Enhancing TB Case Notification in High-Burden Areas of South Ethiopia: The Role of Mapping Hotspot Areas and AI-Assisted Ultra-Portable Digital X-ray Screening in Community-Level Active Case Finding
1
Monitoring, Evaluation and Research, REACH Ethiopia, Addis Ababa, Ethiopia
Popul. Med. 2026;8(Supplement Supplement 1):A742
ABSTRACT
BACKGROUND:
Ethiopia remains among the 30 high-TB-burden countries, with many cases going undetected due to limited access to diagnostic services and geographic barriers. In highly rural regions like South Ethiopia, the health system faces challenges in reaching underserved populations. To optimize TB active case finding, hotspot mapping offers a data-driven approach for prioritizing high-yield screening areas. This study evaluates the combined impact of geospatial hotspot mapping and AI-assisted chest X-ray (CXR) screening under the USAID-funded SWIF-TB initiative to enhance TB case notification. Design/
METHODS:
A pilot study was conducted in four districts of the Sidama Region. TB hotspot mapping was performed using geospatial analysis of historical case data, guiding targeted screening with AI-supported CXR and symptom screening tools. Screening focused on the general population and children with a history of TB contact. Data were collected through KoboToolbox and analyzed using descriptive and inferential methods. Screening and diagnostic services were linked with 20 public health facilities.
RESULTS:
Of the 2,524 TB cases, 2,264 (90%) were successfully mapped. Twenty hotspot villages accounted for over 80% of the TB burden. Among 2,058 individuals screened, 304 presumptive TB cases were identified, with 43 confirmed TB cases, yielding an overall positivity rate of 14.4% (95% CI: 10.6–19.3%). Symptom-based screening alone yielded 3% (95% CI: 0.7–9.5%), CXR alone 13% (95% CI: 8.1–20.3%), and combined screening 29% (95% CI: 20.2–39.4%). The intervention raised the case notification rate to 2,089 per 100,000 (95% CI: 1,531–2,788), nearly seven times higher than the regional average of 313 (95% CI: 308–318). AI-assisted CXR achieved 95.2% sensitivity (95% CI: 84.2–98.7%).
CONCLUSIONS:
Geospatial hotspot mapping improved TB detection and resource use by targeting high-burden areas. Combined with AI-assisted X-ray screening, it enabled early case identification, supporting its integration into national ACF strategies in rural, resource-limited settings.
Ethiopia remains among the 30 high-TB-burden countries, with many cases going undetected due to limited access to diagnostic services and geographic barriers. In highly rural regions like South Ethiopia, the health system faces challenges in reaching underserved populations. To optimize TB active case finding, hotspot mapping offers a data-driven approach for prioritizing high-yield screening areas. This study evaluates the combined impact of geospatial hotspot mapping and AI-assisted chest X-ray (CXR) screening under the USAID-funded SWIF-TB initiative to enhance TB case notification. Design/
METHODS:
A pilot study was conducted in four districts of the Sidama Region. TB hotspot mapping was performed using geospatial analysis of historical case data, guiding targeted screening with AI-supported CXR and symptom screening tools. Screening focused on the general population and children with a history of TB contact. Data were collected through KoboToolbox and analyzed using descriptive and inferential methods. Screening and diagnostic services were linked with 20 public health facilities.
RESULTS:
Of the 2,524 TB cases, 2,264 (90%) were successfully mapped. Twenty hotspot villages accounted for over 80% of the TB burden. Among 2,058 individuals screened, 304 presumptive TB cases were identified, with 43 confirmed TB cases, yielding an overall positivity rate of 14.4% (95% CI: 10.6–19.3%). Symptom-based screening alone yielded 3% (95% CI: 0.7–9.5%), CXR alone 13% (95% CI: 8.1–20.3%), and combined screening 29% (95% CI: 20.2–39.4%). The intervention raised the case notification rate to 2,089 per 100,000 (95% CI: 1,531–2,788), nearly seven times higher than the regional average of 313 (95% CI: 308–318). AI-assisted CXR achieved 95.2% sensitivity (95% CI: 84.2–98.7%).
CONCLUSIONS:
Geospatial hotspot mapping improved TB detection and resource use by targeting high-burden areas. Combined with AI-assisted X-ray screening, it enabled early case identification, supporting its integration into national ACF strategies in rural, resource-limited settings.
| 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.
