Understanding HIV Risk Behavior from a Sociocultural Perspective

Ordóñez, Claudia E.; Marconi, Vincent C.

doi:10.4172/2155-6113.1000e108

Cited by 17 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consistent with previous cohort study conducted at University Hospital in Brazzaville [15] or elsewhere in African region [22], low level of education was among most important predictors of treatment failure . It is well reported that low level of education which like poverty is an important systemic determinant of health in low-income countries and calls for major structural changes [23].…”

Section: Discussionmentioning

confidence: 99%

Factors Associated with Antiretroviral Treatments Failure among HIV-Positive Patients in Congo: A Retrospective Cohort Study

Ndziessi¹,

Aloumba²,

Essie³

et al. 2020

WJA

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Factors Associated with Antiretroviral Treatments Failure among HIV-Positive Patients in Congo: A Retrospective Cohort Study

Ndziessi¹,

Aloumba²,

Essie³

et al. 2020

WJA

View full text Add to dashboard Cite

“…The cohort is described in detail in a manuscript currently under review and Figure 2 is a sub-analysis of this data presented as a visual explanation of the potential utility of SHAP-based metrics in decomposing HIV risk at both an aggregate ( Figure 2A ) and individual ( Figure 2B ) level. Given that the social and behavioural risk factors for HIV vary by context ( 43 ), the relative predictive value of these features seen in Figure 2 is specific to this cohort and likely varies across cultures and regions. This underscores the importance of local validation and fine-tuning of any risk prediction algorithm that utilises socio-behavioural features prior to deployment emphasises the importance of model decomposition in understanding the contributors to risk in a given population.…”

Section: Ml: Model Development and Evaluationmentioning

confidence: 99%

“…Within HIV, exact risk factors for transmission vary significantly by population but are typically behavioural and socio-demographic in nature ( 43 ). This has led to such factors featuring prominently in ML algorithms attempting to estimate HIV risk ( 19 ).…”

Section: Ml: Model Development and Evaluationmentioning

confidence: 99%

The role of machine learning in HIV risk prediction

Fieggen

Smith²,

Arora³

et al. 2022

Front. Reprod. Health

View full text Add to dashboard Cite

Despite advances in reducing HIV-related mortality, persistently high HIV incidence rates are undermining global efforts to end the epidemic by 2030. The UNAIDS Fast-track targets as well as other preventative strategies, such as pre-exposure prophylaxis, have been identified as priority areas to reduce the ongoing transmission threatening to undermine recent progress. Accurate and granular risk prediction is critical for these campaigns but is often lacking in regions where the burden is highest. Owing to their ability to capture complex interactions between data, machine learning and artificial intelligence algorithms have proven effective at predicting the risk of HIV infection in both high resource and low resource settings. However, interpretability of these algorithms presents a challenge to the understanding and adoption of these algorithms. In this perspectives article, we provide an introduction to machine learning and discuss some of the important considerations when choosing the variables used in model development and when evaluating the performance of different machine learning algorithms, as well as the role emerging tools such as Shapely Additive Explanations may play in helping understand and decompose these models in the context of HIV. Finally, we discuss some of the potential public health and clinical use cases for such decomposed risk assessment models in directing testing and preventative interventions including pre-exposure prophylaxis, as well as highlight the potential integration synergies with algorithms that predict the risk of sexually transmitted infections and tuberculosis.

show abstract

“…In the canons of risk theory, rational choice models emphasize the central importance of beliefs, but they do not speak well to how and why individuals come to believe the things they do [35]. Addressing this limitation, sociocultural theory can be used to help us understand the social genesis of personally-held beliefs and worldviews and thereby explain better why people do the things they do [36]. Sociocultural theory therefore seeks to liberate individuals from psychological flowcharts and conceptualize them instead as social animals embedded within social environments.…”

Section: Introductionmentioning

confidence: 99%

Patterns of Online and Offline Connectedness Among Gay, Bisexual, and Other Men Who Have Sex with Men

et al. 2017

View full text Add to dashboard Cite

This study examined patterns of connectedness among 774 sexually-active gay, bisexual, and other men who have sex with men (GBM), aged ≥ 16 years, recruited using respondent-driven sampling in Metro Vancouver. Latent class analysis examined patterns of connectedness including: attendance at gay venues/events (i.e., bars/clubs, community groups, pride parades), social time spent with GBM, use of online social and sex seeking apps/websites, and consumption of gay media. Multinomial regression identified correlates of class membership. A three-class LCA solution was specified: Class 1 "Socialites" (38.8%) were highly connected across all indicators. Class 2 "Traditionalists" (25.7%) were moderately connected, with little app/website-use. Class 3 "Techies" (35.4%) had high online connectedness and relatively lower in-person connectedness. In multivariable modelling, Socialites had higher collectivism than Traditionalists, who had higher collectivism than Techies. Socialites also had higher annual incomes than other classes. Techies were more likely than Traditionalists to report recent serodiscordant or unknown condomless anal sex and HIV risk management practices (e.g., ask their partner's HIV status, get tested for HIV). Traditionalists on the other hand were less likely to practice HIV risk management and had lower HIV/AIDS stigma scores than Socialites. Further, Traditionalists were older, more likely to be partnered, and reported fewer male sex partners than men in other groups. These findings highlight how patterns of connectedness relate to GBM's risk management.

show abstract

Understanding HIV Risk Behavior from a Sociocultural Perspective

Cited by 17 publications

References 23 publications

Factors Associated with Antiretroviral Treatments Failure among HIV-Positive Patients in Congo: A Retrospective Cohort Study

Factors Associated with Antiretroviral Treatments Failure among HIV-Positive Patients in Congo: A Retrospective Cohort Study

The role of machine learning in HIV risk prediction

Patterns of Online and Offline Connectedness Among Gay, Bisexual, and Other Men Who Have Sex with Men

Contact Info

Product

Resources

About