Data-driven risk stratification for preterm birth in Brazil: a population-based study to develop of a machine learning risk assessment approach

Discovering Subgroups of Children With High Mortality in Urban Guinea-Bissau: Exploratory and Validation Cohort Study

BACKGROUND

The decline in global child mortality is an important public health achievement, yet child mortality remains disproportionally high in many low-income countries like Guinea-Bissau. The persisting high mortality rates necessitate targeted research to identify vulnerable subgroups of children and formulate effective interventions.

OBJECTIVE

This study aimed to discover subgroups of children at an elevated risk of mortality in the urban setting of Bissau, Guinea-Bissau, West Africa. By identifying these groups, we intend to provide a foundation for developing targeted health interventions and inform public health policy.

METHODS

We used data from the health and demographic surveillance site, Bandim Health Project, covering 2003 to 2019. We identified baseline variables recorded before children reached the age of 6 weeks. The focus was on determining factors consistently linked with increased mortality up to the age of 3 years. Our multifaceted methodological approach incorporated spatial analysis for visualizing geographical variations in mortality risk, causally adjusted regression analysis to single out specific risk factors, and machine learning techniques for identifying clusters of multifactorial risk factors. To ensure robustness and validity, we divided the data set temporally, assessing the persistence of identified subgroups over different periods. The reassessment of mortality risk used the targeted maximum likelihood estimation (TMLE) method to achieve more robust causal modeling.

RESULTS

We analyzed data from 21,005 children. The mortality risk (6 weeks to 3 years of age) was 5.2% (95% CI 4.8%-5.6%) for children born between 2003 and 2011, and 2.9% (95% CI 2.5%-3.3%) for children born between 2012 and 2016. Our findings revealed 3 distinct high-risk subgroups with notably higher mortality rates, children residing in a specific urban area (adjusted mortality risk difference of 3.4%, 95% CI 0.3%-6.5%), children born to mothers with no prenatal consultations (adjusted mortality risk difference of 5.8%, 95% CI 2.6%-8.9%), and children from polygamous families born during the dry season (adjusted mortality risk difference of 1.7%, 95% CI 0.4%-2.9%). These subgroups, though small, showed a consistent pattern of higher mortality risk over time. Common social and economic factors were linked to a larger share of the total child deaths.

CONCLUSIONS

The study's results underscore the need for targeted interventions to address the specific risks faced by these identified high-risk subgroups. These interventions should be designed to work to complement broader public health strategies, creating a comprehensive approach to reducing child mortality. We suggest future research that focuses on developing, testing, and comparing targeted intervention strategies unraveling the proposed hypotheses found in this study. The ultimate aim is to optimize health outcomes for all children in high-mortality settings, leveraging a strategic mix of targeted and general health interventions to address the varied needs of different child subgroups.

Prediction of deciduous teeth eruption in Brazilian children: A cross-sectional study nested in a prospective birth cohort (BRISA)

BACKGROUND

Dental eruption is part of a set of children´s somatic growth phenomena. The worldwide accepted human dental eruption chronology is still based on a small sample of European children. However, evidence points to some population variations with the eruption at least two months later in low-income countries, and local standards may be useful. So, this study aimed to predict deciduous teeth eruption from 12 months of age in a Brazilian infant population.

METHODS

We developed a cross-sectional study nested in four prospective cohorts - the Brazilian Ribeirão Preto and São Luís Cohort Study (BRISA) - in a sample of 3,733 children aged 12 to 36 months old, corrected by gestational age. We made a reference curve with the number of teeth erupted by age using the Generalized Additive Models for location, scale, and shape (GAMLSS) technique. The explanatory variable was the corrected children´s age. The dependent variable was the number of erupted teeth, by gender, evaluated according to some different outcome distributional forms. The generalized Akaike information criterion (GAIC) and the model residuals were used as the model selection criterion.

RESULTS

The Box-Cox Power Exponential method was the GAMLSS model with better-fit indexes. Our estimation curve was able to predict the number of erupted deciduous teeth by age, similar to the real values, in addition to describing the evolution of children's development, with comparative patterns. There was no difference in the mean number of erupted teeth between the sexes. According to the reference curve, at 12 months old, 25% of children had four erupted teeth or less, while 75% had seven or fewer and 95% had 11 or fewer. At 24 months old, 5% had less than 12, and 75% had 18 or more. At 36 months old, around 50% of the population had deciduous dentition completed (20 teeth).

CONCLUSION

The adjusted age was an important predictor of the number of erupted deciduous teeth. This outcome can be a variable incorporated into children's growth and development curves, such as weight and height curves for age to help dentists and physicians in the monitoring the children's health.

PredictPTB: an interpretable preterm birth prediction model using attention-based recurrent neural networks

BACKGROUND

Early identification of pregnant women at risk for preterm birth (PTB), a major cause of infant mortality and morbidity, has a significant potential to improve prenatal care. However, we lack effective predictive models which can accurately forecast PTB and complement these predictions with appropriate interpretations for clinicians. In this work, we introduce a clinical prediction model (PredictPTB) which combines variables (medical codes) readily accessible through electronic health record (EHR) to accurately predict the risk of preterm birth at 1, 3, 6, and 9 months prior to delivery.

METHODS

The architecture of PredictPTB employs recurrent neural networks (RNNs) to model the longitudinal patient's EHR visits and exploits a single code-level attention mechanism to improve the predictive performance, while providing temporal code-level and visit-level explanations for the prediction results. We compare the performance of different combinations of prediction time-points, data modalities, and data windows. We also present a case-study of our model's interpretability illustrating how clinicians can gain some transparency into the predictions.

RESULTS

Leveraging a large cohort of 222,436 deliveries, comprising a total of 27,100 unique clinical concepts, our model was able to predict preterm birth with an ROC-AUC of 0.82, 0.79, 0.78, and PR-AUC of 0.40, 0.31, 0.24, at 1, 3, and 6 months prior to delivery, respectively. Results also confirm that observational data modalities (such as diagnoses) are more predictive for preterm birth than interventional data modalities (e.g., medications and procedures).

CONCLUSIONS

Our results demonstrate that PredictPTB can be utilized to achieve accurate and scalable predictions for preterm birth, complemented by explanations that directly highlight evidence in the patient's EHR timeline.