Stigma and Ebola survivorship in Liberia: Results from a longitudinal cohort study

Abstract

Background: Survivors of the 2014-2016 West Africa Ebola epidemic have been reported to suffer high levels of stigmatization after return to their communities. We sought to characterize the stigma encountered by a cohort of Ebola survivors in Liberia over time.

Methods: Ebola-related stigma was assessed from June 2015 to August 2017 in 299 adolescent and adult Liberian Ebola Survivor Cohort participants at three month intervals using adapted HIV stigma scales scored from 0 to 10 according to the proportion of answers indicating stigmatization.

Findings: The median time from Ebola Virus Disease (EVD) to study entry was 393 days (IQR 336-492). Participants (43% female) had a median age of 31 (IQR 25-40) years. Mean self-reported stigma levels were greater at baseline (6.28 ± 0.15 [IQR: 4.38-8.75]) compared to the first post-baseline visit (0.60 ± 0.10 [IQR: 0-0]; p<0.0001). During follow-up, stigma levels were stable. Baseline stigma significantly increased during enrollment and following clusters of Ebola re-emergence in Liberia. Survivors encountered primarily enacted and perceived external stigma rather than internalized stigma.

Conclusions: Ebola-related stigma was prevalent among Liberian survivors more than a year after EVD recovery. Self-reported stigma was greater in the period before cohort enrollment; however, some degree of stigmatization persisted years after EVD. Transient rises in stigma were observed following episodic Ebola re-emergence of EVD in Liberia. During future EVD outbreaks, enhanced public health interventions designed to prevent and mitigate Ebola-related stigma that is enacted and external should be implemented to support survivor recovery and community re-integration.

Fig 1. Total and subscale stigma scores at baseline and first follow-up visits.

Fig 1: Top-panel: Comparison of mean baseline stigma scores and stigma scores at first follow-up visit for all respondents. Error bars represent standard error. All differences are significant: total stigma [t(505) = 31.88, P<0.0001], perceived stigma [t(599) = 35.61, P<0.0001], internalized stigma [t(330) = 10.70, P<0.0001), enacted stigma [t(563) = 29.65, P<0.0001], disclosure fears [t(472) = 15.69, P<0.0001]. Bottom panel: Scatter plots of the proportion with at least one stigma indicating response across visits and the mean stigma scores for all respondents with local regression lines using LOESS method and span = 0.2. X-axis labels are the study visit followed by the number of participants sampled at that visit. Later study enrollees have not yet reached visits 6, 7 and 8. Gray bands represent 95% confidence intervals. All follow-up visits are significantly different from the baseline-visit (F_8,1941 = 282.1, p<0.0001), and do not significantly differ from each other (F_{7, 1643} = 1.145, p = 0.33).

Fig 2. Stigma subscale scores at all study visits.

Fig 2: Scatter plots of stigma sub-scores across visits with local regression lines using LOESS method and span = 0.2. X-axis labels are the study visit, followed by the number of participants sampled at that visit. Later study enrollees have not yet reached visits 6, 7 and 8. Gray bands represent 95% confidence intervals. Follow-up visits are not statistically different in the sub-scores: perceived-external stigma (F_7,1643 = 1.516, p = 0.152), internalized stigma (F_{7, 1643} = 0.924, p = 0.487), and enacted stigma (F_{7, 1643} = 1.14, p = 0.335). The disclosure concern score at visit 6, 1.81, was greater than the score at visit 1, 0.74 (F_7,1643 = 2.042, p = 0.0469).

Fig 3. Trend in baseline total stigma scores over time.

Fig 3: Comparison in baseline stigma scores of participants enrolled in the different quartiles of enrollment. X-axis labels are the date range for each quartile of enrollment followed by the number of participants recruited in the quartile in parentheses.

Fig 4. Changes in baseline total and subscale stigma scores during Ebola re-emergence events.

Fig 4: Scatter plots of baseline stigma score data with local regression lines using LOESS method and span = 0.2. Vertical lines represent Ebola re-emergence. Gray bands represent 95% confidence intervals.