Screening high-risk clusters for developing birth defects in mothers in Shanxi Province, China: application of latent class cluster analysis

Screening high-risk population of persistent postpartum hypertension in women with preeclampsia using latent class cluster analysis

BACKGROUND

A significant proportion of women with preeclampsia (PE) exhibit persistent postpartum hypertension (PHTN) at 3 months postpartum associated with cardiovascular morbidity. This study aimed to screen patients with PE to identify the high-risk population with persistent PHTN.

METHODS

This retrospective cohort study enrolled 1,000 PE patients with complete parturient and postpartum blood pressure (BP) profiles at 3 months postpartum. The enrolled patients exhibited new-onset hypertension after 20 weeks of pregnancy, while those with PE superimposed upon chronic hypertension were excluded. Latent class cluster analysis (LCCA), a method of unsupervised learning in machine learning, was performed to ascertain maternal exposure clusters from eight variables and 35 subordinate risk factors. Logistic regression was applied to calculate odds ratios (OR) indicating the association between clusters and PHTN.

RESULTS

The 1,000 participants were classified into three exposure clusters (subpopulations with similar characteristics) according to persistent PHTN development: high-risk cluster (31.2%), medium-risk cluster (36.8%), and low-risk cluster (32.0%). Among the 1,000 PE patients, a total of 134 (13.4%) were diagnosed with persistent PHTN, while the percentages of persistent PHTN were24.68%, 10.05%, and 6.25% in the high-, medium-, and low-risk clusters, respectively. Persistent PHTN in the high-risk cluster was nearly five times higher (OR, 4.915; 95% confidence interval (CI), 2.92-8.27) and three times (OR, 2.931; 95% CI, 1.91-4.49) than in the low- and medium-risk clusters, respectively. Persistent PHTN did not differ between the medium- and low-risk clusters. Subjects in the high-risk cluster were older and showed higher BP, poorer prenatal organ function, more adverse pregnancy events, and greater medication requirement than the other two groups.

CONCLUSION

Patients with PE can be classified into high-, medium-, and low-risk clusters according to persistent PHTN severity; each cluster has cognizable clinical features. This study's findings stress the importance of controlling persistent PHTN to prevent future cardiovascular disease.

Relationship between Eating Habits, Physical Activity and Tobacco and Alcohol Use in Pregnant Women: Sociodemographic Inequalities

Pregnant women must maintain or acquire healthy habits during pregnancy to protect both their own health and their child's. Such habits include an adequate eating pattern along with good adherence to the intake of certain supplements, practice of moderate physical activity and avoiding the consumption of toxic products such as tobacco and alcohol. The objective of this study is to assess the interrelation between such habits and their association with sociodemographic variables. To such end, a cross-sectional study was conducted with a representative sample of pregnant women who attended the scheduled morphology echography consultation at the 20th gestational week in their reference public hospital in the city of Seville (Spain). Results: Younger pregnant women and with lower educational levels are the ones that present the worst eating habits and the highest smoking rate. Pregnant women with lower educational levels are the least active. Non-smoking pregnant women present better eating habits than those who smoke. Pregnant women with lower educational levels are those who accumulate more unhealthy habits during pregnancy. This should be taken into account when planning the health care provided to pregnant women and in public health intersectoral policies.

The association between awareness and behavior concerning the need for protection when using pesticide sprays and neurologic symptoms: A latent class cluster analysis

Pesticide exposure is a major health risk factor among agricultural workers, and poor protective behavior and a lack of awareness concerning the risks of pesticide use in developing countries may increase the intensity of pesticide exposure. This cross-sectional study aimed to explore the relationship between neurologic symptoms and protective behavior and awareness in relation to pesticide use in China. Latent class cluster analysis was used to categorize participants into 3 latent cluster subgroups, namely, a poor protective behavior subgroup, an excellent protective awareness and behavior subgroup, and a poor protective awareness subgroup, using a person-centered approach. Multivariate regression models were used to detect the association between the latent class cluster subgroups and self-reported neurologic symptoms. The results showed that poor protective behavior in pesticide use was an important negative predicator of neurologic symptoms such as reduced sleep quality, frequency of nightmares, debility, hypopsia, and hypomnesis. These findings suggest that targeted interventions for agricultural workers, especially local greenhouse farmers, are urgently needed to improve pesticide protection behavior.

Comparison of Self-Rated Health among Characteristic Groups of Vegetable Greenhouse Farmers Based on Exposure to Pesticide Residuals: A Latent Profile Analysis

Objective

The current study was aimed at using a latent profile analysis (LPA) model to classify greenhouse farmers into a potential cluster according to their exposure to pesticide residuals. Further, the association between self-rated health (SRH) and the cluster exposed to pesticide residual was explored.

Methods

Four hundred sixty-four farmers from vegetable greenhouses were selected, their SRH information was gathered through questionnaires from the “Self-Rated Health Measurement Scale (SRHMS)” Version 1.0, and the corresponding pesticide residuals were detected in a laboratory. The linear mixed regression model was employed for association assessment.

Results

Two latent clusters were extracted as samples, and the results showed that a high amount of pesticide residual accounted for poor physical health, but did not show statistical significance. In addition, an inverse significant association was observed between psychosocial symptoms and negative emotion and pesticide residual level. Furthermore, a diversity of significant relationship was observed in social health and its corresponding dimensions with latent cluster.

Conclusions

LPA offers a holistic and parsimonious method to identify high-risk health clusters of greenhouse workers in various health aspects and allows for a personality-targeted intervention by a local health department.

Using latent class cluster analysis to screen high risk clusters of birth defects between 2009 and 2013 in Northwest China

In the study, we aimed to explore the synergistic effects of multiple risk factors on birth defects, and examine temporal trend of the synergistic effects over time. Two cross-sectional surveys conducted in 2009 and 2013 were merged and then latent class cluster analysis and generalized linear Poisson model were used. A total of 9085 and 29094 young children born within the last three years and their mothers were enrolled in 2009 and 2013 respectively. Three latent maternal exposure clusters were determined: a high-risk, a moderate-risk, and a low-risk cluster (88.97%, 1.49%, 9.54% in 2009 and 82.42%, 3.39%, 14.19% in 2013). The synthetic effects of maternal exposure to multiple risk factors could increase the risk of overall birth defects and cardiovascular system malformation among live births, and this risk is significantly higher in high-risk cluster than that in low-risk cluster. After adjusting for confounding factors using a generalized linear Poisson model, in high-risk cluster the prevalence of nervous system malformation decreased by approximately 2.71%, and the proportion of cardiovascular system malformation rose by 0.92% from 2009 to 2013. The Chinese government should make great efforts to provide primary prevention for those on high-risk cluster as a priority target population.

Predicting congenital heart defects: A comparison of three data mining methods

Congenital heart defects (CHD) is one of the most common birth defects in China. Many studies have examined risk factors for CHD, but their predictive abilities have not been evaluated. In particular, few studies have attempted to predict risks of CHD from, necessarily unbalanced, population-based cross-sectional data. Therefore, we developed and validated machine learning models for predicting, before and during pregnancy, women’s risks of bearing children with CHD. We compared the results of these models in a large-scale, comprehensive population-based retrospective cross-sectional epidemiological survey of birth defects in six counties in Shanxi Province, China, covering 2006 to 2008. This contained 78 cases of CHD among 33831 live births. We constructed nine synthetic variables to use in the models: maternal age, annual per capita income, family history, maternal history of illness, nutrition and folic acid deficiency, maternal illness in pregnancy, medication use in pregnancy, environmental risk factors in pregnancy, and unhealthy maternal lifestyle in pregnancy. The machine learning algorithms Weighted Support Vector Machine (WSVM) and Weighted Random Forest (WRF) were trained on, and a logistic regression (Logit) was fitted to, two-thirds of the data. Their predictive abilities were then tested in the remaining data. True positive rate (TPR), true negative rate (TNR), accuracy (ACC), area under the curves (AUC), G-means, and Weighted accuracy (WTacc) were used to compare the classification performance of the models. Median values, from repeating the data partitioning 1000 times, were used in all comparisons. The TPR and TNR of the three classifiers were above 0.65 and 0.93, respectively, better than any reported in the literature. TPR, wtACC, AUC and G were highest for WSVM, showing that it performed best. All three models are precise enough to identify groups at high risk of CHD. They should all be considered for future investigations of other birth defects and diseases.