COAST

Welcome to COAST project Uganda

End-to-end AI and data systems for targeted surveillance and management of COVID-19 and future pandemics affecting Uganda

LEARN MORE
Map of Uganda with theme illustrations
Scroll Down Arrow
Scroll Down Arrow

Synergistic end-to-end AI and data systems

...
Strengthen data systems resulting in usable and equitable datasets for AI-driven COVID-19 responses and future pandemics in Uganda
...
Develop and deploy AI-driven detection and diagnosis tools for improved patient care and management
...
Model and evaluate COVID-19 interventions for targeted government responses based on the fused datasets from objectives 1 and 2
The fluidity of the COVID-19 outbreak requires innovative data systems that fuse data from multiple sources that need to be frequently updated. In sub-Saharan Africa, data imbalances and underrepresentation can easily arise due to unequal access to government and private services where data is collected due to socio-demographic conditions. If these are not addressed, they can result in AI and data science solutions that do not benefit communities that are most vulnerable for COVID-19 and future pandemics. COAST will address these challenges through three specific objectives:
OBJECTIVE 1

Inclusive and equitable datasets

To strengthen data systems resulting in usable and equitable datasets for AI-driven COVID-19 responses and future pandemics. COAST will uniquely combine multiple existing datasets that include:
• Existing and ongoing near real-time radio broadcast data allowing for collection of male and female community voices on COVID-19 issues
• Existing and ongoing call records from health facilities and community healthcare worker questions about prevention and management of COVID-19 and other infectious diseases
• Existing and ongoing data on air pollution, which is a major risk for respiratory infections. This objective will lead to improved data readiness and local AI capacity for better surveillance and management of COVID-19 in Uganda
People working on a computer.
Photo of a doctor at work in laboratory
OBJECTIVE 2

AI-powered detection and diagnostics tools

To develop and deploy AI-driven detection and diagnosis tools for improved patient care and management. We will develop a data-driven decision support system to screen for COVID-19 and future outbreaks based on data collected through the existing interactive voice response tool that records symptoms including those known to be COVID-19 related in 3,500 people living with HIV and the wider population. The decision support system will be complemented by a Uganda COVID-19 AI chatbot targeting the youth and urban population. Finally, we will evaluate the feasibility of an AI-based lung ultrasound for screening and triage of COVID-19 cases.
OBJECTIVE 3

Targeted government responses and inventions

To model and evaluate COVID-19 interventions for targeted government responses based on the fused datasets from objectives (A) and (B). AI and mathematical forecasting models will be developed for real-time tracking of COVID-19 spread and associated risks to inform regional and population specific interventions. Using AI techniques, we will automatically analyse radio conversations and identify the issues affecting the 'offline' male and female communities and their perceptions towards public policy in the COVID-19 pandemic.
Man using computers.

A combination of AI, data science, epidemiological, statistical and software engineering approaches to provide data-driven interventions for pandemics

Workstream 1
Mining text & audio data for community perceptions

• Radio broadcast data analysis.
• Audio and textual data from healthcare workers seeking advice from a helpline.
Workstream 2
Detection & diagnosis tools for improved patient care & management

• Decision support system for the call for life (CFL)
• Uganda COVID-19 AI chatbot
• ML-guided screening
Workstream 3
Modelling & forecasting transmissions for policy

• Modelling and forecasting COVID-19 transmission and evaluation of COVID-19 responses
Workstream 4
Air quality- COVID-19 risk analysis



• Community risk analysis based on environmental data

Partners and Collaborators

This research project is funded by Canada's International Development Research Centre (IDRC) and the Swedish International Development Cooperation Agency (Sida) as part of the Global South AI4COVID Program.
International Development Research Centre Swedish International Development Cooperation Agency African Centers of Excellence In Bioinformatics Global South Program Makerere University Infectious Disease Institute Airqo Makerere AI Lab Crane Cloud