Background: Since 2017, the Philippines Business for Social Progress (PBSP) has implementedactive case finding for Tuberculosis under their Advancing Client-centered Care and ExpandingSustainable Services for TB (ACCESSTB) project. This study aims to conduct a comparative analysisof a screening approach using AI for Chest X-ray (CXR) interpretation versus an approach relyingsolely on human-readers in three major regions of the Philippines.
Back
Methods: This study undertook a retrospective analysis of data derived from two well-established andongoing screening approaches. The data on number of people screened and the outcome of thescreening at each stage of the screening process was extracted from quarterly reports provided byPBSP. Subsequently, the data was analysed to determine the diagnostic yield, the number needed toscreen and the drop-out rates.
Results: The AI screening approach had a lower number needed to screen (26.3) compared to human-reader screening (41.5). The main reason driving this difference is the lower drop-out rate after CXR(16.6% in AI approach versus 43.1% in human reader approach). This lower drop-out rate isattributed to the quicker turnaround time for CXR results and this has an important public healthbenefit because a higher proportion of positive TB individuals participating in the screening willreceive treatment in the AI screening approach (3.8% versus 2.4%).
Conclusion: The results illustrate that AI-powered CXR screening has clear benefits compared toscreening with human readers. Further research is required to determine the comparative cost-effectiveness of the two screening approaches.
