{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:46:58Z","timestamp":1793321218867,"version":"4.5.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"Background<\/jats:title>Mexico has one of the highest global incidences of paediatric overweight and obesity. Public health interventions have shown only moderate success, possibly from relying on knowledge extracted using limited types of statistical data analysis methods.<\/jats:p><\/jats:sec>Purpose<\/jats:title>To explore if multimodal machine learning can enhance identifying predictive features from obesogenic environments and investigating complex disease or social patterns, using the Mexican National Health and Nutrition Survey.<\/jats:p><\/jats:sec>Methods<\/jats:title>We grouped features into five data modalities corresponding to paediatric population exogenous factors, in two multimodal machine learning pipelines, against a unimodal early fusion baseline. The supervised pipeline employed four methods: Linear classifier with Elastic Net regularisation, k-Nearest Neighbour, Decision Tree, and Random Forest. The unsupervised pipeline used traditional methods with k-Means and hierarchical clustering, with the optimal number of clusters calculated to be k<\/jats:italic> = 2.<\/jats:p><\/jats:sec>Results<\/jats:title>The decision tree classifier in the supervised early fusion approach produced the best quantitative results. The top five most important features for classifying child or adolescent health were measures of an adult in the household, selected at random: BMI, obesity diagnosis, being single, seeking care at private healthcare, and having paid TV in the home. Unsupervised learning approaches varied in the optimal number of clusters but agreed on the importance of home environment features when analysing inter-cluster patterns. Main findings from this study differed from previous studies using only traditional statistical methods on the same database. Notably, the BMI of a randomised adult within the household emerged as the most important feature, rather than maternal BMI, as reported in previous literature where unwanted cultural bias went undetected.<\/jats:p><\/jats:sec>Conclusion<\/jats:title>Our general conclusion is that multimodal machine learning is a promising approach for comprehensively analysing obesogenic environments. The modalities allowed for a multimodal approach designed to critically analyse data signal strength and reveal sources of unwanted bias. In particular, it may aid in developing more effective public health policies to address the ongoing paediatric obesity epidemic in Mexico.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpubh.2024.1369041","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T06:52:13Z","timestamp":1736232733000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multimodal machine learning for analysing multifactorial causes of disease\u2014The case of childhood overweight and obesity in Mexico"],"prefix":"10.3389","volume":"12","author":[{"given":"Rosario","family":"Silva Sepulveda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magnus","family":"Boman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"key":"B1","volume-title":"Gu\u00eda de Evidencias y Recomendaciones: Gu\u00eda de Pr\u00e1ctica Cl\u00ednica: Prevenci\u00f3n y diagn\u00f3stico de sobrepeso y obesidad en ni\u00f1os y adolescents","author":"Arriaga-C\u00e1zares","year":"2018"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e12636","DOI":"10.1111\/ijpo.12636","article-title":"Body weight impact of the sugar-sweetened beverages tax in Mexican children: a modeling study","volume":"15","author":"Torres-\u00c1lvarez","year":"2020","journal-title":"Pediatr Obes"},{"key":"B3","volume-title":"Report of the Commission on Ending Childhood Obesity","year":"2016"},{"key":"B4","doi-asserted-by":"publisher","first-page":"187","DOI":"10.4103\/2249-4863.154628","article-title":"Childhood obesity: causes and consequences","volume":"4","author":"Sahoo","year":"2015","journal-title":"J Fam Med Prim Care"},{"key":"B5","volume-title":"The heavy burden of obesity: The Economics of Prevention","author":"Cecchini","year":"2019"},{"key":"B6","volume-title":"Global nutrition targets 2025: childhood overweight policy brief","year":"2014"},{"key":"B7","unstructured":"Obesity and overweight\n \n 2021"},{"key":"B8","unstructured":"Shamah-Levy\n T\n \n \n Vielma-Orozco\n E\n \n \n Heredia-Hern\u00e1ndez\n O\n \n \n Romero-Mart\u00ednez\n M\n \n \n Mojica-Cuevas\n J\n \n \n Cuevas-Nasu\n L\n \n \n Encuesta Nacional de Salud y Nutrici\u00f3n 2018-19: Resultados Nacionales\n \n 2020"},{"key":"B9","volume-title":"Encuesta Nacional de Salud y Nutrici\u00f3n 2021 sobre COVID-19. Resultados nacionales","author":"Shamah-Levy","year":"2022"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2055102919849406","DOI":"10.1177\/2055102919849406","article-title":"Childhood obesity in Mexico: a critical analysis of the environmental factors, behaviours and discourses contributing to the epidemic","volume":"6","author":"Turnbull","year":"2019","journal-title":"Health Psychol Open"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.3390\/nu11081727","article-title":"The Mexican national health and nutrition survey as a basis for public policy planning: overweight and obesity","volume":"11","author":"Shamah-Levy","year":"2019","journal-title":"Nutrients"},{"key":"B12","unstructured":"London\n Mexico: Policies, Interventions and Actions\n \n 2022"},{"key":"B13","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1111\/obr.12667","article-title":"A review of machine learning in obesity","volume":"19","author":"DeGregory","year":"2018","journal-title":"Obes Rev"},{"key":"B14","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/ANNES.1995.499512","article-title":"Application of artificial neural networks for childhood obesity prediction","volume-title":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","author":"Novak","year":"1995"},{"key":"B15","doi-asserted-by":"publisher","first-page":"2466","DOI":"10.3390\/nu12082466","article-title":"Machine learning models to predict childhood and adolescent obesity: a review","volume":"12","author":"Colmenarejo","year":"2020","journal-title":"Nutrients"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e233","DOI":"10.3109\/17477166.2010.545410","article-title":"The relative importance of predictors of body mass index change, overweight and obesity in adolescent girls","volume":"6","author":"Rehkopf","year":"2011","journal-title":"Int J Pediatr Obes"},{"key":"B17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/ICTAI.2017.00014","article-title":"Identifying discriminative attributes to gain insights regarding child obesity in hispanic preschoolers using machine learning techniques","volume-title":"2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI)","author":"Wiechmann","year":"2017"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4684","DOI":"10.3390\/ijerph16234684","article-title":"Predicting factors affecting adolescent obesity using general Bayesian network and what-if analysis","volume":"16","author":"Kim","year":"2019","journal-title":"Int J Environ Res Public Health"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-020-01538-5","article-title":"Obesogenic environments and obesity: a comment on \u2018Are environmental area characteristics at birth associated with overweight and obesity in school-aged children? Findings from the SLOPE (Studying Lifecourse Obesity PrEdictors) population-based cohort in the south of England'","volume":"18","author":"Hobbs","year":"2020","journal-title":"BMC Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e13158","DOI":"10.1111\/obr.13158","article-title":"Obesogenic environment and childhood obesity","volume":"22","author":"Jia","year":"2021","journal-title":"Obes Rev"},{"key":"B21","doi-asserted-by":"publisher","first-page":"vdac031","DOI":"10.1093\/noajnl\/vdac031","article-title":"Utility of multimodality molecular profiling for pediatric patients with central nervous system tumors","volume":"4","author":"Rajappa","year":"2022","journal-title":"Neurooncol Adv"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1109\/JPROC.2015.2460697","article-title":"Multimodal data fusion: an overview of methods, challenges, and prospects","volume":"103","author":"Lahat","year":"2015","journal-title":"Proc IEEE"},{"key":"B23","doi-asserted-by":"publisher","first-page":"248","DOI":"10.3390\/genes14020248","article-title":"Omics data preprocessing for machine learning: a case study in childhood obesity","volume":"14","author":"Torres-Martos","year":"2023","journal-title":"Genes"},{"key":"B24","doi-asserted-by":"publisher","first-page":"e804","DOI":"10.7717\/peerj-cs.804","article-title":"Comparing supervised and unsupervised approaches to multimodal emotion recognition","volume":"7","author":"Carbonell","year":"2021","journal-title":"PeerJ Comput Sci"},{"key":"B25","doi-asserted-by":"publisher","first-page":"8036","DOI":"10.1038\/s41598-024-58527-4","article-title":"Refining outcome prediction after traumatic brain injury with machine learning algorithms","volume":"14","author":"Bark","year":"2024","journal-title":"Sci Rep"},{"key":"B26","volume-title":"Computation of centiles and z-scores for height-for-age, weight-for-age and BMI-for-age","year":"2007"},{"key":"B27","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.jbmt.2017.04.010","article-title":"Body composition estimation in children and adolescents by bioelectrical impedance analysis: a systematic review","volume":"22","author":"de Castro","year":"2018","journal-title":"J Bodyw Mov Ther"},{"key":"B28","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1201\/9781315152950-2","article-title":"World Health Organization child growth standards","volume-title":"The Biology of the First 1,000 Days","author":"De Onis","year":"2017"},{"key":"B29","unstructured":"BMI-for-age (5-19 years)\n \n 2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"660","DOI":"10.2471\/BLT.07.043497","article-title":"Development of a WHO growth reference for school-aged children and adolescents","volume":"85","author":"Onis","year":"2007","journal-title":"Bull World Health Organ"},{"key":"B31","volume-title":"Sampling Techniques","author":"Cochran","year":"1977"},{"key":"B32","first-page":"270","article-title":"Dietary patterns are associated with overweight and obesity in Mexican school-age children","volume":"61","author":"Rodr\u00edguez-Ram\u00edrez","year":"2011","journal-title":"Arch Latinoam Nutr"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2753","DOI":"10.3390\/nu11112753","article-title":"Dietary patterns and the double burden of malnutrition in Mexican adolescents: results from ENSANUT-2006","volume":"11","author":"Z\u00e1rate-Ortiz","year":"2019","journal-title":"Nutrients"},{"key":"B34","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1017\/S1368980017003299","article-title":"Sociodemographic factors are associated with dietary patterns in Mexican schoolchildren","volume":"21","author":"Garc\u00eda-Ch\u00e1vez","year":"2018","journal-title":"Public Health Nutr"},{"key":"B35","doi-asserted-by":"publisher","first-page":"120","DOI":"10.11114\/ijsss.v7i3.4223","article-title":"Micro, meso and macro levels of social analysis","volume":"7","author":"Serpa","year":"2019","journal-title":"Int'l J Soc Sci Stud"},{"key":"B36","volume-title":"Hands-On Machine Learning with Scikit-Learn and TensorFlow","author":"G\u00e9ron","year":"2017"},{"key":"B37","volume-title":"Data Science for Business","author":"Fawcett","year":"2013"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv:1802.03426","article-title":"Umap: uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Cali\u0144ski","year":"1974","journal-title":"Commun Stat-Theory Methods"},{"key":"B40","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J Comput Appl Math"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e34492","DOI":"10.2196\/34492","article-title":"Traditional machine learning models and bidirectional encoder representations from transformer (BERT)-based automatic classification of tweets about eating disorders: algorithm development and validation study","volume":"10","author":"Ben\u00edtez-Andrades","year":"2022","journal-title":"JMIR Med Inf"},{"key":"B42","doi-asserted-by":"publisher","first-page":"e014371","DOI":"10.1136\/bmjopen-2016-014371","article-title":"Food insecurity and maternal-child nutritional status in Mexico: cross-sectional analysis of the National Health and Nutrition Survey 2012","volume":"7","author":"Shamah-Levy","year":"2017","journal-title":"BMJ Open"},{"key":"B43","doi-asserted-by":"publisher","first-page":"852","DOI":"10.21149\/10585","article-title":"Overweight and obesity in Mexican vulnerable population results of Ensanut 100k","volume":"61","author":"Shamah-Levy","year":"2020","journal-title":"Salud P\u00fablica M\u00e9x"},{"key":"B44","doi-asserted-by":"publisher","first-page":"29625","DOI":"10.3402\/gha.v9.29625","article-title":"Obesity-promoting factors in Mexican children and adolescents: challenges and opportunities","volume":"9","author":"Aceves-Martins","year":"2016","journal-title":"Glob Health Action"},{"key":"B45","doi-asserted-by":"publisher","first-page":"725","DOI":"10.21149\/11552","article-title":"Prevalence and susceptibility to obesity in a national sample of school-age children and adolescents in Mexico","volume":"62","author":"Shamah-Levy","year":"2020","journal-title":"Salud P\u00fablica M\u00e9xico"},{"key":"B46","doi-asserted-by":"publisher","first-page":"125","DOI":"10.21149\/10388","article-title":"Risk factors associated with overweight and obesity among female Mexican teenagers","volume":"62","author":"Medina-Zacar\u00edas","year":"2020","journal-title":"Salud P\u00fablica M\u00e9xico"},{"key":"B47","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.jand.2021.08.105","article-title":"Price trends of healthy and less healthy foods and beverages in Mexico from 2011-2018","volume":"122","author":"Batis","year":"2022","journal-title":"J Acad Nutr Diet"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/GMEPE-PAHCE.2017.7972105","article-title":"Feasibility of a screening tool for obesity diagnosis in Mexican children from a vulnerable community of Me'Phaa ethnicity in the State of Guerrero, Mexico","author":"R\u00edos-Juli\u00e1n","year":"2017","journal-title":"2017 Global Medical Engineering Physics Exchanges\/Pan American Health Care Exchanges (GMEPE\/PAHCE)"},{"key":"B49","doi-asserted-by":"publisher","first-page":"e0215571","DOI":"10.1371\/journal.pone.0215571","article-title":"Predicting childhood obesity using electronic health records and publicly available data","volume":"14","author":"Hammond","year":"2019","journal-title":"PLoS ONE"},{"key":"B50","doi-asserted-by":"publisher","first-page":"917","DOI":"10.21149\/11095","article-title":"Encuesta Nacional de Salud y Nutrici\u00f3n (Ensanut 2018): metodolog\u00eda y perspectivas","volume":"61","author":"Romero-Mart\u00ednez","year":"2019","journal-title":"Salud P\u00fablica M\u00e9xico"},{"key":"B51","doi-asserted-by":"publisher","first-page":"591696","DOI":"10.3389\/fpubh.2020.591696","article-title":"Potential impact of the nonessential energy-dense foods tax on the prevalence of overweight and obesity in children: a modeling study","volume":"8","author":"Illescas-Z\u00e1rate","year":"2021","journal-title":"Front Public Health"},{"key":"B52","doi-asserted-by":"publisher","first-page":"e12664","DOI":"10.1111\/mcn.12664","article-title":"Dietary energy density is associated with body mass index-for-age in Mexican adolescents","volume":"15","author":"Arango-Angarita","year":"2019","journal-title":"Matern Child Nutr"},{"key":"B53","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1111\/ijpo.12234","article-title":"Intakes and sources of total and added sugars among 4 to 13-year-old children in China, Mexico and the United States","volume":"13","author":"Afeiche","year":"2018","journal-title":"Pediatr Obes"},{"key":"B54","doi-asserted-by":"publisher","first-page":"e12838","DOI":"10.1111\/ijpo.12838","article-title":"Is store density associated with sugar-sweetened beverages consumption and overweight or obesity in Mexican adolescents?","volume":"17","author":"Arango-Angarita","year":"2022","journal-title":"Pediatr Obes"},{"key":"B55","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1210\/jc.2016-2573","article-title":"Pediatric obesity\u2013assessment, treatment, and prevention: an Endocrine Society clinical practice guideline","volume":"102","author":"Styne","year":"2017","journal-title":"J Clin Endocrinol Metab"},{"key":"B56","doi-asserted-by":"publisher","first-page":"104","DOI":"10.24875\/BMHIM.M18000015","article-title":"Maternal employment and Mexican school-age children overweight in 2012: the importance of households features","volume":"75","author":"Espinosa","year":"2018","journal-title":"Bol Med Hosp Infant Mex"},{"key":"B57","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.acap.2021.05.020","article-title":"Grandparent coresidence and risk of early child overweight and obesity in low-income, hispanic families in New York City","volume":"22","author":"Katzow","year":"2022","journal-title":"Acad Pediatr"},{"key":"B58","first-page":"128","article-title":"Cultural considerations for treatment of childhood obesity","volume":"7","author":"Davis","year":"2000","journal-title":"J Cult Divers"},{"key":"B59","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/10693971211021558","article-title":"Cross-national comparison of breastfeeding, malnutrition and associated risk factors among Mexican-origin children living in Mexico and the US","volume":"55","author":"Campos","year":"2021","journal-title":"Cross-Cult Res"},{"key":"B60","doi-asserted-by":"publisher","first-page":"85","DOI":"10.12873\/383caballero","article-title":"Evaluaci\u00f3n de la calidad nutricional del refrigerio y estado nutricio de una poblaci\u00f3n de estudiantes de primaria de Veracruz, M\u00e9xico","volume":"38","author":"Cerd\u00e1n","year":"2018","journal-title":"Nutr Cl"},{"key":"B61","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1377\/hlthaff.2018.05469","article-title":"Cost-effectiveness of the sugar-sweetened beverage excise tax in Mexico","volume":"38","author":"Basto-Abreu","year":"2019","journal-title":"Health Aff"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2024.1369041\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T06:52:23Z","timestamp":1736232743000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2024.1369041\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,7]]},"references-count":61,"alternative-id":["10.3389\/fpubh.2024.1369041"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2024.1369041","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,7]]},"article-number":"1369041"}}