The impact that Non-Communicable Diseases (NCDs) have on the health status of the population has generated the need for an in-depth analysis of health habits and NCDs. In addition to its significant impact on population health, this phenomenon also translates into substantial economic consequences for countries. This study delves into the analysis of the relationship between health habits and NCDs among the economically active population of Mexico. Through a hybrid approach that integrates the use of machine learning (ML) models and a structural equation model (SEM), we seek to quantify the direct and indirect causal effects between health habits and NCDs. For this study, information from the 2022 National Health and Nutrition Survey carried out in Mexico for the working-age population is used. According to the results obtained in the first stage of analysis using ML, the most relevant variables (health habits) that impact the probability of individuals presenting with NCDs were identified (random forest precision of 78.66% and Lasso with 71.27%). The second stage of analysis through SEM using the most relevant variables, which were selected through ML, allowed us to measure the direct and indirect causal effect of health habits on NCDs. The SEM model was statistically significant (Chi-square: 449.186; p-value = 0.0000) and revealed that negative health habits, such as a poor diet, physical inactivity, smoking and alcohol consumption, significantly increase the risk of NCDs in the working-age population in Mexico (0.23), while vigorous physical activity and salary has a negative impact (−0.17 and −0.23, respectively) on the presence of NCDs. This study highlights the ability of machine learning and SEM approaches to model the impact of health habits on NCDs for the economically active population in Mexico.

INTRODUCTION: Noncommunicable diseases (NCD), such as cardiovascular, oncological, respiratory diseases and diabetes mellitus, remain the leading cause of mortality worldwide. These diseases are associated with factors such as lack of physical activity, poor diet, smoking and excessive alcohol consumption. The economic and social cost of NCD in developed countries is considerable. In addition to the effects on the quality of life and health of individuals, these diseases generate a significant financial burden on health systems and the economy in general. The main causes of mortality together with an analysis of mathematical models, can provide fundamental information to monitor trends in the health outcomes, recognize the pattern of diseases that affect mortality and disability, identify emerging health challenges, evaluate the effectiveness of interventions and aid in health decision-making.OBJECTIVES: To evaluate the relationship of a selected set of economic, dietary health risk factors of the economically active population in 13 developing countries for the year 2019 in NCD. Apply a dimension reduction method to detect cross-sectional variability in the selected countries, carry out a behavioral analysis of the underlying variables, identify patterns and generate indices for monitoring related factors of NCD.METHODS: A database was built for the 2019 period of 13 developing countries including 76 variables, considering economic, food and lifestyle indicators. The principal components method was used to create new dimensions to group relevant information from all the variables used and characterize the diseases in developing countries for 4 selected NCD: cardiovascular disease, chronic respiratory disease, neoplasia, and diabetes mellitus. NCD monitoring indices were created considering an index of diet, economic and factors that affect the mortality. Using the generated indices, a cluster model was applied to group countries with similar characteristics according to the information analysed for each index.RESULTS: Some relevant characteristics were identified in the countries analyzed, as well as interesting patterns among the factors related to NCD. The countries could be grouped considering their economic and nutritional behavior. It was observed that Latin American countries and Poland behave similarly, just as Asian countries show a similarity in eating behavior. The economic indicators of investment in health, as well as hours worked, behave in a similar way. It was identified that there are certain foods that have a similar behavior both in their consumption and in how they affect NCD. Thanks to the elaboration of the indices, it was observed that the countries of the Middle East and North Africa have a better food balance, but not the countries of Latin America.CONCLUSION: The application of a dimensionality reduction method and cluster analysis out of quantitative methods made it possible to characterize the behavior of a set of variables that impact NCD, as well as to synthesize this information into specific indices by category of analysis. Strategies focused on improving NCD indicators can have a greater impact by identifying similar behavior profiles among developing countries, in the same way, joint policies could be designed to address NCD through specific actions by dimension of analysis and extend these policies to countries with similar profiles.