Smart Solutions Battling Malaria in Liberia with AI

In just a few weeks, Omdena brought together experts from 8+ countries to build an AI-powered malaria prediction app for Liberia—enabling county-level outbreak forecasting and targeted prevention. By integrating multi-source health and climate data and deploying a high-accuracy predictive model, the solution helps health officials anticipate high-risk periods and allocate resources more effectively to protect children, pregnant women, and vulnerable communities.

Introduction

On May 15, 2024, the Omdena community proudly presented the project “Developing an AI-powered App for Predictive Modeling and Forecasting of Malaria Prevention in Liberia.”

This global initiative brought together data practitioners from Sri Lanka, India, the United States, Bolivia, Portugal, Brazil, and multiple West African nations, including Liberia. For many participants, it was an opportunity to apply their academic and technical knowledge in Data Analytics, Data Science, and Machine Learning Engineering to solve a critical real-world challenge.

The project combined different data sources and predictive modeling techniques to identify patterns in malaria transmission and mortality. The goal was to enable proactive planning and early intervention—reducing malaria cases and preventing avoidable deaths, especially among children and pregnant women who are most at risk.

Malaria continues to be a major public health threat across Africa. By integrating multiple datasets and using advanced predictive models, this AI-powered app helps health officials anticipate when and where malaria outbreaks are likely to occur, making prevention efforts more targeted and effective.

The project was led by Liberian Data Scientist Daikukai Bindah, who guided the team through the process of designing and implementing the AI-driven solution. This article highlights why malaria remains a critical challenge in Liberia and how the team addressed data scarcity to build an effective predictive model.

The Problem

Child receiving malaria testing and treatment in Sierra Leone. Photo by PMI Impact Malaria

Malaria remains one of the deadliest diseases globally, particularly impacting children under five and pregnant women. In 2020, Africa accounted for 95% of malaria cases and 96% of malaria-related deaths. According to the study “Mathematical Modelling and Optimal Control of Malaria Using Awareness-Based Interventions” by Fahad Al Basir and Teklebirhan Abraha, 80% of these deaths were among children under five. The World Health Organization (WHO) also notes that malaria during pregnancy can lead to severe complications such as anemia, premature birth, and low birth weight.

Efforts to control and eliminate malaria face several obstacles. The Anopheles mosquitoes that transmit malaria have developed resistance to commonly used medications and insecticides. Limited health infrastructure, restricted financial resources, and climate conditions further accelerate transmission. Additionally, population mobility within and across regions contributes to the spread of the disease.

Despite these challenges, new solutions are emerging. Advances in molecular identification, highlighted in the study “Revolutionizing Malaria Vector Control: The Importance of Accurate Species Identification through Enhanced Molecular Capacity,” and ongoing technological innovations, such as those reviewed in “Leveraging Innovation Technologies to Respond to Malaria: A Systematized Literature Review of Emerging Technologies,” offer promising avenues for malaria control. However, these strategies rely on accurate and continuous data collection, which is often difficult to maintain.

As noted in recent research, 34% of new anti-malaria innovations are web-based, 28% are mobile applications, 25% focus on diagnostic tools and devices, and 13% involve drone-based technologies. Our approach falls into the web-based category — currently the most widely adopted and accessible format for public health systems.
.

Project Goals

The AI-powered Anti-Malaria App was developed to support more effective malaria prevention and response in Liberia. To achieve this, the project team focused on three core goals:

Methodology and Sources Of Data

One of the main challenges in this project was data scarcity. Accurate predictive modeling requires continuous and comprehensive data, yet many regions in Liberia lack the resources and infrastructure needed to collect it consistently.

To overcome this, the team integrated data from several reliable international sources:

By combining these sources, the team collected sufficient county-level data for Liberia, which was essential for building accurate predictive models. As Thomas James, a North American Data Scientist on the team, explained during the project presentation:

What We Found From Analyzing The Data

The team conducted Exploratory Data Analysis (EDA) to understand how rainfall patterns, malaria cases, and malaria-related deaths were connected across Liberia’s 15 counties. The analysis highlighted notable differences in malaria prevalence from one county to another.

The data showed that both malaria cases and deaths have continued to increase year over year, indicating that current prevention efforts are not reducing the burden of the disease at the national level.

Additionally, the analysis revealed that each county experiences malaria differently. For example, Greater Kru and River Gee counties demonstrated significantly different case numbers and mortality rates. These variations emphasize the importance of localized public health strategies, rather than a one-size-fits-all approach.

.

Choosing the Model: After extensive testing, the team selected the Random Forest Regressor (RFR) as the best-performing model. Key performance metrics included:

These results show that the model was able to reliably predict malaria cases and deaths. Predictive modeling is rapidly becoming a core capability for NGOs It also offered valuable insights into how rainfall patterns and various malaria interventions — such as Indoor Residual Spraying (IRS), Insecticide-Treated Nets (ITNs), and medical treatments — influence disease transmission.

Application and Future Directions

The AI-powered app gives users a deeper understanding of how environmental and social factors influence malaria transmission in Liberia. By accurately identifying high-risk areas and predicting when outbreaks are likely to occur, the app helps health officials and policymakers plan more effective prevention strategies.

This targeted approach ensures that resources are used where they are needed most, making malaria control efforts more efficient and impactful. As a result, the app plays an important role in reducing malaria cases and deaths, improving public health outcomes, and building stronger, healthier communities.

Benefits of Using these Methodologies and Impact

Future Possibilities

Conclusion

The development of the AI-powered Anti-Malaria App in Liberia demonstrates the transformative potential of data-driven approaches in tackling global health challenges. By combining the expertise of a diverse, international team with advanced machine learning techniques, this project offers a promising solution to one of the world’s most persistent health threats.

Continued innovation and collaboration are essential to further enhance the app’s capabilities and expand its impact. By leveraging AI and comprehensive data analysis, we can move closer to a future where malaria is no longer a threat to millions of lives.