JMIR Publications

ABSTRACT

Background:

In resource-limited areas, severe shortages of radiologist contribute to high rates of missed pulmonary tuberculosis (PTB) cases when relying solely on conventional chest X-ray (CXR). Although artificial intelligence (AI)-powered computer-aided detection (CAD) has shown effective in PTB diagnosis, its real-world clinical utility and scalability in primary healthcare settings remained underexplored.

Objective:

To evaluate the real-world performance of CAD technology for triaging of PTB patients in primary healthcare facilities in high-incidence areas, and to assess its potential for optimizing radiological resource allocation.

Methods:

We conducted a retrospective paired-design diagnostic accuracy study using CXR images collected from 7 county- and 32 township-level healthcare facilities in Yichang city between 2022 and 2024. All images were retrospectively reprocessed with CAD software (JF CXR-1 v2), and the original radiology reports interpreted by radiologists were extracted. CAD and radiologist performances were compared using two primary evaluation indicators: diagnostic yield among diagnosed cases (DYD) and positive predictive value (PPV). Subgroup analysis (by region, age, sex, healthcare facility tier, and patients category) and sensitivity analysis were conducted to assess the robustness of the results.

Results:

Among 93,319 enrolled study patients (including 273 bacteriologically confirmed PTB cases), CAD demonstrated a substantially higher DYD (83.88%, 229/273) than radiologists (25.64%, 70/273), though with much lower PPV (1.70% vs. 10.31%). This high-sensitivity performance achieved an 85.52% reduction (only 13,515 instead of 93,319 CXRs) in radiologist workload via selective review of CAD-positive images, without missing any radiologist-identified PTB cases. Furthermore, among CAD-positive images, probability scores >0.75 was a key threshold for identifying high-risk PTB patients, prioritizing for radiologist review. Subgroup analysis further revealed that CAD outperformed radiologists in identifying PTB cases across all scenarios, despite some heterogeneity. In township healthcare facilities, CAD demonstrated significantly better performance than in county-level facilities, with DYD of 86.72% and 62.50%, and PPV of 2.00% and 0.65%, respectively.

Conclusions:

CAD technology demonstrates valuable PTB screening performance in primary healthcare facilities. Combined with a tiered "AI pre-screening with selective human review" strategy, this approach effectively alleviates workload of radiologist in resource-constrained regions, offering a scalable solution for tuberculosis prevention and control.