A collaborative research team from the University of Southern California, Microsoft AI for Good Lab, Amref Health Africa, and Kenya’s Ministry of Health has created an artificial intelligence model that can predict acute child malnutrition in Kenya up to six months before it occurs. This breakthrough tool provides governments and humanitarian organizations with crucial advance notice to deliver essential supplies and healthcare to vulnerable regions.
Key Findings
The machine learning model combines clinical data from over 17,000 Kenyan health facilities with satellite information on crop health and productivity, achieving 89% accuracy in one-month forecasts and 86% accuracy over six months. This represents a significant improvement over traditional models that rely solely on historical malnutrition trends.
Improving Malnutrition Prediction
The new AI tool excels particularly in regions where malnutrition rates fluctuate and surges are challenging to anticipate. “This model is a game-changer,” said Bistra Dilkina, associate professor of computer science and co-director of the USC Center for Artificial Intelligence in Society. “By using data-driven AI models, we can capture complex relationships between multiple variables that help us predict malnutrition prevalence more accurately.”
Addressing a Public Health Emergency
In Kenya, approximately 350,000 children under five suffer from acute malnutrition, a condition that severely weakens the immune system and increases the risk of death from common illnesses. The current forecasting methods, largely based on expert judgment and historical data, struggle to predict new hotspots or rapid changes.
“Malnutrition is a public health emergency in Kenya. Children are sick unnecessarily. Children are dying unnecessarily,” said Laura Ferguson, director of research at USC’s Institute on Inequalities in Global Health.
Innovative Approach and Future Directions
The research team developed a prototype dashboard that visualizes regional malnutrition risk, enabling quicker and more targeted responses. Ferguson and Dilkina are now working with Kenyan health authorities and Amref Health Africa to integrate the model into government systems, aiming to create a sustainable public resource.
The AI-driven framework, which relies on existing health and satellite data, has the potential to be adapted for use in other countries. “If we can do this for Kenya, we can do it for other countries,” Dilkina stated, highlighting the global implications of this innovative approach to combating malnutrition.
