Gupta R, Szczesniak RD, Macaluso M. Modeling repeated count measures with excess zeros in an epidemiological study. Ann Epidemiol. 2015 Aug;25(8):583-9

Valid and precise modeling of self-reported problems with condom use is necessary for research on condom safety and effectiveness. Traditional techniques may produce misleading estimates when modeling large proportion of zero values (perfect users or non-reporters) and discrete nonzero counts (at risk of reporting problems). Zero-inflated Poisson mixed regression allowed us to identify the characteristics of the two groups: that older women were significantly more likely to be non-reporters or perfect users. The nonzero problem rate decreased during follow-up, and was lower among women who believed in the benefits of condom use, and had no sexually transmitted diseases at baseline.

Length of hospital stay, and number of surgeries for children presenting with certain conditions, offer examples of excess numbers of zeros in pediatric research setting. Zero-inflated regression techniques can produce the mixture of correct probability distributions, examine the effects of study variables, and conclusively draw accurate inferences about child health.

Szczesniak RD, Li D, Amin RS. Semiparametric mixed models for nested repeated measures applied to ambulatory blood pressure monitoring data. J Mod Appl Stat Methods. 2016 May;15(1):255-75.
Researchers need flexible statistical approaches to reveal complex relationships between treatment and nonlinear outcomes in pediatric diseases and disorders, especially as intensive medical monitoring becomes a more powerful tool in research and care. It is particularly challenging to characterize hierarchical longitudinal correlations arising from long data sequences generated on multiple subjects before and after treatment. In this study, researchers applied a series of semiparametric mixed models, which provide a nonparametric representation of long data sequences over time while allowing for flexible covariance specification, to examine effects of a surgical intervention on the circadian rhythm of ambulatory blood pressure in children with sleep apnea. Unlike their traditional counterparts, the semiparametric mixed models estimated precise timing of clinical features, such as morning surge and nocturnal dipping, and demonstrated that intervention effects are strongest on nocturnal diastolic blood pressure. These models provide a sensitive, efficient means to analyze medical monitoring data in pediatric medicine.
Brunst KJ, Ryan PH, Brokamp C, Bernstein D, Reponen T, Lockey J, Hershey GKK, Levin L, Grinshpun SA, LeMasters G. Timing and Duration of Traffic-related Air Pollution Exposure and the Risk for Childhood Wheeze and Asthma. Am J Respir Crit Care Med. 2015 Aug 15;192(4):421-7.
Prior studies examining exposure to air pollution and childhood respiratory outcomes, including wheeze and new-onset asthma, have reported inconsistent results. Few studies, however, have examined the relationship between timing and duration of traffic-related air pollution (TRAP) exposure and childhood wheezing and asthma development. This study provides evidence that early-life exposure to high levels of TRAP associates with wheeze symptoms during childhood. Researchers associate exposure to high levels of TRAP over the first seven years of life with asthma development.
Woo JG, Herbers PM, McMahon RJ, Davidson BS, Ruiz-Palacios GM, Peng YM, Morrow AL. Longitudinal Development of Infant Complementary Diet Diversity in 3 International Cohorts. J Pediatr. 2015 Nov;167(5):969-74.
This paper provides novel information regarding infant complementary dietary diversity in three global predominantly-breastfed cohorts: Cincinnati, Mexico City and Shanghai, China. Complementary diet diversity may be an important precursor to both healthy dietary habits later in life, as well as improved health of infants regarding growth and metabolic outcomes. The major findings are that infants are more likely to achieve minimal dietary diversity, and achieve it earlier, than infants in Mexico City or Cincinnati, driven by greater intake in meats and eggs. By contrast, Cincinnati infants who are highly breastfed late in the first year of life have very low dietary diversity scores, similar to low-income countries, potentially suggesting inappropriate or inadequate complementary feeding in this population. Exploration of the impacts of these findings on infant growth and health remain.
Brokamp C, LeMasters GK, Ryan PH. Residential mobility impacts exposure assessment and community socioeconomic characteristics in longitudinal epidemiology studies. J Expo Sci Environ Epidemiol. 2016 Jun;26(4):428-34.
Epidemiologic studies in pediatric research often use residential locations to estimate environmental exposures or community level characteristics, often with the assumption that a birth record address is constant throughout childhood. Using the Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS) cohort, we found that over half of the cohort moved at least once before age seven. Overall, moves showed a separation by a median of four miles, and associated with a decrease in harmful environmental exposures and an improvement in community economic characteristics. We showed that ignoring residential mobility by only using the birth record address resulted in exposure misclassification leading to a bias towards the null when associating the exposures with asthma at age seven. Future studies should consider residential mobility to prevent biased conclusions in pediatric medicine and research.