{"id":5608,"date":"2025-08-08T04:05:26","date_gmt":"2025-08-08T04:05:26","guid":{"rendered":"https:\/\/scientificworld.org\/?p=5608"},"modified":"2025-08-08T04:05:28","modified_gmt":"2025-08-08T04:05:28","slug":"ai-model-predicts-child-malnutrition-up-to-six-months-in-advance-aiding-prevention-efforts","status":"publish","type":"post","link":"https:\/\/scientificworld.org\/?p=5608","title":{"rendered":"AI Model Predicts Child Malnutrition Up to Six Months in Advance, Aiding Prevention Efforts"},"content":{"rendered":"\n<p>A groundbreaking artificial intelligence (AI) tool developed by researchers from the USC School of Advanced Computing, the Keck School of Medicine, and collaborators from the Microsoft AI for Good Lab, Amref Health Africa, and Kenya\u2019s Ministry of Health can predict acute child malnutrition in Kenya up to six months ahead of time. Published in\u00a0<a href=\"http:\/\/dx.doi.org\/10.1371\/journal.pone.0322959\"><em>PLOS One<\/em><\/a>\u00a0on May 14, 2025, this innovation provides governments and humanitarian organizations with critical lead time to deploy life-saving interventions.<\/p>\n\n\n\n<p>The machine learning model integrates clinical data from over 17,000 Kenyan health facilities with satellite data on crop health and productivity. It achieves 89% accuracy for one-month forecasts and maintains 86% accuracy over six months, outperforming traditional methods that rely solely on historical trends. Notably, the tool excels in regions where malnutrition rates fluctuate unpredictably.<\/p>\n\n\n\n<p>\u201cThis model is a game-changer,\u201d said Bistra Dilkina, co-director of the USC Center for Artificial Intelligence in Society. By analyzing complex relationships between variables, the AI provides more accurate predictions, enabling proactive measures. Girmaw Abebe Tadesse of Microsoft AI for Good Lab emphasized the tool\u2019s potential to address food insecurity exacerbated by climate change.<\/p>\n\n\n\n<p>In Kenya, 5% of children under five, approximately 350,000, suffer from acute malnutrition, with rates reaching 25% in some areas. Globally, undernutrition contributes to nearly half of all deaths in this age group. Current forecasting methods, based on expert judgment, often miss emerging hotspots. The new model leverages Kenya\u2019s District Health Information System 2 (DHIS2) and satellite data to identify at-risk regions with precision.<\/p>\n\n\n\n<p>The team has developed a prototype dashboard to visualize malnutrition risk, aiding targeted responses. Laura Ferguson of USC\u2019s Institute on Inequalities in Global Health highlighted the importance of multidisciplinary collaboration: \u201cIf you take out any single partner, it just doesn\u2019t work.\u201d The researchers are working with Kenyan authorities to integrate the tool into government systems, with potential for global adaptation in over 125 countries using DHIS2.<\/p>\n\n\n\n<p>This AI-driven framework, reliant on existing data, offers a scalable solution to combat malnutrition worldwide. As Dilkina noted, \u201cThe sky\u2019s the limit when there is a genuine commitment to work in partnerships.\u201d The study underscores the transformative potential of AI in addressing pressing public health challenges.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A groundbreaking artificial intelligence (AI) tool developed by researchers from the USC School of Advanced Computing, the Keck School of Medicine, and collaborators from the Microsoft AI for Good Lab, Amref Health Africa, and Kenya\u2019s Ministry of Health can predict acute child malnutrition in Kenya up to six months ahead of time. Published in\u00a0PLOS One\u00a0on [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1123],"tags":[702,3298,726,1566,1380,1091],"class_list":["post-5608","post","type-post","status-publish","format-standard","hentry","category-public-health","tag-ai","tag-child-malnutrition","tag-health","tag-health-medicine","tag-machine-learning","tag-public-health"],"_links":{"self":[{"href":"https:\/\/scientificworld.org\/index.php?rest_route=\/wp\/v2\/posts\/5608","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scientificworld.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scientificworld.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scientificworld.org\/index.php?rest_route=\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/scientificworld.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5608"}],"version-history":[{"count":1,"href":"https:\/\/scientificworld.org\/index.php?rest_route=\/wp\/v2\/posts\/5608\/revisions"}],"predecessor-version":[{"id":5609,"href":"https:\/\/scientificworld.org\/index.php?rest_route=\/wp\/v2\/posts\/5608\/revisions\/5609"}],"wp:attachment":[{"href":"https:\/\/scientificworld.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5608"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scientificworld.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5608"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scientificworld.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5608"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}