Association Between Distance to an Abortion Facility and Abortion or Pregnancy Outcome Among a Prospective Cohort of People Seeking Abortion Online

Abstract

Importance: Many people face barriers to abortion care, including long distances to an abortion facility.

Objectives: To investigate the association of distance to the nearest abortion facility with abortion or pregnancy outcome.

Design, setting, and participants: This cohort study was conducted using data from the Google Ads Abortion Access study, a prospective cohort study of individuals considering abortion recruited between August 2017 and May 2018. Individuals from 50 states and Washington, District of Columbia, who were pregnant and considering abortion based on self-report were recruited online using a stratified sampling technique. Participants completed online baseline and 4-week follow-up surveys. Data were analyzed between May and August 2021.

Exposures: Driving distance to an abortion facility calculated from participant zip code and grouped into 4 categories (<5 miles, 5-24 miles, 25-49 miles, and ≥50 miles).

Main outcomes and measures: Abortion or pregnancy outcome reported at 4-week follow-up, categorized as had an abortion, still seeking an abortion, or planning to continue pregnancy. Other measures included reported experience of 8 distance-related barriers to abortion, such as having to gather money for travel expenses and having to keep the abortion a secret.

Results: Among 1485 pregnant individuals considering abortion who completed the baseline survey and provided contact information, 1005 individuals completed follow-up (follow-up rate, 67.7%) and 856 participants were included in the analytic sample (443 individuals ages 25-34 years [51.8%]; 208 Black individuals [24.3%]; 101 Hispanic or Latinx individuals [11.8%], and 468 White individuals [54.8%]). Most participants had at least some college education (474 individuals [55.5%]). Distance to an abortion facility was less than 5 miles for 233 individuals (27.2%), 5 to 24 miles for 373 individuals (43.6%), 25 to 49 miles for 85 individuals (9.9%), and 50 or more miles for 165 individuals (19.3%) (mean [SD] distance = 28.3 [43.8] miles). Most participants reported at least 1 distance-related barrier (763 individuals [89.1%]), with a mean of 3.3 barriers (95% CI, 3.2-3.5 barriers) reported. For 7 of 8 distance-related barriers, an increased percentage of participants living farther from an abortion facility reported the barrier compared with participants living less than 5 miles from a facility; for example, 61.8% (95% CI, 53.5%-69.4%) of individuals living less than 5 miles reported having to gather money for travel expenses, while 81.2% (95% CI, 70.8%-88.5%; P = .002) of those living 25 to 49 miles and 75.8% (95% CI, 69.9%-81.0%; P = .02) of those living 50 or more miles from a facility reported this barrier. At follow-up, participants living 50 or more miles from a facility had higher odds of still being pregnant and seeking abortion (adjusted odds ratio [aOR] = 2.07; 95% CI, 1.35-3.17; P = .001) or planning to continue pregnancy (aOR = 1.96; 95% CI, 1.06-3.63; P = .03) compared with participants living within 5 miles.

Conclusions and relevance: This study found that greater distance from an abortion facility was associated with delays in obtaining abortion care and inability to receive abortion care. These findings suggest that innovative approaches to abortion provision may be needed to mitigate outcomes associated with long distances to abortion facilities.

Figure 1.. Abortion Facility Locations in 2017 and Density of Participant Locations

Map shows locations of 781 abortion facilities and 856 participants, with participant density shown by latitude and longitude.

Figure 2.. Online Abortion Information-Seeking Behaviors

Behaviors are shown among 409 participants who had obtained an abortion by 4-week follow-up.

Figure 3.. Estimated Proportions of Participants Reporting Distance-Related Barriers to Abortion by Distance Category

Estimated proportions are based upon mixed-effects logistic regression models accounting for clustering by respondents’ state of residence. P values are for estimated proportions reporting this barrier within each distance group compared with individuals living less than 5 miles from an abortion facility. Whiskers indicate 95% CIs.