Implementation Outcomes of AI-Driven Hotspot Mapping for HIV Case Detection among Pregnant Women in Imo State, Nigeria
1
TB/HIV Services, Caritas Nigeria, Abuja, Federal Capital Territory, Nigeria
2
TB/HIV, Institute of Human Virology, Nigeria, Abuja, Federal Capital Territory, Nigeria
3
TB/HIV/Malaria, Global Fund, Geneva, Switzerland
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
INTRODUCTION:
Pregnant women in Nigeria face persistent gaps in timely HIV screening, especially in crisis-prone settings with fragmented antenatal services, undermining progress toward elimination of mother-to-child transmission (EMTCT). Traditional outreach models often lack precision, resulting in inefficient resource use. This study assesses the use of artificial intelligence (AI)–driven hotspot mapping to enable data-driven, targeted house-to-house HIV testing for pregnant women in high-burden communities.
METHODS:
Using an implementation research design, a before-and-after comparative analysis was conducted on house-to-house HIV testing services (HTS) using HIV/syphilis dual kits among pregnant women (≥15 years) across 27 local government areas in Imo State. Baseline outcomes (January–December 2024) were compared with the intervention period (January–December 2025). Following a two-day technical training, 27 community volunteers and 55 mentor mothers delivered community-based HTS. The EPCON AI tool integrated routine ANC, HIV, and geospatial data to identify high-risk hotspots for targeted testing. Implementation was supported by quarterly supervision. Routine program data were analyzed in MS Excel to assess HTS coverage, case detection yield, and PMTCT linkage rates.
RESULTS:
At baseline in 2024, 5,675 pregnant women were reached and tested with HIV/syphilis dual kits; 65 (1.1%) were HIV-positive and 1 (<0.1%) syphilis-reactive, with 100% linkage to care. EID included 30 samples, all HIV-negative. Following AI-guided hotspot mapping in 2025, reach increased to 26,900 pregnant women, with 25,629 (95.3%) tested. HIV case detection rose to 131 (0.5%) and 2 syphilis cases, all linked to ART. Of 129 EID samples, 10 were positive and linked to care.
CONCLUSIONS:
Integrating AI-driven hotspot mapping into community house-to-house HIV testing services significantly optimizes HIV case finding by shifting from broad interventions to high-precision, and data-led targeting. This approach proves that AI-enabled precision is a scalable necessity for closing the HIV case detection gap and achieving eMTCT targets in the last mile.
Pregnant women in Nigeria face persistent gaps in timely HIV screening, especially in crisis-prone settings with fragmented antenatal services, undermining progress toward elimination of mother-to-child transmission (EMTCT). Traditional outreach models often lack precision, resulting in inefficient resource use. This study assesses the use of artificial intelligence (AI)–driven hotspot mapping to enable data-driven, targeted house-to-house HIV testing for pregnant women in high-burden communities.
METHODS:
Using an implementation research design, a before-and-after comparative analysis was conducted on house-to-house HIV testing services (HTS) using HIV/syphilis dual kits among pregnant women (≥15 years) across 27 local government areas in Imo State. Baseline outcomes (January–December 2024) were compared with the intervention period (January–December 2025). Following a two-day technical training, 27 community volunteers and 55 mentor mothers delivered community-based HTS. The EPCON AI tool integrated routine ANC, HIV, and geospatial data to identify high-risk hotspots for targeted testing. Implementation was supported by quarterly supervision. Routine program data were analyzed in MS Excel to assess HTS coverage, case detection yield, and PMTCT linkage rates.
RESULTS:
At baseline in 2024, 5,675 pregnant women were reached and tested with HIV/syphilis dual kits; 65 (1.1%) were HIV-positive and 1 (<0.1%) syphilis-reactive, with 100% linkage to care. EID included 30 samples, all HIV-negative. Following AI-guided hotspot mapping in 2025, reach increased to 26,900 pregnant women, with 25,629 (95.3%) tested. HIV case detection rose to 131 (0.5%) and 2 syphilis cases, all linked to ART. Of 129 EID samples, 10 were positive and linked to care.
CONCLUSIONS:
Integrating AI-driven hotspot mapping into community house-to-house HIV testing services significantly optimizes HIV case finding by shifting from broad interventions to high-precision, and data-led targeting. This approach proves that AI-enabled precision is a scalable necessity for closing the HIV case detection gap and achieving eMTCT targets in the last mile.
| 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.
