Global Epidemiology最新文献

Background

Methods

Results

Conclusions

Background

Objectives

Methods

Results

Conclusions

Objectives

Study design and methods

Results

Discussion

Background

Fiji is a Pacific Island nation with the predominant ethnic groups indigenous Fijians (iTaukei) (62 %) and Fijians of Indian descent (31 %). This study reports on the effect of a Parental Assistance Payment Program (PAPP) tied to on-time birth registration, available in Fiji from August 2018 to July 2020.

Methods

Unit record birth registration data (n = 117,829) for children born during 2016–22 were used to calculate mean birth-to-registration intervals and the likelihood of on-time birth registration (within 365 days) before the PAPP (January 2016–July 2018) compared to during the PAPP (August 2018–July 2020), by population disaggregations (sex, ethnicity, age, marital status).

Results

During the PAPP, mean birth-to-registration intervals declined sharply by 81 %, from 665 days (95 %CI: 658–671) to 124 days (121–127). The largest declines were among i-Taukei children (803 to 139 days, 83 %) compared to non-iTaukei (283 to 76 days, 73 %); mothers aged 10–19 years (880 to 134 days, 85 %) compared to ≥20 years (653 to 123 days, 81 %); and single mothers (983 to 145 days, 85 %) compared to married mothers (570 to 115 days, 80 %). On-time birth registration increased from 57 % to 93 %, and the adjusted hazard ratio showed children born during the PAPP were 2.3 times more likely (95 %CI: 2.2–2.4) to have their birth registered on-time compared to children born before the PAPP. When the PAPP was discontinued in August 2020, the birth-to-registration interval increased sharply in all population groups.

Conclusions

During the two-year period the PAPP was available, it was highly effective at improving the timeliness of birth registration, particularly among iTaukei children, young mothers, and single mothers. After the PAPP was discontinued, the timeliness of birth registration deteriorated sharply. Longer post-PAPP follow-up time (≠5 years) is required to determine whether the timeliness of birth registration has deteriorated to levels similar to those during the pre-PAPP period.

Objective

The successful implementation and interpretation of machine learning (ML) models in epidemiological studies can be challenging without an extensive programming background. We provide a didactic example of machine learning for risk prediction in this study by determining whether early life factors could be useful for predicting adolescent psychopathology.

Methods

In total, 9643 adolescents ages 9–10 from the Adolescent Brain and Cognitive Development (ABCD) Study were included in ML analysis to predict high Child Behavior Checklist (CBCL) scores (i.e., t-scores ≥ 60). ML models were constructed using a series of predictor combinations (prenatal, family history, sociodemographic) across 5 different algorithms. We assessed ML performance through sensitivity, specificity, F1-score, and area under the curve (AUC) metrics.

Results

A total of 1267 adolescents (13.1 %) were found to have high CBCL scores. The best performing algorithms were elastic net and gradient boosted trees. The best performing elastic net models included prenatal and family history factors (Sensitivity 0.654, Specificity 0.713; AUC 0.742, F1-score 0.401) and prenatal, family, history, and sociodemographic factors (Sensitivity 0.668, Specificity 0.704; AUC 0.745, F1-score 0.402). Across all 5 ML algorithms, family history factors (e.g., either parent had nervous breakdowns, trouble holding jobs/fights/police encounters, and counseling for mental issues) and sociodemographic covariates (e.g., maternal age, child's sex, caregiver income and caregiver education) tended to be better predictors of adolescent psychopathology. The most important prenatal predictors were unplanned pregnancy, birth complications, and pregnancy complications.

Conclusion

Our results suggest that inclusion of prenatal, family history, and sociodemographic factors in ML models can generate moderately accurate predictions of adolescent psychopathology. Issues associated with model overfitting, hyperparameter tuning, and system seed setting should be considered throughout model training, testing, and validation. Future early risk predictions models may improve with the inclusion of additional relevant covariates.

The use of unverified models for risk estimates and policy recommendations can be highly misleading, as their predictions may not reflect real-world health impacts. For example, a recent article states that NO₂ from gas stoves “likely causes ∼50,000 cases of current pediatric asthma from long-term NO₂ exposure alone” annually in the United States. This explicitly causal claim, which is contrary to several methodology and review articles published in this journal, among others, reflects both (a) An unverified modeling assumption that pediatric asthma burden is approximately proportional to NO₂; and (b) An unverified causal assumption that the assumed proportionality between exposure and response is causal. The article is devoid of any causal analysis showing that these assumptions are likely to be true. It does not show that reducing NO₂ exposure from gas stoves would reduce pediatric asthma risk. Its key references report no significant associations – let alone causation – between NO₂ and pediatric asthma. Thus, the underlying data suggests that the number of pediatric asthma cases caused by gas stoves in the United States is indistinguishable from zero. This highlights the need to rigorously validate modeling assumptions and causal claims in public health risk assessments to ensure scientifically sound foundations for policy decisions.