Background: The Dominican Republic (DR) ranks among nations with the highest burden of HIV in the Caribbean. Cultural and gender roles in rural areas of the DR may place women at increased HIV risk. However, little is known about sexual health and HIV testing behaviors among women in the rural DR. Methods: We conducted a needs assessment among a systematic sample of adult women in a rural DR community in 2016. Demographic and behavioral attributes related to HIV testing, sexual health, and healthcare utilization were evaluated. Poisson regression analysis was used to identify demographics and behaviors associated with having had a previous HIV test. Significance was defined as a p-value < 0.05. Results: Among 105 women evaluated, 77% knew someone with HIV and 73% of women reported that they would be very or extremely likely to take an HIV test if offered. Only 68% reported a previous HIV test, including 47% who were tested over 2 years prior. Barriers to HIV testing included low risk perception (23%), distance or requisite travel (13%), and discomfort being tested (11%). Women who had never been tested for HIV were more likely than those who had been tested to be older (p = 0.03), to have a lower level of education (p = 0.04), and to have never been tested for other sexually transmitted infections (STI; p < 0.01). In the Poisson multiple regression model, the only significant predictor of having had an HIV test was having had an STI test (p = 0.03). Conclusions: In the rural DR, numerous barriers contribute to low prevalence of HIV testing among women. Most women report willingness to have an HIV test and many engage in routine health care, indicating that this population may benefit from incorporating HIV testing and other sexual health promotion activities into routine medical care.

In 2010, the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) started the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-be (nuMoM2b), a prospective cohort study of a racially/ethnically/geographically diverse population of nulliparous women with singleton gestation. The nuMoM2b is a very large dataset, consisting of data for 10,038 patients with over 4,600 features per patient, spread out over 80 files. In this report, we share our experience preparing and working with this dataset. We present our data preprocessing of the nuMoM2b dataset to get a deeper understanding of the data, extract the most relevant features, make the fewest assumptions when filling in unknown values, and reducing the dimensionality of the data. We hope this report is useful to researchers interested in building machine learning and statistical models from the nuMoM2b dataset.

No abstract