A model-based study by Ateneo de Manila University researchers, published in August 2026, projects that artificial intelligence-assisted chest X-ray interpretation could lower the cost of tuberculosis screening in Philippine rural health units compared with manual reading, though the researchers caution that the savings depend on local conditions.
The research, published in the BMC Health Services Research journal, was conducted by Dr. Harold Henrison Chiu, Dr. Bryan Christopher Lao, and Dr. Gloanne C. Adolor of Ateneo de Manila University. A press release from the university's Research Communications Section, issued on September 25, 2026, described the study as an effort to determine whether AI can help bridge the Philippines' public healthcare gap.
Scale of the TB Burden in the Philippines
The Philippines carries a significant share of the world's tuberculosis burden. According to the World Health Organization, an estimated 739,000 people in the Philippines developed tuberculosis in 2024 alone — representing 6.8 percent of the 10.8 million TB cases recorded globally that year.
Early detection is critical because TB caught at an advanced stage can cause irreversible damage. However, in geographically isolated or disadvantaged communities, even obtaining an X-ray does not guarantee timely results. Patients in rural health units may wait extended periods for a radiologist or teleradiology service to interpret their images — delays that can mean additional travel, extra expenses, lost wages, or a missed opportunity for continued care.
How the Research Model Was Constructed
The Ateneo team developed a decision-analytic model based on a theoretical annual cohort of 1,000 presumptive TB patients undergoing chest radiography in rural health units. According to the study, the analysis covered costs and outcomes over a five-year period and factored in AI software and operating expenses, radiologist reading fees, and confirmatory GeneXpert testing.
The model-based projections showed that the AI-assisted screening strategy would entail an estimated annual cost of ₱877,330, compared with ₱1.14 million for manual interpretation. Divided across the 1,000 individuals screened, this translated to approximately ₱877 per person under the AI-assisted approach, versus roughly ₱1,142 per person using manual radiologist reading.
AI as a Tool for Geographic Equity, Not Just Efficiency
The researchers argue that the value of AI-assisted X-ray reading extends well beyond cost savings or diagnostic speed. In the study, the team framed the central question in terms of access and equity rather than technological performance.
"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 researchers stated.
The study notes that, if properly integrated into existing TB programs — using portable digital X-ray equipment and systems capable of operating under limited internet connectivity — AI could help bring TB screening directly to underserved populations.
Limitations and the Role of Local Cost Conditions
The research also identifies conditions under which AI's cost advantage diminishes. When a lower manual or teleradiology reading fee was applied in the model, or when diagnostic performance figures drawn from a Philippine-specific scenario were used, AI remained more effective but was no longer necessarily cost-saving.
The study is based on a theoretical cohort and relies on assumptions about costs and diagnostic accuracy. Additionally, AI-assisted findings would still require confirmatory testing.
Researchers Recommend Pilots Before Broad Rollout
Rather than advocating for rapid national adoption, the Ateneo team recommends beginning 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 rollout.
The study, titled Cost-effectiveness evaluation of artificial intelligence-assisted chest radiograph interpretation for tuberculosis screening in rural health units in the Philippines, was published 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.
Photo credit: Chiu et al., 2026