Interrupted-time-series analysis of the immediate impact of COVID-19 mitigation measures on preterm birth in China

Abstract

Preliminary evidence from China and other countries has suggested that coronavirus disease 2019 (COVID-19) mitigation measures have caused a decline in preterm births, but evidence is conflicting. Utilising a national representative data of 11,714,947 pregnant women in China, we explored the immediate changes in preterm birth rates during the COVID-19 mitigation period using an interrupted-time-series analysis. We defined the period prior to February 1, 2020 as the baseline, followed by the COVID-19 mitigation stage. In the first month of the COVID-19 mitigation, a significant absolute decrease in preterm birth rates of 0.68% (95%CI:-1.10% to -0.26%) in singleton, and of 2.80% (95%CI:-4.51% to -1.09%) in multiple births was noted. This immediate decline in Wuhan was greater than that at the national level among singleton births [-2.21% (95%CI:-4.09% to -0.34% vs. -0.68%)]. Here we report an immediate impact of COVID-19 mitigation measures on preterm birth in China.

Fig. 1. Interrupted time series analysis (ITSA) of the preterm birth rate across different type pregnancies in China, 2012–2020.

a singleton births; b multiple births. Dots indicate true monthly preterm birth rates, solid lines indicate the mean of estimated preterm birth rates per month by ITSA model, and red solid lines indicate the mean of estimated preterm birth rates per month assuming that COVID-19 mitigation measure had not occurred by ordinary least-squares regression with Newey-West standard errors. Baseline: from January 1, 2012 to January 31, 2020; Intervention stage: from February 1, 2020 to December 31, 2020. COVID-19: coronavirus disease 2019. The p values are two-sided.

Fig. 2. Interrupted time series analysis (ITSA) of the preterm birth rate across different socioeconomic statuses in China, 2012–2020.

a advantaged in singleton births; b disadvantaged in singleton births; c the result of ITSA in singleton births across population; d advantaged in mutiple births; e disadvantaged in mutiple births; f the result of ITSA in multiple births across population. Dots indicate true monthly preterm birth rates and solid lines indicate the mean of estimated preterm birth rates per month by ITSA model, and red solid lines indicate the mean of estimated preterm birth rates per month assuming that COVID-19 mitigation measure had not occurred by ordinary least-squares regression with Newey-West standard errors. Women who were illiterate, or had only primary school education, who were unmarried, or who had fewer than five antenatal visits were defined as the disadvantaged group. On the contrary, women with middle school or above education, married, and had more than five antenatal visits were defined as the advantaged group. Baseline: from January 1, 2012 to January 31, 2020; Intervention stage: from February 1, 2020 to December 31, 2020. Intercept change: change in level compared with the previous stage; Slope change: change in trend compared with the previous stage, per month. CI confidence interval, COVID-19 Coronavirus disease 2019. The p values are two-sided.

Fig. 3. Interrupted time series analysis (ITSA) of the preterm birth rate across different type pregnancies in Wuhan, 2012–2020.

a singleton births; b multiple births; c the result of ITSA across different type pregnancies. Dots indicate true monthly preterm birth rates and solid lines indicate the mean of estimated preterm birth rates per month by ITSA model, and red solid lines indicate the mean of estimated preterm birth rates per month assuming that COVID-19 mitigation measure had not occurred by ordinary least-squares regression with Newey-West standard errors. Baseline: from January 1, 2012 to January 31, 2020; Intervention stage: from February 1, 2020 to December 31, 2020. Intercept change: change in level compared with the previous stage; Slope change: change in trend compared with the previous stage, per month. CI: confidence interval; COVID-19: coronavirus disease 2019. The p values are two-sided.