Publications by authors named "Wilson Ramos"

4 Publications

  • Page 1 of 1

Using Machine Learning to Predict Young People's Internet Health and Social Service Information Seeking.

Prev Sci 2021 May 11. Epub 2021 May 11.

University of California, UCLA Center for Community Health, 10920 Wilshire Blvd Suite 350, Los AngelesLos Angeles, CA, 90024, USA.

Machine learning creates new opportunities to design digital health interventions for youth at risk for acquiring HIV (YARH), capitalizing on YARH's health information seeking on the internet. To date, researchers have focused on descriptive analyses that associate individual factors with health-seeking behaviors, without estimating of the strength of these predictive models. We developed predictive models by applying machine learning methods (i.e., elastic net and lasso regression models) to YARH's self-reports of internet use. The YARH were aged 14-24 years old (N = 1287) from Los Angeles and New Orleans. Models were fit to three binary indicators of YARH's lifetime internet searches for general health, sexual and reproductive health (SRH), and social service information. YARH responses regarding internet health information seeking were fed into machine learning models with potential predictor variables based on findings from previous research, including sociodemographic characteristics, sexual and gender minority identity, healthcare access and engagement, sexual behavior, substance use, and mental health. About half of the YARH reported seeking general health and SRH information and 26% sought social service information. Areas under the ROC curve (≥ .75) indicated strong predictive models and results were consistent with the existing literature. For example, higher education and sexual minority identification was associated with seeking general health, SRH, and social service information. New findings also emerged. Cisgender identity versus transgender and non-binary identities was associated with lower odds of general health, SRH, and social service information seeking. Experiencing intimate partner violence was associated with higher odds of seeking general health, SRH, and social service information. Findings demonstrate the ability to develop predictive models to inform targeted health information dissemination strategies but underscore the need to better understand health disparities that can be operationalized as predictors in machine learning algorithms.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
May 2021

Optimizing screening for anorectal, pharyngeal, and urogenital C. trachomatis and N. gonorrhoeae infections in at risk adolescents and young adults in New Orleans, Louisiana and Los Angeles, California, USA.

Clin Infect Dis 2020 Dec 10. Epub 2020 Dec 10.

Division of Infectious Diseases, David Geffen School of Medicine, University of California, Los Angeles, California, USA.

Background: Public health organizations have inconsistent recommendations for screening adolescents and young adults for Chlamydia trachomatis (C. trachomatis) and Neisseria gonorrhoeae (N. gonorrhoeae) infections. Guidelines suggest different combinations of anorectal, pharyngeal, and urogenital testing based on age, sex, and sexual activity. Further evaluation of how identity and behaviors impact the anatomic distribution of C. trachomatis and N. gonorrhoeae infection is needed to optimize future screening practices.

Methods: We assessed the positivity of C. trachomatis and N. gonorrhoeae infections at different anatomic sites in a cohort of at-risk sexually active adolescents and young adults between 12-24 years old in New Orleans, Louisiana and Los Angeles, California. Participants were tested for C. trachomatis and N. gonorrhoeae at three sites (anorectum, pharynx, and urethral/cervix) every four months using self-collected swabs. We stratified anatomic distributions of infection into four gender and sexual behavior categories: (i) cisgender men who have sex with men and transgender women (MSMTW), (ii) cis-heterosexual males, (iii) cis-heterosexual females, and (iv) gender minorities assigned female at birth.

Results: While three-site testing detected all infections, two-site (anorectum and urethra/cervix) testing identified 92-100% of C. trachomatis or N. gonorrhoeae infections in participants assigned female at birth and cis-heterosexual males. For MSMTW, two site anorectal and pharyngeal testing versus single site anorectal testing increased the proportion of individuals with either infection from 74 to 93%.

Conclusion: Sexual behavioral and gender identity factors may influence detection of C. trachomatis and N. gonorrhoeae infections at specific anatomic testing sites. Testing guidelines should incorporate sexual behavior and gender identity.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
December 2020

Sexually Transmitted Infection Positivity Among Adolescents With or at High-Risk for Human Immunodeficiency Virus Infection in Los Angeles and New Orleans.

Sex Transm Dis 2019 11;46(11):737-742

From the Division of Infectious Diseases.

Background: Gay, bisexual, and transgender youth and homeless youth are at high risk for sexually transmitted infections (STIs). However, little recent data exist describing STI positivity by anatomical site among those groups. We determined the positivity of Chlamydia trachomatis (CT) infection, Neisseria gonorrhoeae (NG) infection, and syphilis antibody reactivity among lesbian, gay, bisexual, transgender, and homeless youth.

Methods: We recruited 1,264 adolescents with high risk behavior aged 12 to 24 years from homeless shelters, lesbian, gay, bisexual, and transgender organizations, community health centers, and using social media and online dating apps in Los Angeles, California and New Orleans, Louisiana from May 2017 to February 2019. Participants received point-of-care pharyngeal, rectal, and urethral/vaginal CT and NG testing and syphilis antibody testing. We calculated STI positivity by anatomical site and compared positivity by participant subgroups based on human immunodeficiency virus (HIV) status, sex assigned at birth, and gender identity.

Results: CT and NG positivity and syphilis antibody reactivity was higher among HIV-infected adolescent men who have sex with men (MSM) than HIV-uninfected adolescent MSM (40.2% vs. 19%, P < 0.05), particularly CT or NG rectal infection (28% vs. 12.3%, P < 0.05). Of participants with positive CT or NG infections, 65% had extragenital-only infections, 20% had both extragenital and urogenital infections, and 15% had urogenital-only infections.

Conclusions: Sexually transmitted infection positivity was high, particularly among transgender women and MSM. The high proportion of rectal and pharyngeal infections highlights the importance of both urogenital and extragenital STI screening. More accessible STI testing is necessary for high-risk adolescent populations.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
November 2019

Design of a Community-Engaged Health Informatics Platform with an Architecture of Participation.

AMIA Annu Symp Proc 2015 5;2015:905-14. Epub 2015 Nov 5.

Columbia University Department of Biomedical Informatics, New York, NY.

Community-engaged health informatics (CEHI) applies information technology and participatory approaches to improve the health of communities. Our objective was to translate the concept of CEHI into a usable and replicable informatics platform that will facilitate community-engaged practice and research. The setting is a diverse urban neighborhood in New York City. The methods included community asset mapping, stakeholder interviews, logic modeling, analysis of affordances in open-source tools, elicitation of use cases and requirements, and a survey of early adopters. Based on synthesis of data collected, (GHH) was developed using open-source LAMP stack and Drupal content management software. Drupal's organic groups module was used for novel participatory functionality, along with detailed user roles and permissions. Future work includes evaluation of GHH and its impact on agency and service networks. We plan to expand GHH with additional functionality to further support CEHI by combining informatics solutions with community engagement to improve health.
View Article and Find Full Text PDF

Download full-text PDF

February 2018