Africa’s new epidemic watchdog: AI-driven, gender-inclusive and community-powered

Emerging and re-emerging infectious diseases continue to pose serious threats to global public health, with zoonotic outbreaks increasingly challenging already strained healthcare systems. Effective control now demands integrated, data-driven solutions capable of tracking transmission across human, animal, and environmental domains, solutions that traditional approaches alone can no longer deliver.

The study, titled “Leveraging AI in Digital One Health: An Inter-University Collaboration for Emerging and Re-Emerging Infectious Disease Control in Cameroon”, published in Frontiers in Digital Health, outlines a comprehensive framework known as DigiCare Cameroon, which applies a Digital One Health (DOH) approach to epidemic and pandemic preparedness through AI-powered surveillance, forecasting, and public health decision support.

The initiative, funded by Canada’s International Development Research Centre and supported through the AI4PEP (Artificial Intelligence for Pandemic and Epidemic Preparedness and Response) network, brings together interdisciplinary teams from the University of Buea and the University of Ngaoundéré. By integrating human, animal, and environmental health data with machine learning models, the consortium aims to deliver real-time outbreak prediction, localized response strategies, and equitable community-based healthcare interventions.

How does DigiCare integrate AI with One Health to address epidemic risks?

The initiative is rooted in the One Health concept, which recognizes that human, animal, and environmental health are interconnected. With over 60% of emerging infectious diseases (EIDs) being zoonotic in origin, the study emphasizes the need for a unified surveillance strategy that spans veterinary science, public health, and environmental monitoring. The DigiCare platform uses AI to link these domains under a digital framework capable of tracking, predicting, and responding to disease outbreaks in a more timely and equitable manner.

Through machine learning and natural language processing, the project will develop mobile apps and interactive dashboards capable of synthesizing data from community reports, environmental metrics, and clinical databases. These systems will detect early signals of epidemics like cholera or Ebola, allowing health authorities to respond before outbreaks escalate. AI-powered chatbots are also planned to deliver tailored health information in local languages, expanding public engagement while reducing misinformation.

A key feature of DigiCare’s technical design is its emphasis on data interoperability and real-time analytics. Health information systems will be deployed at pilot sites to automate patient-level data collection, forming the basis for training predictive AI models. These models are expected to enhance resource allocation, optimize contact tracing, and provide community-specific risk assessments for decision-makers.

What makes this collaboration unique in the African research landscape?

The strength of DigiCare lies in its inter-university structure, bringing together a uniquely diverse pool of experts across fields as varied as epidemiology, computer science, veterinary medicine, gender studies, and cardiology. Each participating team contributes five researchers, creating a 15-member consortium enriched by gender and disciplinary diversity. This blend of medical, technical, and social science expertise enables the development of AI tools that are context-sensitive and adaptable to both rural and urban environments.

Researchers from the University of Buea’s Faculty of Health Sciences focus on epidemiology and public health programming, while teams from the Faculty of Science bring in data science, maternal health, and gender equity dimensions. Veterinary specialists from the University of Ngaoundéré play a critical role in zoonotic surveillance and integration of animal health into disease forecasting models. Their collaboration ensures a holistic application of the One Health model.

This diversity also helps the consortium bridge a critical gap in AI research - equity. DigiCare’s design prioritizes community participation and gender inclusion, recognizing that digital tools must reflect the lived realities of marginalized populations. Community engagement campaigns are being conducted to build trust and literacy in AI applications. At the institutional level, the study outlines governance structures to ensure ethical data use, protection of patient privacy, and algorithmic fairness.

What are the broader impacts and challenges facing AI-based disease control?

The DigiCare project is already being positioned as a national test case for scalable AI deployment in public health infrastructure. The authors emphasize its alignment with two Sustainable Development Goals - SDG 3 (Good Health and Well-being) and SDG 5 (Gender Equality). With strategic support from York University in Canada and other African partners, DigiCare also signals a shift toward African-led innovation in digital health and pandemic response.

Initial deployment began in late 2023, marked by a high-level launch event at the University of Buea that included government officials, researchers, and civil society representatives. Early outcomes include institutional partnerships, student engagement, and pledges from health authorities to integrate AI outputs into local decision-making processes. The collection of baseline community data is currently underway and will inform the design of AI algorithms tailored to Cameroon's socio-epidemiological context.

However, the project is not without hurdles. The study identifies significant risks related to data ethics, cybersecurity, and community mistrust. Concerns around informed consent, data ownership, and algorithmic bias are particularly pressing in low-resource settings. To address these, the consortium is developing a standardized ethical framework based on FAIR (Findable, Accessible, Interoperable, Reusable) data principles and community advisory participation.

Sustainability is another challenge. Ensuring that AI tools remain usable after the project period will require investments in local capacity building, ongoing stakeholder engagement, and integration with existing health infrastructure. The study calls for long-term policy alignment to embed AI-driven One Health tools into Cameroon’s national epidemic preparedness strategy.