[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121551-en":3,"doc-seo-121551-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121551,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Predicting Risk of Inadequate Micronutrient Intake with Transferable Machine Learning Models - Research","Identifying populations at risk of inadequate micronutrient intake is essential for governments and development partners in low- and middle-income countries to support timely, evidence-based nutrition decisions. This study presents a machine learning approach that uses household dietary diversity, socioeconomic status, and climate indicators to predict risk. Case studies from Ethiopia and Nigeria show reliable prediction performance, with stable key predictors and practical model transferability across settings. The method generates geographically and socioeconomically disaggregated risk estimates for more targeted interventions.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nPredicting risk of inadequate micronutrient intake with transferable machine learning models  \nVasilikiVoukelatou1􀀍, Kevin Tang2,3, Ilaria Lauzana1, Manita Jangid2, Giulia Martini1, Saskia de Pee2,4, Frances Knight2,3 & Duccio Piovani1  \nIdentifying populations at risk of inadequate micronutrient intake is necessary for governments and development partners in low-and middle-income countries to make informed and timely decisionson nutrition-relevant policies and programmes. In this study, we propose a machine learning methodological approach using data on household dietary diversity, socioeconomic status, and climate indicators to predict the risk of inadequate micronutrient intake. Using case studies from Ethiopia and Nigeria, we demonstrate that the models effectively predict risk, with key predictors showing consistency in terms of importance and direction. We also illustrate the feasibility of transferring models between countries, offering a short-term, practical solution for contexts lacking nationally representative micronutrient data. Our results show that this machine learning methodological approach can generate geographically and socioeconomically disaggregated risk estimates that reflect expected patterns of nutritional vulnerability, supporting more targeted and data-driven nutrition interventions.  \nKeywords Nutrition, Policy, Classification, Machine learning, Data science for social good  \nMicronutrient deficiencies (MND), a form of malnutrition, affect half of all children and two thirds of women worldwide and pose a significant threat to the health, development, and economic productivity of countries and their populations1,2. Low quality, non-diverse diets provide inadequate quantities of essential micronutrients and are a direct cause of MND, particularly in low-and middle-income countries (LMICs)3,4. In response, public policy and programmes aimed at reducing the burden of MND often seek to improve micronutrient intake through vitamin and mineral fortification5 of staple foods, supplementation, dietary diversification and other food systems interventions6–9.  \nDetermining the need for and effectively designing policies and programmes to reduce the risk of inadequate micronutrient intake requires quantitative dietary intake data. These data are used by government agencies or other organizations, such as the United Nations World Food Programme (WFP), to assess the extent to which a population’s micronutrient intake meets recommended levels. Analysis of these data can also identify geographies or sub populations most vulnerable to inadequate intake, micronutrient intake gaps that need to be addressed and the contributions different interventions could have to improving intake10. Outcome-based indicators like biomarkers and anthropometry reflect nutritional status but are influenced by multiple factors beyond diet. These can include biological requirements, genetics, infection, care practices, and other determinants. This study focuses on inadequate micronutrient intake, a modifiable risk that can be directly addressed through food-based interventions.  \nDietary intake can be measured directly using individual-level dietary recall surveys and is used to estimate the risk of inadequate micronutrient intake11. Unfortunately, due to the cost and complexity of measuring dietary intake, few LMICs collect or have access to current and nationally representative dietary intake data10, 12. Alternatively, dietary intake and the risk of inadequate micronutrient intake can be estimated using the food  \n1Forecasting and Early Warning Unit, United Nations World Food Programme, Via Cesare Giulio Viola 68, Rome 00148, Italy. 2Nutrition Unit, United Nations World Food Programme, Via Cesare Giulio Viola 68, Rome 00148, Italy.  \n3Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, Keppel St, London WC1E 7HT, UK. ","cbCaitPt2f5yMY1z","https://ap.wps.com/l/cbCaitPt2f5yMY1z","pdf",2566835,1,12,"English","en",105,"# Introduction\n## Micronutrient deficiencies and their determinants\n## Data needs for assessing inadequate intake\n# Methods\n## Machine learning approach and input data\n## Data-constrained vs data-rich contexts\n# Results\n## Prediction performance in Ethiopia and Nigeria\n## Transferability of models across countries\n# Discussion\n## Implications for targeted, data-driven nutrition interventions","[{\"question\":\"Why is predicting the risk of inadequate micronutrient intake important?\",\"answer\":\"It helps governments and development partners identify vulnerable populations and micronutrient intake gaps so policies and programmes can be designed and timed appropriately in low- and middle-income countries.\"},{\"question\":\"What data inputs are used for the machine learning predictions?\",\"answer\":\"The approach uses household dietary diversity, socioeconomic status, and climate indicators to estimate the risk of inadequate micronutrient intake.\"},{\"question\":\"Can the trained models be used across countries?\",\"answer\":\"Yes. Case studies in Ethiopia and Nigeria demonstrate that models can be transferred between countries, with key predictors showing consistent importance and direction.\"}]","Predicting Risk of Inadequate Micronutrient Intake with Transferable Machine Learning Models - Research | PDF",1785736205,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-risk-of-inadequate-micronutrient-intake-with-transferable-machine-learning-models-research","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-risk-of-inadequate-micronutrient-intake-with-transferable-machine-learning-models-research/121551/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is predicting the risk of inadequate micronutrient intake important?","Question",{"text":75,"@type":76},"It helps governments and development partners identify vulnerable populations and micronutrient intake gaps so policies and programmes can be designed and timed appropriately in low- and middle-income countries.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data inputs are used for the machine learning predictions?",{"text":80,"@type":76},"The approach uses household dietary diversity, socioeconomic status, and climate indicators to estimate the risk of inadequate micronutrient intake.",{"name":82,"@type":73,"acceptedAnswer":83},"Can the trained models be used across countries?",{"text":84,"@type":76},"Yes. Case studies in Ethiopia and Nigeria demonstrate that models can be transferred between countries, with key predictors showing consistent importance and direction.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]