Artificial Intelligence and Machine Learning for HIV Prevention: Emerging Approaches to Ending the Epidemic

Marcus, Julia L.; Sewell, Whitney; Balzer, Laura B.; Krakower, Douglas S.

doi:10.1007/s11904-020-00490-6

Cited by 82 publications

(56 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the recent advances in prediction tools and identification techniques in HIV statistical data [ 20 – 22 ], machine learning offers greater capability in processing huge amounts of data. Its recent application in the identification of potential candidates for preexposure prophylaxis (PrEP) in the USA and Denmark and a population-based research setting in Eastern Africa highlights some of its capabilities [ 23 ]. Klon et al used Laplacian-modified naïve Bayesian to identify active inhibitor compounds from a target database [ 24 ].…”

Section: Background Literaturementioning

confidence: 99%

Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa

Mutai

McSharry

Ngaruye

et al. 2021

BMC Med Res Methodol

View full text Add to dashboard Cite

Aim HIV prevention measures in sub-Saharan Africa are still short of attaining the UNAIDS 90–90-90 fast track targets set in 2014. Identifying predictors for HIV status may facilitate targeted screening interventions that improve health care. We aimed at identifying HIV predictors as well as predicting persons at high risk of the infection. Method We applied machine learning approaches for building models using population-based HIV Impact Assessment (PHIA) data for 41,939 male and 45,105 female respondents with 30 and 40 variables respectively from four countries in sub-Saharan countries. We trained and validated the algorithms on 80% of the data and tested on the remaining 20% where we rotated around the left-out country. An algorithm with the best mean f1 score was retained and trained on the most predictive variables. We used the model to identify people living with HIV and individuals with a higher likelihood of contracting the disease. Results Application of XGBoost algorithm appeared to significantly improve identification of HIV positivity over the other five algorithms by f1 scoring mean of 90% and 92% for males and females respectively. Amongst the eight most predictor features in both sexes were: age, relationship with family head, the highest level of education, highest grade at that school level, work for payment, avoiding pregnancy, age at the first experience of sex, and wealth quintile. Model performance using these variables increased significantly compared to having all the variables included. We identified five males and 19 females individuals that would require testing to find one HIV positive individual. We also predicted that 4·14% of males and 10.81% of females are at high risk of infection. Conclusion Our findings provide a potential use of the XGBoost algorithm with socio-behavioural-driven data at substantially identifying HIV predictors and predicting individuals at high risk of infection for targeted screening.

show abstract

Section: Background Literaturementioning

confidence: 99%

Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa

Mutai

McSharry

Ngaruye

et al. 2021

BMC Med Res Methodol

View full text Add to dashboard Cite

show abstract

“…There is an ongoing interest in this topic in the scientific community and the tendency is adding up. Moreover, reviews on different AI health applications are being published, such as cardiovascular health care [7], Human immunodeficiency virus (HIV) prevention [8], mental health [9], dementia [10], type 1 diabetes [11] and aging societies [12].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence in Pregnancy: A Scoping Review

et al. 2020

View full text Add to dashboard Cite

Artificial Intelligence has been widely applied to a majority of research areas, including health and medicine. Certain complications or disorders that can appear during pregnancy can endanger the life of both mother and fetus. There is enough scientific literature to support the idea that emotional aspects can be a relevant risk factor in pregnancy (such as anxiety, stress or depression, for instance). This paper presents a scoping review of the scientific literature from the past 12 years (2008)(2009)(2010)(2011)(2012)(2013)(2014)(2015)(2016)(2017)(2018)(2019)(2020) to identify which methodologies, techniques, algorithms and frameworks are used in Artificial Intelligence and Affective Computing for pregnancy health and well-being. The methodology proposed by Arksey and O'Malley, in conjunction with PRISMA-ScR framework has been used to create this review. Despite the relevance that emotional status can have as a risk factor during pregnancy, one of the main findings of this study is that there is still not a significant amount of literature on automatic analysis of emotion. Health enhancement and well-being for pregnant women can be achieved with artificial intelligence or affective computing based devices, hence future work on this topic is strongly suggested.

show abstract

“…First, comparison of the AUC-ROCs of the full model versus individual predictors or more parsimonious models will help differentiate key predictors for identifying risk groups and prioritising resources and the relative value of factors that are more invasive or intensive to collect. Use of machine-learning techniques has also showed a potential to improving prediction accuracy and can be incorporated into some prevention interventions [40]. Second, additional risk score development and validation using recent incidence data from wider geographic settings will increase the generalisability of HIV risk scores.…”

Section: Discussionmentioning

confidence: 99%

Risk scores for predicting HIV incidence among adult heterosexual populations in sub-Saharan Africa: a systematic review and meta-analysis

Jia

Eilerts

Edun

et al. 2021

Preprint

View full text Add to dashboard Cite

Introduction: Several HIV 'risk scores' have been developed to identify individuals for prioritised HIV prevention in sub-Saharan Africa. We systematically reviewed HIV risk scores to: (i) identify factors that consistently predicted incident HIV infection, (ii) review inclusion of community-level HIV risk in predictive models, and (iii) examine predictive performance. Methods: We systematically searched nine databases for studies developing and/or validating HIV risk scores among the general population in sub-Saharan Africa from database inception until February 15, 2021. Studies not prospectively observing seroconversion or recruiting only key populations were excluded. Record screening, data extraction, and critical appraisal were conducted in duplicate. We used random-effect meta-analysis to summarise hazard ratios and the area under the receiver-operating characteristic curve (AUC-ROC). Results: From 1563 initial search records, we identified 14 risk scores in 13 studies. Seven studies were among sexually active women using contraception enrolled in randomised-controlled trials, three among adolescent girls and young women (AGYW), and three among cohorts enrolling both men and women. Consistently identified HIV prognostic factors among women were younger age (pooled adjusted hazard ratio: 1.62 [95% Confidence Interval: 1.17, 2.23], compared to above-25), single/not cohabiting with primary partners (2.33 [1.73, 3.13]) and having sexually transmitted infections (STIs) at baseline (HSV-2: 1.67 [1.34, 2.09]; curable STIs: 1.45 [1.17; 1.79]). Among AGYW only STIs were consistently associated with higher incidence, but studies were limited (n=3). Community-level HIV prevalence or unsuppressed viral load strongly predicted incidence but were only considered in three of 11 multi-site studies. The AUC-ROC ranged from 0.56 to 0.79 on the model development sets. Only the VOICE score was externally validated by multiple studies, with pooled AUC-ROC 0.626 [0.588, 0.663] (I2: 64.02%). Conclusions: Younger age, non-cohabiting, and recent STIs were consistently identified as predicting future HIV infection. Both community HIV burden and individual factors should be considered to quantify HIV risk. However, HIV risk scores had only low-to-moderate discriminatory ability and uncertain generalizability outside of the study populations. Further evidence on the relative value of specific factors and data outside high-risk populations will help inform optimal implementation of risk scoring algorithms in HIV programmes. PROSPERO Number: CRD42021236367

show abstract

Artificial Intelligence and Machine Learning for HIV Prevention: Emerging Approaches to Ending the Epidemic

Cited by 82 publications

References 56 publications

Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa

Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa

Artificial Intelligence in Pregnancy: A Scoping Review

Risk scores for predicting HIV incidence among adult heterosexual populations in sub-Saharan Africa: a systematic review and meta-analysis

Contact Info

Product

Resources

About