New Frontiers in TB Control: AI-Driven Screening in Refugee Settings in Kenya
1
Kalobeyei Refugee Operation, Kenya Red Cross Society, Kakuma, Kenya
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
BACKGROUND:
The incidence of Tuberculosis (241/100,000) in Kakuma Refugee Camp, Turkana County, Kenya, remains high, far exceeding the national average. Worsening congestion from an ever-increasing refugee population due to geopolitical tensions in East Africa facing some of the worst, underreported humanitarian crisis, with limited diagnostic tools in the humanitarian setting, continuously leads to delayed detection of Tuberculosis. Kalobeyei Refugee Operation is implementing a portable digital chest X-ray program with computer-aided detection (CAD4TB) artificial intelligence to address this gap. The program aligns with the WHO's guidance on using artificial intelligence to improve screening and reduce the incidence of TB by 80% by 2030. Description Since the inception of the CAD4TB program in 2022, Kalobeyei Refugee Operation has run facility-based and outreach TB screening in the high-risk, vulnerable populations in Turkana West. Symptomatic patients and TB contacts receive on-site digital CXR with instant AI-interpretation. All presumptive cases are subject to Gene-Xpert testing with same-day initiation of confirmed cases. Despite power and connectivity challenges, results are shared back through an Android-based application (T-bu lite) by CHPs.
RESULTS:
From September,2022 to September,2025, 12,448 CXRs were performed (5776-facility,6672-outreach). Of these, 539 patients confirmed through GeneXpert and 660 initiated on TB treatment, with same-day linkage achieved in most cases. About 80% of all the cases were presumptive TB, while 15% were contacts or PLHIV, demonstrating targeted screening for vulnerable groups. CAD4TB-portable CXR increased screening reach (up to 1200 interpreted images/day) and reduced the diagnostic delay compared to historical symptom-based screening. Integrating the CAD4TB-services with the TB-register improved continuity-in-care, while task sharing with CHPs strengthened PHC capacity. Conclusion. Tuberculosis continues to hit displaced populations disproportionately, hindering the achievement of UHC across Africa, where political instability is still rampant. Scaling AI-powered TB screening in refugee and other high-burden settings is essential in Africa's move towards self-reliance and UHC.
The incidence of Tuberculosis (241/100,000) in Kakuma Refugee Camp, Turkana County, Kenya, remains high, far exceeding the national average. Worsening congestion from an ever-increasing refugee population due to geopolitical tensions in East Africa facing some of the worst, underreported humanitarian crisis, with limited diagnostic tools in the humanitarian setting, continuously leads to delayed detection of Tuberculosis. Kalobeyei Refugee Operation is implementing a portable digital chest X-ray program with computer-aided detection (CAD4TB) artificial intelligence to address this gap. The program aligns with the WHO's guidance on using artificial intelligence to improve screening and reduce the incidence of TB by 80% by 2030. Description Since the inception of the CAD4TB program in 2022, Kalobeyei Refugee Operation has run facility-based and outreach TB screening in the high-risk, vulnerable populations in Turkana West. Symptomatic patients and TB contacts receive on-site digital CXR with instant AI-interpretation. All presumptive cases are subject to Gene-Xpert testing with same-day initiation of confirmed cases. Despite power and connectivity challenges, results are shared back through an Android-based application (T-bu lite) by CHPs.
RESULTS:
From September,2022 to September,2025, 12,448 CXRs were performed (5776-facility,6672-outreach). Of these, 539 patients confirmed through GeneXpert and 660 initiated on TB treatment, with same-day linkage achieved in most cases. About 80% of all the cases were presumptive TB, while 15% were contacts or PLHIV, demonstrating targeted screening for vulnerable groups. CAD4TB-portable CXR increased screening reach (up to 1200 interpreted images/day) and reduced the diagnostic delay compared to historical symptom-based screening. Integrating the CAD4TB-services with the TB-register improved continuity-in-care, while task sharing with CHPs strengthened PHC capacity. Conclusion. Tuberculosis continues to hit displaced populations disproportionately, hindering the achievement of UHC across Africa, where political instability is still rampant. Scaling AI-powered TB screening in refugee and other high-burden settings is essential in Africa's move towards self-reliance and UHC.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
