AI can predict child malnutrition and support prevention efforts

A multidisciplinary team of researchers from the USC School of Advanced Computing and the Keck School of Medicine, working alongside experts from the Microsoft AI for Good Lab, Amref Health Africa, and Kenya’s Ministry of Health, has developed an artificial intelligence (AI) model that can predict acute child malnutrition in Kenya up to six months in advance.

The tool offers governments and humanitarian organizations critical lead time to deliver life-saving food, health care, and supplies to at-risk areas. The machine learning model outperforms traditional approaches by integrating clinical data from more than 17,000 Kenyan health facilities with satellite data on crop health and productivity.

It achieves 89% accuracy when forecasting one month out, and maintains 86% accuracy over six months—a significant improvement over simpler baseline models that rely only on recent historical child malnutrition prevalence trends.

In contrast to existing models, the new tool is especially effective at forecasting malnutrition in regions where prevalence fluctuates and surges are difficult 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, you can capture more complex relationships between multiple variables that work together to help us predict malnutrition prevalence more accurately.”

The findings are detailed in a PLOS One study titled “Forecasting acute childhood malnutrition in Kenya using machine learning and diverse sets of indicators.”

The study was co-authored by Girmaw Abebe Tadesse (Microsoft AI for Good Lab), Laura Ferguson (USC Institute on Inequalities in Global Health), Caleb Robinson, Rahul Dodhia, Juan M. Lavista Ferres (Microsoft AI for Good Lab), Shiphrah Kuria, Herbert Wanyonyi, Samuel Mburu (Amref Health Africa), Samuel Murage (Kenyan Ministry of Health), and Bistra Dilkina (USC Center for AI in Society).

Girmaw Abebe Tadesse, principal scientist and manager at the Microsoft AI for Good Lab in Nairobi, Kenya, said he believes the predictive AI tool will make a difference.

“This project is important, as malnutrition poses a significant challenge to children in Africa, a continent that is facing a major food insecurity exacerbated by climate change,” he said.

A public health emergency

In Kenya, 5% of children under the age of five—an estimated 350,000 individuals—suffer from acute malnutrition, a condition that weakens the immune system and dramatically increases the risk of death from common illnesses like diarrhea and malaria. In some regions, the rate climbs as high as 25%. Globally, undernutrition is linked to nearly half of all deaths in children under five.

“Malnutrition is a public health emergency in Kenya,” said Laura Ferguson, director of research at USC’s Institute on Inequalities in Global Health and associate professor of population and public health sciences at the Keck School of Medicine of USC. “Children are sick unnecessarily. Children are dying unnecessarily.”

Current forecasting efforts in Kenya are largely based on expert judgment and historical knowledge—methods that struggle to anticipate new hotspots or rapid shifts.

Instead, the team’s model uses Kenya’s routine health data, collected through the District Health Information System 2 (DHIS2), alongside satellite-derived indicators like crop health and productivity to identify emerging risk areas with far greater precision.

“The best way to predict the future is to create it using available data for better planning and prepositioning in developing countries,” said Murage S.M. Kiongo, Program Officer for Monitoring and Evaluation, Division of Nutrition and Dietetics, Ministry of Health, Kenya. “Trends tell us a story. Multifaceted data sources, coupled with machine learning, offer an opportunity to improve programming on nutrition and health issues.”

The researchers have developed a prototype dashboard that visualizes regional malnutrition risk, enabling quicker, better-targeted responses to child malnutrition risks. Ferguson and Dilkina are now working with the Kenyan Ministry of Health and Amref Health Africa to integrate the model and dashboard into government systems and decision making, with the goal of creating a sustainable and regularly updated public resource.

“Most global health problems cannot be solved within the health field alone, and this is one of them,” Ferguson said. “So, we absolutely need public health experts. We need medical officials. We need nonprofits. We need engineers. If you take out any single partner, it just doesn’t work and won’t have the impact that we hope for.”

More than 125 countries currently use DHIS2, including about 80 low- and middle-income countries. That means this AI-driven framework—which relies only on existing health and satellite data—could be adapted to fight malnutrition in other countries across the globe.

“If we can do this for Kenya, we can do it for other countries,” Dilkina said. “The sky’s the limit when there is a genuine commitment to work in partnership.”