Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evaluation of Country Dietary Habits Using Machine Learning Techniques in Relation to Deaths from COVID-19

María Teresa García-Ordás, Natalia Arias, Carmen Benavides, Oscar García-Olalla, José Alberto Benítez-Andrades

TL;DR

The paper investigates whether country-level dietary patterns influence COVID-19 mortality by integrating 94 dietary features across 170 countries. A two-step ML pipeline uses PCA to reduce features to 23 components explaining $95\%$ of variance, followed by K-Means clustering and Davies–Bouldin validation to identify 20 clusters. Results show high-mortality clusters correlate with greater intake of animal products, fats, and higher total caloric consumption ($3277.5$ Kcal/day on average) compared to lower-mortality clusters ($2764.3$ Kcal/day), with obesity emerging as a risk factor and cereals linked to lower risk. The findings suggest dietary patterns may inform risk profiling and public health strategies, though future work should incorporate race, age, and socioeconomic factors to enhance clustering reliability.

Abstract

COVID-19 disease has affected almost every country in the world. The large number of infected people and the different mortality rates between countries has given rise to many hypotheses about the key points that make the virus so lethal in some places. In this study, the eating habits of 170 countries were evaluated in order to find correlations between these habits and mortality rates caused by COVID-19 using machine learning techniques that group the countries together according to the different distribution of fat, energy, and protein across 23 different types of food, as well as the amount ingested in kilograms. Results shown how obesity and the high consumption of fats appear in countries with the highest death rates, whereas countries with a lower rate have a higher level of cereal consumption accompanied by a lower total average intake of kilocalories.

Evaluation of Country Dietary Habits Using Machine Learning Techniques in Relation to Deaths from COVID-19

TL;DR

The paper investigates whether country-level dietary patterns influence COVID-19 mortality by integrating 94 dietary features across 170 countries. A two-step ML pipeline uses PCA to reduce features to 23 components explaining of variance, followed by K-Means clustering and Davies–Bouldin validation to identify 20 clusters. Results show high-mortality clusters correlate with greater intake of animal products, fats, and higher total caloric consumption ( Kcal/day on average) compared to lower-mortality clusters ( Kcal/day), with obesity emerging as a risk factor and cereals linked to lower risk. The findings suggest dietary patterns may inform risk profiling and public health strategies, though future work should incorporate race, age, and socioeconomic factors to enhance clustering reliability.

Abstract

COVID-19 disease has affected almost every country in the world. The large number of infected people and the different mortality rates between countries has given rise to many hypotheses about the key points that make the virus so lethal in some places. In this study, the eating habits of 170 countries were evaluated in order to find correlations between these habits and mortality rates caused by COVID-19 using machine learning techniques that group the countries together according to the different distribution of fat, energy, and protein across 23 different types of food, as well as the amount ingested in kilograms. Results shown how obesity and the high consumption of fats appear in countries with the highest death rates, whereas countries with a lower rate have a higher level of cereal consumption accompanied by a lower total average intake of kilocalories.
Paper Structure (9 sections, 6 equations, 5 figures, 1 table)

This paper contains 9 sections, 6 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Principal Component Analysis (Pca)
  4. K-Means
  5. Clustering Metric: Davies--Bouldin
  6. Experiments and Results
  7. Dataset
  8. Experiments
  9. Discussion and Conclusions

Figures (5)

  • Figure S1: Study of the best number of clusters using Davies--Bouldin index.
  • Figure S2: Number of countries per cluster.
  • Figure S3: 3rd quartile % of deaths per cluster.The red part represents a high % of deaths and the green part a low one. The red circles show the groups that fall into the red area.
  • Figure S4: Mean percentage and standard deviation of consumption for different food in high and low death clusters. (a) Animal products, (b) Milk, (c) Cereals, (d) Sugar and Sweeteners, (e) Meat, and (f) Animal fats.
  • Figure S5: Obesity and undernourished diseases for high and normal death clusters.