Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries
Global targets to reduce salt intake have been proposed, but their monitoring is challenged by the lack of population-based data on salt consumption. We developed a machine learning (ML) model to predict salt consumption at the population level based on simple predictors and applied this model to na...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2022-01-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/72930 |
| _version_ | 1797998427681849344 |
|---|---|
| author | Wilmer Cristobal Guzman-Vilca Manuel Castillo-Cara Rodrigo M Carrillo-Larco |
| author_facet | Wilmer Cristobal Guzman-Vilca Manuel Castillo-Cara Rodrigo M Carrillo-Larco |
| author_sort | Wilmer Cristobal Guzman-Vilca |
| collection | DOAJ |
| description | Global targets to reduce salt intake have been proposed, but their monitoring is challenged by the lack of population-based data on salt consumption. We developed a machine learning (ML) model to predict salt consumption at the population level based on simple predictors and applied this model to national surveys in 54 countries. We used 21 surveys with spot urine samples for the ML model derivation and validation; we developed a supervised ML regression model based on sex, age, weight, height, and systolic and diastolic blood pressure. We applied the ML model to 54 new surveys to quantify the mean salt consumption in the population. The pooled dataset in which we developed the ML model included 49,776 people. Overall, there were no substantial differences between the observed and ML-predicted mean salt intake (p<0.001). The pooled dataset where we applied the ML model included 166,677 people; the predicted mean salt consumption ranged from 6.8 g/day (95% CI: 6.8–6.8 g/day) in Eritrea to 10.0 g/day (95% CI: 9.9–10.0 g/day) in American Samoa. The countries with the highest predicted mean salt intake were in the Western Pacific. The lowest predicted intake was found in Africa. The country-specific predicted mean salt intake was within reasonable difference from the best available evidence. An ML model based on readily available predictors estimated daily salt consumption with good accuracy. This model could be used to predict mean salt consumption in the general population where urine samples are not available. |
| first_indexed | 2024-04-11T10:48:36Z |
| format | Article |
| id | doaj.art-331c44a0c055438687a8ab1d3cbfbaf4 |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-04-11T10:48:36Z |
| publishDate | 2022-01-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-331c44a0c055438687a8ab1d3cbfbaf42022-12-22T04:28:58ZengeLife Sciences Publications LtdeLife2050-084X2022-01-011110.7554/eLife.72930Development, validation, and application of a machine learning model to estimate salt consumption in 54 countriesWilmer Cristobal Guzman-Vilca0https://orcid.org/0000-0002-2194-8496Manuel Castillo-Cara1https://orcid.org/0000-0002-2990-7090Rodrigo M Carrillo-Larco2https://orcid.org/0000-0002-2090-1856School of Medicine Alberto Hurtado, Universidad Peruana Cayetano Heredia, Lima, Peru; CRONICAS Centre of Excellence in Chronic Diseases, Universidad Peruana Cayetano Heredia, Lima, Peru; Sociedad Científica de Estudiantes de Medicina Cayetano Heredia (SOCEMCH), Universidad Peruana Cayetano Heredia, Lima, PeruUniversidad de Lima, Lima, PeruCRONICAS Centre of Excellence in Chronic Diseases, Universidad Peruana Cayetano Heredia, Lima, Peru; Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, London, United KingdomGlobal targets to reduce salt intake have been proposed, but their monitoring is challenged by the lack of population-based data on salt consumption. We developed a machine learning (ML) model to predict salt consumption at the population level based on simple predictors and applied this model to national surveys in 54 countries. We used 21 surveys with spot urine samples for the ML model derivation and validation; we developed a supervised ML regression model based on sex, age, weight, height, and systolic and diastolic blood pressure. We applied the ML model to 54 new surveys to quantify the mean salt consumption in the population. The pooled dataset in which we developed the ML model included 49,776 people. Overall, there were no substantial differences between the observed and ML-predicted mean salt intake (p<0.001). The pooled dataset where we applied the ML model included 166,677 people; the predicted mean salt consumption ranged from 6.8 g/day (95% CI: 6.8–6.8 g/day) in Eritrea to 10.0 g/day (95% CI: 9.9–10.0 g/day) in American Samoa. The countries with the highest predicted mean salt intake were in the Western Pacific. The lowest predicted intake was found in Africa. The country-specific predicted mean salt intake was within reasonable difference from the best available evidence. An ML model based on readily available predictors estimated daily salt consumption with good accuracy. This model could be used to predict mean salt consumption in the general population where urine samples are not available.https://elifesciences.org/articles/72930artificial intelligencedeep learningcardio-metabolic risk factorscardiovascular healthglobal healthpopulation health |
| spellingShingle | Wilmer Cristobal Guzman-Vilca Manuel Castillo-Cara Rodrigo M Carrillo-Larco Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries eLife artificial intelligence deep learning cardio-metabolic risk factors cardiovascular health global health population health |
| title | Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries |
| title_full | Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries |
| title_fullStr | Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries |
| title_full_unstemmed | Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries |
| title_short | Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries |
| title_sort | development validation and application of a machine learning model to estimate salt consumption in 54 countries |
| topic | artificial intelligence deep learning cardio-metabolic risk factors cardiovascular health global health population health |
| url | https://elifesciences.org/articles/72930 |
| work_keys_str_mv | AT wilmercristobalguzmanvilca developmentvalidationandapplicationofamachinelearningmodeltoestimatesaltconsumptionin54countries AT manuelcastillocara developmentvalidationandapplicationofamachinelearningmodeltoestimatesaltconsumptionin54countries AT rodrigomcarrillolarco developmentvalidationandapplicationofamachinelearningmodeltoestimatesaltconsumptionin54countries |