The intergenerational persistence of opioid dependence: Evidence from administrative data

Abstract

To address the opioid crisis, it is crucial to understand its origins. We provide descriptive evidence for the intergenerational persistence of opioid dependence. Our analysis is based on administrative data covering the universe of Austrian births from 1984 to 1990. We consider prescription opioids and a new proxy for addiction to illicit opioids. We find that, if at least one parent is using illicit opioids, the likelihood of the child using increases from 1% to 7%. For prescription opioids, we observe an increase from 3.6% to 6.7%. Both associations are stable and do not change when controlling for environmental variables.

Keywords: addiction; drug abuse; heroin; illicit opioids; intergenerational correlation; intergenerational transmission; opioids; prescription opioids.

FIGURE 1

Birth cohorts in study and data availability. This figure illustrates the birth cohorts in study and data availability. UAHIF health records are available between 1998 and 2017, this is the blue shaded area. We consider the cohorts 1984–1990, where we observe each child from age 14 to 27. For example, a child born in 1984 is 14 in 1998 and 27 in 2011. A child born in 1990 is 14 in 2004 and 27 in 2017. Our results are robust to choosing different cohorts; in Figure A2, we extend the window to children born between 1980 and 1990, which leads to very similar conclusions as in our baseline. UAHIF, Upper Austrian Health Insurance Fund

FIGURE 2

Age at onset of substitution and prescription opioid therapy. This figure shows distributions of the age at onset for the first recorded (a) substitution therapy and (b) prescription opioid therapy per patient in the full 1998–2017 UAHIF database. The shaded area indicates the age range 14–27, which is the period in which we observe substitution therapy and prescription opioid therapy for the children in our sample. UAHIF, Upper Austrian Health Insurance Fund

FIGURE 3

The intergenerational persistence of opioid dependence. This graph plots the intergenerational persistence estimates for illicit opioids and prescription opioids with varying covariates. Dependence to illicit opioids is approximated with participation in substitution therapy. Prescription opioids comprise all drugs in ATC categories N01AH and N02A. Children are considered to exposed to parental opioid use if either the father or the mother have ever been using illicit opioids or prescription opioids, respectively. The bars represent OLS estimates and 95% confidence intervals based on municipality‐level clustered and heteroskedasticity‐robust standard errors are indicated by the purple lines. The covariate included are listed in Table 1. ATC, Anatomical Therapeutic Chemical Classification System

FIGURE 4

The intergenerational persistence of opioid dependence: Effect of mothers versus fathers. This graph plots the intergenerational persistence estimates for (a) illicit opioids and (b) prescription opioids with varying covariates. Dependence to illicit opioids is approximated by participation in substitution therapy. We present results based on two treatment definitions. First, a child is considered exposed to parental opioid use if their mother has ever been in substitution therapy (filled bars). These estimations are based on a sample of 74,909 mother‐child pairs, containing 225 substituted mothers and 844 substituted children. Second, a child is considered exposed to parental opioid use if their father has ever been in substitution therapy (hollow bars). These estimations are based on a sample of 60,649 father‐child pairs, which comprises 301 substituted fathers and 578 substituted children. Prescription opioids comprise all drugs in ATC categories N01AH and N02A. Here the mother‐child pairs (filled bars) contain 16,345 mothers and 3583 children with at least one prescription. The father‐child pairs (hollow bars) contain 14,364 fathers and 2698 children. The covariates included are listed in Table 1. The bars represent OLS estimates and 95% confidence intervals based on municipality‐level clustered and heteroskedasticity‐robust standard errors are indicated by the orange lines. ATC, Anatomical Therapeutic Chemical Classification System

FIGURE A1

Opioid prescriptions per million population among OECD member countries. Average availability of analgesic opioids in OECD countries 2014–2016 in defined daily doses for statistical purposes per million population per day. The data are retrieved from www.oecd.org/els/health‐systems/opioids.htm, accessed on June 16, 2020

FIGURE A2

Intergenerational persistence of opioid dependence, extended sample 1980–1990. This graph replicates the regressions in Figure 3 on a sample that also includes children born between 1980 and 1983. For these cohorts we do not have information on mothers' education and job, we therefore do not control for these variables when we introduce mother socioeconomics. The bars represent OLS estimates and 95% confidence intervals based on municipality‐level clustered and heteroskedasticity‐robust standard errors are indicated by the purple lines. The covariates included are listed in Table 1

FIGURE A3

Intergenerational persistence of opioid dependence, restricted sample 1984–1985. This graph replicates the regressions in Figure 1 on a sample that also includes only children born between 1984 and 1985. This allows us to observe children between ages 14–32. The bars represent OLS estimates and 95% confidence intervals based on municipality‐level clustered and heteroskedasticity‐robust standard errors are indicated by the purple lines. The covariate included are listed in Table 1