What is the name of your organization?
Vector Control Innovations
What is the name of your solution?
VectorCam
Provide a one-line summary or tagline for your solution.
AI-enabled community mosquito surveillance powering predictive intelligence in low-resource health systems.
In what city, town, or region is your solution team headquartered?
Baltimore, MD, USA
In what country is your solution team headquartered?
United States
What type of organization is your solution team?
Nonprofit
Film your elevator pitch.
What specific problem are you solving?
Vector-borne diseases threaten over half of the world’s population and cause an estimated 1 billion infections annually. Malaria alone accounts for hundreds of thousands of deaths each year, with approximately 95% occurring in sub-Saharan Africa. Despite this burden, recent assessments indicate that up to 92% of Ministries of Health in Africa face significant challenges sustaining routine entomological surveillance practices, or the monitoring of the mosquitoes that transmit the disease.
Climate variability, insecticide resistance, invasive species, and rapid urbanization are accelerating changes in vector ecology, making transmission patterns increasingly dynamic. Yet surveillance systems remain constrained by shortages of trained entomologists, centralized laboratory workflows, intermittent funding, and fragmented reporting systems.
While predictive modeling and AI tools continue to advance globally, these approaches depend on reliable upstream sensing data. In many endemic districts, that foundational data infrastructure is inconsistent or absent. By the time case-based surveillance detects rising infections, transmission is already underway.
The critical constraint is not the absence of predictive models, but the absence of scalable, sustainable community-embedded sensing systems capable of generating continuous, structured vector data for anticipatory public health action.
What is your solution?
VectorCam is a community-embedded, AI-enabled mosquito surveillance platform that builds the upstream sensing infrastructure required for predictive public health in low-resource settings. Village Health Teams and vector control officers use a low-cost, 3D-printed smartphone optical device to capture mosquito specimens in the field. An edge machine learning model classifies species, sex, and feeding status offline, enabling structured, real-time data capture even in areas with limited connectivity.
These data integrate into VectorInsight, a district-level analytics layer compatible with national health information systems such as DHIS2. By aggregating longitudinal entomological signals across geography and time, the system generates interpretable risk indicators that support earlier and more targeted intervention planning.
Rather than introducing standalone forecasting models into fragile systems, VectorCam strengthens the foundational sensing layer those models depend on. By linking human-mediated community surveillance with AI-assisted classification and centralized analytics, the platform enables Ministries of Health to transition from reactive vector control campaigns toward anticipatory, data-informed disease prevention. This solution empowers local health workers to not only collect relevant transmission information from their communities, but inform them of cost-neutral solutions to protect their communities.
Link: https://www.youtube.com/watch?v=1GTTaWPl2ZE
Who does your solution serve, and in what ways will the solution impact their lives?
VectorCam serves Ministries of Health, National Malaria/Dengue Elimination Programs, and district-level vector control teams, particularly in low-resource and underserved settings.
Primary users include Village Health Teams and vector control officers who collect mosquito specimens but often lack rapid identification tools and structured reporting systems. Secondary users include district health officials responsible for planning interventions such as indoor residual spraying, larval source management, and resource allocation. By equipping frontline workers with AI-assisted identification tools, the system strengthens individual-level sensing capacity. Through centralized dashboards and longitudinal data aggregation, it strengthens system-level decision-making.
This dual design ensures that community-based workers retain ownership of data collection while district officials gain timely, interpretable insights into vector density trends and species composition shifts. Ultimately, communities at risk of malaria and other mosquito-borne diseases benefit from earlier, more targeted interventions that improve efficiency, reduce reactive emergency responses, and enhance health system resilience.
