Using unsupervised machine learning to classify behavioral risk markers of bacterial vaginosis.

INTRODUCTION: This study used an unsupervised machine learning algorithm, sidClustering and random forests, to identify clusters of risk behaviors of Bacterial Vaginosis (BV), the most common cause of abnormal vaginal discharge linked to STI and HIV acquisition.  METHODS: Participants were 391 cisgender women in Miami, Florida, with a mean of 30.8 (SD = 7.81) years of age; 41.7% identified as Hispanic; 41.7% as Black and 44.8% as White. Participants completed measures of demographics, risk behaviors [sexual, medical, and reproductive history, substance use, and intravaginal practices (IVP)], and underwent collection of vaginal samples; 135 behavioral variables were analyzed. BV was diagnosed using Nugent criteria. RESULTS: We identified four clusters, and variables were ranked by importance in distinguishing clusters: Cluster 1: nulliparous women who engaged in IVPs to clean themselves and please sexual partners, and used substances frequently [n = 118 (30.2%)]; Cluster 2: primiparous women who engaged in IVPs using vaginal douches to clean themselves (n = 112 (28.6%)]; Cluster 3: primiparous women who did not use IVPs or substances [n = 87 (22.3%)]; and Cluster 4: nulliparous women who did not use IVPs but used substances [n = 74 (18.9%)]. Clusters were related to BV (p < 0.001). Cluster 2, the cluster of women who used vaginal douches as IVPs, had the highest prevalence of BV (52.7%). CONCLUSIONS: Machine learning methods may be particularly useful in identifying specific clusters of high-risk behaviors, in developing interventions intended to reduce BV and IVP, and ultimately in reducing the risk of HIV infection among women.

PrEP awareness and use among reproductive age women in Miami, Florida.

BACKGROUND: Miami, Florida is an epicenter of the HIV epidemic in the US, with 20% of new HIV infections occurring in women. Despite effectiveness of Pre-Exposure Prophylaxis (PrEP) in preventing HIV, only 10% of eligible women benefit from its use. SETTING: This study evaluates PrEP awareness and use, and factors associated with PrEP awareness among sexually active women in Miami, Florida. METHODS: Results reported in this study included cross-sectional data that were collected as part of a baseline visit from a parent study. Cis-gender, HIV-negative, 18-45-year-old, sexually active women were recruited as part of a study evaluating recurrent bacterial vaginosis and HIV risk. Participants completed questionnaires assessing socio-demographics, HIV risk factors, prior history of HIV testing and reproductive tract infections, PrEP awareness and use. Relationships between variables and PrEP awareness were analyzed and multivariable logistic regression identified variables strongly associated with PrEP awareness. RESULTS: Among the 295 women enrolled, median age was 31 (24-38) years, 49% Black, 39% White, and 34% Hispanic. Of 63% who knew about PrEP, only 5% were on PrEP. Women with income below poverty line (OR = 2.00[1.04,3.87];p = 0.04), more male sexual partners in past month (OR = 1.30[1.01,1.68];p = 0.04), lifetime HIV testing (OR = 6.42[2.83,14.52];p<0.01), and current bacterial vaginosis (OR = 2.28[1.18,4.40];p = 0.01) were more likely to be aware of PrEP. Lower odds of PrEP awareness were associated with being Black (OR = 0.38[0.15,0.96];p = 0.04), Hispanic (OR = 0.18[0.08,0.39];p<0.01), heterosexual (OR = 0.29[0.11,0.77];p<0.01), and reporting inconsistent condom use during vaginal sex (OR = 0.21[0.08,0.56];p<0.01). CONCLUSION: PrEP awareness is low among reproductive age women in a high-risk setting. Culturally tailored interventions are needed to increase PrEP awareness and uptake, especially among Black and Hispanic women with inconsistent condom use during vaginal sex with male partners.

Severe Acute Respiratory Syndrome Coronavirus 2: Vaccine Hesitancy Among Underrepresented Racial and Ethnic Groups With HIV in Miami, Florida.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and human immunodeficiency virus (HIV) disproportionally affect underrepresented ethnoracial groups in the United States. Medical mistrust and vaccine hesitancy will likely impact acceptability of SARS-CoV-2 vaccines. This study examined SARS-CoV-2 vaccine hesitancy among underrepresented ethnoracial groups with HIV and identified factors that may reduce vaccine uptake. METHODS: We conducted a cross-sectional study of adults ≥18 years of age with HIV residing in Miami, Florida. Participants were invited to participate in the ACTION (A Comprehensive Translational Initiative on Novel Coronavirus) cohort study. A baseline survey was administered from April to August 2020 and followed by a coronavirus disease 2019 (COVID-19) vaccine hesitancy survey from August to November 2020. The COVID-19 vaccine hesitancy survey was adapted from the Strategic Advisory Group of Experts survey. Comparisons by race and ethnicity were performed using the Freedman-Haltmann extension of the Fisher exact test. RESULTS: A total of 94 participants were enrolled; mean age was 54.4 years, 52% were female, 60% were Black non-Latinx, and 40% were non-Black Latinx. Black non-Latinx participants were less likely to agree that vaccinations are important for health when compared to non-Black Latinx (67.8% vs 92.1%, P = .009), less likely to agree that vaccines are effective in preventing disease (67.8% vs 84.2%, P = .029), less likely to believe that vaccine information is reliable and trustworthy (35.7% vs 71.1%, P = .002), and less likely to believe vaccines were unnecessary because COVID-19 would disappear soon (11% vs 21%, P = .049). CONCLUSIONS: Medical mistrust, vaccine hesitancy, and negative sentiments about SARS-CoV-2 vaccines are prevalent among underrepresented ethnoracial groups with HIV, particularly Black non-Latinx. Targeted strategies to increase vaccine uptake in this population are warranted.