A study from Ateneo de Manila University, published in August 2026, projects, in a model-based analysis, that using artificial intelligence to read chest X-rays could lower the cost of tuberculosis screening in Philippine rural health units compared with manual reading, though the researchers note that the savings depend on local conditions.
Who Conducted the Study and Where It Appeared
The research was carried out by Dr. Harold Henrison Chiu, Dr. Bryan Christopher Lao, and Dr. Gloanne C. Adolor, all of Ateneo de Manila University. According to the university's Research Communications Section, which issued a press release on September 25, 2026, the study was published in the journal BMC Health Services Research and was framed as an inquiry into whether AI tools can help address gaps in the Philippine public healthcare system.
The Scale of TB in the Philippines
The Philippines carries a significant share of the world's tuberculosis burden. The World Health Organization estimated that around 739,000 people in the country developed TB in 2024 alone, accounting for 6.8 percent of the 10.8 million TB cases recorded globally that year.
Early detection is essential, as TB identified at an advanced stage can cause irreversible harm. Yet in geographically isolated and disadvantaged communities, receiving an X-ray does not automatically mean timely results. Patients in rural health units may wait extended periods before a radiologist or teleradiology service reviews their images — delays that can lead to additional travel costs, lost wages, or a missed opportunity for continued care.
How the Research Model Was Built
The Ateneo team constructed a decision-analytic model based on a theoretical annual cohort of 1,000 presumptive TB patients undergoing chest radiography in rural health units. The study covered projected costs and outcomes over five years, incorporating AI software and operating expenses, radiologist reading fees, and confirmatory GeneXpert testing, according to the release.
Under the AI-assisted approach, the model projected an estimated annual cost of ₱877,330 — translating to roughly ₱877 per person screened. The manual radiologist reading pathway, by comparison, came to approximately ₱1.14 million annually, or about ₱1,142 per individual. The AI-assisted strategy thus represented the lower-cost option under the study's baseline assumptions.
Access and Equity as the Central Argument
The researchers framed the core value of AI-assisted X-ray reading as a matter of geographic equity rather than technological superiority. In the study, as cited in the Ateneo Research Communications Section's release, the team wrote:
"For resource-constrained communities, the most important question is therefore not whether AI can outperform or assist an expert reader, but whether it can extend expert-level support to places where expertise is scarce in a way that is affordable, sustainable, and equitable."
The study notes that, when combined with portable digital X-ray equipment and systems capable of functioning under limited internet connectivity, AI could bring TB screening directly to underserved populations.
When the Cost Advantage Narrows
The research identifies circumstances under which the AI approach's financial edge may not hold. When a lower manual or teleradiology reading fee was applied to the model, or when diagnostic performance figures from a Philippines-specific scenario were used, AI remained more effective but was not necessarily cheaper.
The study is grounded in a theoretical cohort and relies on assumptions about both costs and diagnostic accuracy. AI findings would also still require confirmatory testing.
Pilot Programs Recommended Before National Rollout
Rather than pushing for rapid national adoption, the Ateneo team recommends starting with targeted pilot implementation in underserved rural health units. The researchers call for local validation, quality assurance protocols, continuous monitoring, and budget assessment to accompany any expansion.
The full study — titled Cost-effectiveness evaluation of artificial intelligence-assisted chest radiograph interpretation for tuberculosis screening in rural health units in the Philippines — appears in the August 2026 issue of BMC Health Services Research and is available at archium.ateneo.edu/gsb-pubs/87/.
As the Ateneo release puts it, the question may ultimately be less about bringing the newest technology into healthcare and more about where that technology can help deliver expertise to people with the least access to it.
Source: Ateneo de Manila University Research Communications Section press release