Development, validation, and application of a machine learning model to estimate salt consumption in 54 countries
Curation statements for this article:-
Curated by eLife
Evaluation Summary:
This study by Guzman-Vilca et al. developed a machine learning (ML) tool to estimate the sodium/salt intake in a pooled database of a WHO surveys entailing more than 45,000 people in low- and middle-income countries. Their ML model based on age, sex, weight, height, systolic and diastolic blood pressure values provided a reasonably accurate estimate of the salt/sodium intake in the population in such countries. While waiting for further validation using the gold standard of 24-hour urinary sodium excretion, as reference, this tool can be important for estimating sodium consumption in low-mid income countries, which cannot afford measurements of sodium in the urine.
(This preprint has been reviewed by eLife. We include the public reviews from the reviewers here; the authors also receive private feedback with suggested changes to the manuscript. Reviewer #1 agreed to share their name with the authors.)
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (eLife)
Abstract
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.
Article activity feed
-
-
Evaluation Summary:
This study by Guzman-Vilca et al. developed a machine learning (ML) tool to estimate the sodium/salt intake in a pooled database of a WHO surveys entailing more than 45,000 people in low- and middle-income countries. Their ML model based on age, sex, weight, height, systolic and diastolic blood pressure values provided a reasonably accurate estimate of the salt/sodium intake in the population in such countries. While waiting for further validation using the gold standard of 24-hour urinary sodium excretion, as reference, this tool can be important for estimating sodium consumption in low-mid income countries, which cannot afford measurements of sodium in the urine.
(This preprint has been reviewed by eLife. We include the public reviews from the reviewers here; the authors also receive private feedback with suggested …
Evaluation Summary:
This study by Guzman-Vilca et al. developed a machine learning (ML) tool to estimate the sodium/salt intake in a pooled database of a WHO surveys entailing more than 45,000 people in low- and middle-income countries. Their ML model based on age, sex, weight, height, systolic and diastolic blood pressure values provided a reasonably accurate estimate of the salt/sodium intake in the population in such countries. While waiting for further validation using the gold standard of 24-hour urinary sodium excretion, as reference, this tool can be important for estimating sodium consumption in low-mid income countries, which cannot afford measurements of sodium in the urine.
(This preprint has been reviewed by eLife. We include the public reviews from the reviewers here; the authors also receive private feedback with suggested changes to the manuscript. Reviewer #1 agreed to share their name with the authors.)
-
Reviewer #1 (Public Review):
This is an interesting study that made an attempt to estimate salt consumption in the population of the low income countries by using artificial intelligence to obviate to the lack of actual measurements of sodium in a 24 hour urine collection or in a spot urinary sample. As this is a general problem the results are important.
-
Reviewer #2 (Public Review):
This study by Guzman-Vilca et al. provides a novel machine learning based approach to estimate the sodium/salt intake. By pooling 19 WHO STEPS surveys that included more than 45,000 people in the low- and middle-income countries (LMICs), the Authors trained and tested a supervised ML model based on routinely available parameters as ages, sex, weight, height, systolic and diastolic blood pressure values, to estimate the salt/sodium intake in the population. They also applied the model to other 49 surveys for assessing salt intake. No significant differences were found between the observed and predicted values, however with relevant differences across countries.
Strengths:
The major strength is the development of a tool for estimating the sodium intake, which could be applied in each country, particularly in …Reviewer #2 (Public Review):
This study by Guzman-Vilca et al. provides a novel machine learning based approach to estimate the sodium/salt intake. By pooling 19 WHO STEPS surveys that included more than 45,000 people in the low- and middle-income countries (LMICs), the Authors trained and tested a supervised ML model based on routinely available parameters as ages, sex, weight, height, systolic and diastolic blood pressure values, to estimate the salt/sodium intake in the population. They also applied the model to other 49 surveys for assessing salt intake. No significant differences were found between the observed and predicted values, however with relevant differences across countries.
Strengths:
The major strength is the development of a tool for estimating the sodium intake, which could be applied in each country, particularly in those where it is difficult to collect urine specimens.Weaknesses:
A methodological limitation is the use of 'golden standard' methods (spot urine samples), not of a gold standard method as reference (i.e. 24-hour urine sample), as recommended by STARD.Another weakness is the lack of preliminary evaluation of the quality of the survey considered for the machine learning training and validation, and also for salt prediction using a validated scoring system.
-
