The effect of regulatory advisories on maternal antidepressant prescribing, 1995-2007: an interrupted time series study of 228,876 pregnancies

Abstract

The purpose of this study was to assess whether antidepressant prescribing during pregnancy decreased following release of U.S. and Canadian public health advisory warnings about the risk of perinatal complications with antidepressants. We analyzed data from 228,876 singleton pregnancies among women (aged 15-44 years) continuously enrolled in Tennessee Medicaid with full pharmacy benefits (1995-2007). Antidepressant prescribing was determined through outpatient pharmacy dispensing files. Information on sociodemographic and clinical factors was obtained from enrollment files and linked birth certificates. An interrupted time series design with segmented regression analysis was used to quantify the impact of the advisory warnings (2002-2005). Antidepressant prescribing rates increased steadily from 1995 to 2001, followed by sharper increases from 2002 to late 2004. Overall antidepressant prescribing prevalence was 34.51 prescriptions [95 % confidence interval (CI) 33.37-35.65] per 1,000 women in January 2002, and increased at a rate of 0.46 (95 % CI 0.41-0.52) prescriptions per 1,000 women per month until the end of the pre-warning period (May 2004). During the post-warning period (October 2004-June 2005), antidepressant prescribing decreased by 1.48 (95 % CI 1.62-1.35) prescriptions per 1,000 women per month. These trends were observed for both selective serotonin reuptake inhibitors (SSRI) and non-SSRI antidepressants, although SSRI prescribing decreased at a greater rate. We conclude that antidepressant prescribing to pregnant women in Tennessee Medicaid increased from 1995 to late 2004. U.S. and Canadian public health advisories about antidepressant-associated perinatal complications were associated with steady decreases in antidepressant prescribing from late 2004 until the end of the study period, suggesting that the advisory warnings were impactful on antidepressant prescribing in pregnancy.

Figure 1

Antidepressant prescribing rates during pregnancy (1995–2007). The dates of FDA (blue dashed line) and Health Canada (green dashed line) pregnancy warnings are also shown. Smoothed lines were drawn for antidepressant prescribing rates over time using a locally-weighted polynomial regression to smooth the data.

Figure 2

Figure 2A. Results of the interrupted time-series analysis focused on the association between release of the FDA and Health Canada pregnancy warnings and antidepressant prescribing during pregnancy, using a 4 month transition period (June 1, 2004–September 30, 2004). Figure 2B. Results of the interrupted time-series analysis that estimated the association between pregnancy and suicide warnings and antidepressant prescribing during pregnancy, using an expanded transition period (January 1, 2004–October 31, 2004).

Figure 2

Figure 2A. Results of the interrupted time-series analysis focused on the association between release of the FDA and Health Canada pregnancy warnings and antidepressant prescribing during pregnancy, using a 4 month transition period (June 1, 2004–September 30, 2004). Figure 2B. Results of the interrupted time-series analysis that estimated the association between pregnancy and suicide warnings and antidepressant prescribing during pregnancy, using an expanded transition period (January 1, 2004–October 31, 2004).