AI Tool Forecasts Acute Child Malnutrition Up to Six Months Ahead

A new AI tool developed by researchers from the University of Southern California, Microsoft’s AI for Good Lab, and Kenya’s Ministry of Health predicts acute child malnutrition up to six months in advance, aiming to address the serious public health issue in Kenya, where 5% of children are acutely malnourished. The tool utilizes a machine learning model that integrates clinical health data from over 17,000 facilities and satellite imagery, achieving 89% accuracy in one-month predictions and 86% over six months. This advancement allows for the identification of areas at risk of malnutrition, facilitating effective prevention and treatment strategies. Researchers aspire to adapt this tool for use in 125 countries where malnutrition is prevalent. To enhance its impact, experts emphasize the need for cross-sector collaboration and ongoing investment in digital health infrastructure. Despite its promise, some caution that the quality of DHIS2 data poses challenges for accurate forecasting.

Source link