Interpregnancy interval and preterm delivery: An empirical comparison of between-persons and within-sibship designs.

Abstract

Short interpregnancy interval has been associated with increased risk of preterm delivery; recent studies employing within-sibship designs suggest that this risk may be exaggerated. There are unresolved issues regarding properties of this design. To compare directly the results, for short intervals, of between-person and within-sibship analyses when applied to the same target population. Cross-sectional data are from the National Survey of Family Growth, a statistically representative survey of women and men in the USA, 2006-2015. Participants provided a complete pregnancy history including outcome, duration and ending date, enabling calculation of interval. Conventional analysis employed log-linear regression, controlling survey design, early life events, demographic variables, pregnancy intendedness, breastfeeding of the previous birth and obstetric history. Within-sibship analyses, utilising conditional log-linear regression, controlled the same variables, except those remaining static within each participant. Among participants with at least three live- or stillbirths, the percentage of pregnancies in each interval, and the percent of deliveries that were preterm following that interval were 9.2%, 14.6% for <6, and 14.7%, 15.4% for 6-11, versus 12.2%, 14.7% for 18-23 months. Among participants with at least three live- or stillborn infants, those in the within-sibship analysis had a higher risk profile than comparably parous, ineligible participants. In a between-participant analysis, among those included in within-sibship models, the adjusted risk ratios (vs 18-23 months) for preterm delivery for intervals <6 and 6-11 months were 0.74 (95% CI 0.63, 0.88) and 0.85 (95% CI 0.74, 0.98). The corresponding risk ratios were 0.56 (95% CI 0.14, 2.30) and 0.49 (95% CI 0.13, 1.80) for those ineligible for the within-sibship models. When comparable analyses were employed, the association between interval and preterm delivery was similar between participants included in the within-sibship analysis and those ineligible for the within-sibship analysis, but differed from those in the full cohort, perhaps due to different target populations.