Toward improving retention in HIV care after pregnancy: lessons from a post-pandemic cohort in the United States

Abstract

Introduction: People living with HIV (PLWH) often experience low rates of retention in HIV care (RIC) and suboptimal viral suppression postpartum. Understanding contemporary barriers to RIC is crucial to identify risk factors for loss to care and thereby improve support during this vulnerable transition. This work aimed to identify factors associated with adequate RIC, defined as two HIV care visits ≥90 days apart in the first year postpartum.

Methods: Electronic records were retrospectively reviewed for PLWH who delivered from 2019 to 2023 and received prenatal care within a single county health system. Variables were collected related to both maternal and neonatal HIV and obstetric or pediatric care. Variables were analyzed using descriptive statistics, and Kaplan-Meier curves were used to assess viral suppression during pregnancy and the first year postpartum. A Random Forest machine learning model was used to determine variables of relative importance for prediction of adequate RIC. Multivariable logistic regression was used to evaluate impact of identified variables on RIC.

Results: Of 182 pregnancies, sixty individuals (33%) achieved adequate postpartum RIC. Adequate RIC correlated with year of delivery (p = 0.018), attending at least two obstetrical postpartum visits (p = 0.025), viral suppression at initial prenatal visit (p = 0.030), and shorter duration between pregnancy visit and HIV care visits before and after pregnancy (p < 0.001). Viral suppression was generally excellent at time of delivery (99.4%). However, viral loads rebounded after delivery, with 66.8% suppressed at 12 months postpartum. Random Forest modeling identified several clinical and social factors with relative importance for prediction of RIC. Multivariable logistic regression supported above findings with significant decreased odds of adequate RIC based on year of delivery [2021 aOR 0.306 (0.097-0.956), 2022 0.146 (0.046-0.458), 2023 0.071 (0.011-0.455)], higher viral load at initial prenatal visit [aOR 0.038 (0.002-0.889)], and longer duration between last HIV care visit and first pregnancy visit [aOR 0.419 (0.176-0.998)].

Discussion: Postpartum RIC was suboptimal in this contemporary US single-site cohort. Engagement in prenatal and postpartum obstetric care predicted improved postpartum RIC. Further qualitative research is essential to improve deeper understanding of patterns of engagement perinatally in order to develop effective interventions to improve support for individuals during this difficult transition.

Keywords: HIV; barriers; postpartum; pregnancy; retention.

Figure 1

Cohort diagram. A total cohort of 182 pregnant people living with HIV (PLWH) met study criteria. Of these, only 33% had adequate postpartum retention in care (RIC), defined as 2 visits ≥90 days apart in the first 12 months post-delivery.

Figure 2

Social vulnerability. Centers for Disease Control and Prevention (CDC) Social Vulnerability Index (SVI) demonstrates high vulnerability throughout the entire cohort. Vulnerability is ranked in comparison to vulnerability across all other census tracts in the state.

Figure 3

Retention in care by year of delivery. Post-pandemic years showed a significant increase in inadequate postpartum retention in care (RIC).

Figure 4

Viral suppression during pregnancy and postpartum. Viral suppression (having an undetectable viral load, <50 copies/mL) increases during pregnancy (A), then decreases steadily after delivery (B). Time 0 indicates date of delivery. Note the drop off in lab values available following delivery, consistent with inadequate retention in care. ND, viral load not detectable; <50 copies/mL.

Figure 5

Random forest machine learning model. (A) Machine learning identifies variables of importance associated with adequate postpartum retention in care. (B) Confusion matrix of the model shows performance of the model in prediction of adequate retention in care. APNCU, Adequacy of Prenatal Care Utilization index; SVI, CDC Social Vulnerability Index; VL, viral load; BMI, body mass index.