI systems are calibrated to local epidemiological patterns, integrated into clinical workflows, and supported by strong digital infrastructure. Ensuring responsible use of AI also requires attention to equity, data governance, and consistent performance across diverse populations. These considerations align closely with ASEAN’s earlier assessments, which emphasize disparities in diagnosis and the need for coordinated action across Member States to strengthen TB control efforts.

      Regional collaboration will be key to transforming AI from isolated projects into systems-wide innovation. Platforms such as ASEAN4TB can help standardize evaluation methods, facilitate shared calibration datasets, and support cross-country research on AI-assisted diagnosis. With several ASEAN countries historically classified as high TB burden nations and facing similar diagnostic challenges, a coordinated approach can reduce costs, speed up adoption, and ensure safer, more equitable rollout. By uniting evidence, policy, and innovation, ASEAN has the opportunity to lead globally in applying AI to end tuberculosis.

References:

1. World Health Organization. Global Tuberculosis Report 2025. Geneva: WHO; 2025.

2. World Health Organization. Use of computer-aided detection (CAD) for tuberculosis screening and triage for X-ray. Geneva: WHO; 2021

3. Burhan E, Maryastuti M, Wulandari L, Handayani D, et al. Pulmonary tuberculosis prediction using CAD4TB artificial intelligence based on thoracic X-ray photos among Indonesian subjects in hospital. medRxiv. 2025.

4. Innes AL, Martinez A, Gao X, Dinh N, Hoang GL, Nguyen TBP, et al. Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam’s District Health Facilities: An Implementation Study. Trop Med Infect Dis. 2023;8(11):488.

5. Marquez N, et al. Performance of chest X-ray with AI-based computer-aided detection for TB screening in the Philippines: a real-world evaluation. BMC Glob Public Health. 2025;5:198.

6. Tanomkiat W, Chaichulee S, et al. Thailand is implementing artificial intelligence to assist interpreting chest radiographs in public health. ASEAN J Radiol. 2025;26(3):270–83.