Predicting nationwide obesity from food sales using machine learning

被引:23
作者
Dunstan, Jocelyn [1 ,2 ]
Aguirre, Marcela [2 ]
Bastias, Magdalena [2 ]
Nau, Claudia [1 ]
Glass, Thomas A. [1 ]
Tobar, Felipe [2 ]
机构
[1] Johns Hopkins Univ, Baltimore, MD 21218 USA
[2] Univ Chile, Santiago, Chile
基金
美国国家卫生研究院;
关键词
databases and data mining; food sales; machine learning; obesity; supervised learning; CONSUMPTION; DIET; CLASSIFICATION; OVERWEIGHT;
D O I
10.1177/1460458219845959
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
The obesity epidemic progresses everywhere across the globe, and implementing frequent nationwide surveys to measure the percentage of obese population is costly. Conversely, country-level food sales information can be accessed inexpensively through different suppliers on a regular basis. This study applies a methodology to predict obesity prevalence at the country-level based on national sales of a small subset of food and beverage categories. Three machine learning algorithms for nonlinear regression were implemented using purchase and obesity prevalence data from 79 countries: support vector machines, random forests and extreme gradient boosting. The proposed method was validated in terms of both the absolute prediction error and the proportion of countries for which the obesity prevalence was predicted satisfactorily. We found that the most-relevant food category to predict obesity is baked goods and flours, followed by cheese and carbonated drinks.
引用
收藏
页码:652 / 663
页数:12
相关论文
共 42 条
[1]   Integration of metabolomics, lipidomics and clinical data using a machine learning method [J].
Acharjee, Animesh ;
Ament, Zsuzsanna ;
West, James A. ;
Stanley, Elizabeth ;
Griffin, Julian L. .
BMC BIOINFORMATICS, 2016, 17
[2]   Predicted growth of world urban food waste and methane production [J].
Adhikari, Bijaya K. ;
Barrington, Suzelle ;
Martinez, Jose .
WASTE MANAGEMENT & RESEARCH, 2006, 24 (05) :421-433
[3]  
[Anonymous], 2013, BMJ BRIT MED J, DOI DOI 10.1136/BMJ.F6189
[4]  
[Anonymous], 2017, INTRO STAT LEARNING
[5]  
[Anonymous], 2006, Pattern recognition and machine learning
[6]  
[Anonymous], PASSP DAT
[7]  
[Anonymous], ONLINE J PUBLIC HLTH
[8]  
[Anonymous], SJAC ESSENTIAL MED S
[9]  
[Anonymous], 2012, LANCET, DOI DOI 10.3103/S0735272712060015
[10]   The transitional dynamics of caloric ecosystems: changes in the food supply around the world [J].
Basu, Sanjay .
CRITICAL PUBLIC HEALTH, 2015, 25 (03) :248-264