Sex and population differences in the cardiometabolic continuum: a machine learning study using the UK Biobank and ELSA-Brasil cohorts.

BACKGROUND: The temporal relationships across cardiometabolic diseases (CMDs) were recently conceptualized as the cardiometabolic continuum (CMC), sequence of cardiovascular events that stem from gene-environmental interactions, unhealthy lifestyle influences, and metabolic diseases such as diabetes, and hypertension. While the physiological pathways linking metabolic and cardiovascular diseases have been investigated, the study of the sex and population differences in the CMC have still not been described. METHODS: We present a machine learning approach to model the CMC and investigate sex and population differences in two distinct cohorts: the UK Biobank (17,700 participants) and the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) (7162 participants). We consider the following CMDs: hypertension (Hyp), diabetes (DM), heart diseases (HD: angina, myocardial infarction, or heart failure), and stroke (STK). For the identification of the CMC patterns, individual trajectories with the time of disease occurrence were clustered using k-means. Based on clinical, sociodemographic, and lifestyle characteristics, we built multiclass random forest classifiers and used the SHAP methodology to evaluate feature importance. RESULTS: Five CMC patterns were identified across both sexes and cohorts: EarlyHyp, FirstDM, FirstHD, Healthy, and LateHyp, named according to prevalence and disease occurrence time that depicted around 95%, 78%, 75%, 88% and 99% of individuals, respectively. Within the UK Biobank, more women were classified in the Healthy cluster and more men in all others. In the EarlyHyp and LateHyp clusters, isolated hypertension occurred earlier among women. Smoking habits and education had high importance and clear directionality for both sexes. For ELSA-Brasil, more men were classified in the Healthy cluster and more women in the FirstDM. The diabetes occurrence time when followed by hypertension was lower among women. Education and ethnicity had high importance and clear directionality for women, while for men these features were smoking, alcohol, and coffee consumption. CONCLUSIONS: There are clear sex differences in the CMC that varied across the UK and Brazilian cohorts. In particular, disadvantages regarding incidence and the time to onset of diseases were more pronounced in Brazil, against woman. The results show the need to strengthen public health policies to prevent and control the time course of CMD, with an emphasis on women.

Exploring cross-country heterogeneity in the relation between female labor force participation and fertility in Latin America / Explorando a heterogeneidade entre países na relação entre participação feminina na força de trabalho e fecundidade na América Latina / Explorando la heterogeneidad entre países en la relación entre participación laboral de las mujeres y fecundidad en América Latina

Abstract In Latin America, despite an apparent convergence on the relation between female labor force participation (FLFP) and total fertility rates (TFR), there are differences between and within countries that must be considered. This paper aimed to understand the heterogeneity in the relation between the FLFP rate and the TFR in Latin American from 1990 to 2018 in order to identify cross-country patterns. Using World Bank data for the 20 countries in Latin America, clustering longitudinal data was performed, and mixed-effect models were fitted to quantify the heterogeneity. Three patterns of relationship were observed in Latin American countries: low TFR and intermediate FLFP, high TFR and high FLFP, and high TFR and low FLFP. The heterogeneity identified suggests the diversity of socio-economic and cultural factors influences the dynamics of the relation between FLFP and TFR in Latin America.

Resumo Na América Latina, apesar de uma aparente convergência na relação entre taxas de fecundidade total (TFT) e participação feminina na força de trabalho (PFFT), existem diferenças entre e dentro dos países que devem ser consideradas. Este artigo objetiva entender a heterogeneidade na relação entre a PFFT e a TFR na América Latina de 1990 a 2018, a fim de identificar padrões entre países. Usando dados do Banco Mundial para os 20 países da América Latina, dados de agrupamento longitudinal foram realizados e modelos de efeito misto foram ajustados para quantificar a heterogeneidade. Três padrões de relacionamento foram observados nos países latino-americanos: TFT baixa e PFFT intermediária; TFT alta e PFFT alta; e TFR alta e PFFT baixa. A heterogeneidade identificada sugere que a diversidade de fatores socioeconômicos e culturais influencia a dinâmica da relação entre PFFT e TFT na América Latina.

Resumen En América Latina, a pesar de una aparente convergencia en la relación entre las tasas globales de fecundidad (TGF) y la participación de femenina en la fuerza de trabajo (PFFT), hay diferencias entre y dentro de los países de la región, que deben ser consideradas. El objetivo de este trabajo es entender la heterogeneidad en la relación entre la tasa de PFFT y la TGF en América Latina desde 1990 hasta 2018, con el fin de identificar patrones entre países. Utilizando datos del Banco Mundial para los veinte países de América Latina, se agruparon datos longitudinales y se ajustaron modelos de efectos mixtos para cuantificar la heterogeneidad. Se observaron tres patrones de relación en los países de América Latina: baja TGF y PFFT intermedia; alta TGF y alta PFFT, y alta TGF y baja PFFT. La heterogeneidad identificada sugiere que la diversidad de factores socioeconómicos y culturales influye en la dinámica de la relación entre la PFFT y la TGF en América Latina.