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

Challenges and Opportunities in Big Data Science to Address Health Inequities and Focus the HIV Response

PURPOSE OF REVIEW

Big Data Science can be used to pragmatically guide the allocation of resources within the context of national HIV programs and inform priorities for intervention. In this review, we discuss the importance of grounding Big Data Science in the principles of equity and social justice to optimize the efficiency and effectiveness of the global HIV response.

RECENT FINDINGS

Social, ethical, and legal considerations of Big Data Science have been identified in the context of HIV research. However, efforts to mitigate these challenges have been limited. Consequences include disciplinary silos within the field of HIV, a lack of meaningful engagement and ownership with and by communities, and potential misinterpretation or misappropriation of analyses that could further exacerbate health inequities. Big Data Science can support the HIV response by helping to identify gaps in previously undiscovered or understudied pathways to HIV acquisition and onward transmission, including the consequences for health outcomes and associated comorbidities. However, in the absence of a guiding framework for equity, alongside meaningful collaboration with communities through balanced partnerships, a reliance on big data could continue to reinforce inequities within and across marginalized populations.

The synergy of artificial intelligence and personalized medicine for the enhanced diagnosis, treatment, and prevention of disease

INTRODUCTION

The completion of the Human Genome Project in 2003 marked the beginning of a transformative era in medicine. This milestone laid the foundation for personalized medicine, an innovative approach that customizes healthcare treatments.

CONTENT

Central to the advancement of personalized medicine is the understanding of genetic variations and their impact on drug responses. The integration of artificial intelligence (AI) into drug response trials has been pivotal in this domain. These technologies excel in handling large-scale genomic datasets and patient histories, significantly improving diagnostic accuracy, disease prediction and drug discovery. They are particularly effective in addressing complex diseases such as cancer and genetic disorders. Furthermore, the advent of wearable technology, when combined with AI, propels personalized medicine forward by offering real-time health monitoring, which is crucial for early disease detection and management.

SUMMARY

The integration of AI into personalized medicine represents a significant advancement in healthcare, promising more accurate diagnoses, effective treatment plans and innovative drug discoveries.

OUTLOOK

As technology continues to evolve, the role of AI in enhancing personalized medicine and transforming the healthcare landscape is expected to grow exponentially. This synergy between AI and healthcare holds great promise for the future, potentially revolutionizing the way healthcare is delivered and experienced.

Utilizing Big Data analytics and electronic health record data in HIV prevention, treatment, and care research: a literature review

Propelled by the transformative power of modern information and communication technologies, digitalization of data, and the increasing affordability of high-performance computing, Big Data science has brought forth revolutionary advancement in many areas of business, industry, health, and medicine. The HIV research and care service community is no exception to the benefits from the availability and utilization of Big Data analytics. Electronic health record (EHR) data (e.g., administrative and billing data, electronic medical records, or other digital records of information pertinent to individual or population health) are an essential source of health and disease outcome data because of the large amount of real-world, comprehensive, and often longitudinal data, which provide a good opportunity for leveraging advanced Big Data analytics in addressing challenges in HIV prevention, treatment, and care. This review focuses on studies that apply Big Data analytics to EHR data with aims to synthesize the HIV-related issues that EHR data studies can tackle, identify challenges in the utilization of EHR data in HIV research and practice, and discuss future needs and directions that can realize the promising potential role of Big Data in ending the HIV epidemic.

Assessing Patient Acceptance of an Automated Algorithm to Identify Ciswomen for HIV Pre-Exposure Prophylaxis

The use of HIV pre-exposure prophylaxis (PrEP) in cisgender women (ciswomen) lags far behind their need. Data elements from the electronic medical record (EMR), including diagnosis of a sexually transmitted infection (STI), can be incorporated into automated algorithms for identifying clients who are most vulnerable to HIV and would benefit from PrEP. However, it is unknown how women feel about the use of such technology. In this study, we assessed women's attitudes and opinions about an automated EMR-based HIV risk algorithm and determined if their perspectives varied by level of HIV risk. Respondents were identified using best practice alerts or referral to a clinic for STI symptoms from January to December 2021 in Chicago, IL. Participants were asked about HIV risk factors, their self-perceived HIV risk, and their thoughts regarding an algorithm to identify ciswomen who could benefit from PrEP. Most of the 112 women who completed the survey (85%) thought they were at low risk for HIV, despite high rates of STI diagnoses. The majority were comfortable with the use of this algorithm, but their comfort level dropped when asked about the algorithm identifying them specifically. Ciswomen had mixed feelings about the use of an automated HIV risk algorithm, citing it as a potentially helpful and empowering tool for women, yet raising concerns about invasion of privacy and potential racial bias. Clinics must balance the benefits of using an EMR-based algorithm for ciswomen with their concerns about privacy and bias to improve PrEP uptake among particularly vulnerable women.

PROVIDENT: Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island

BACKGROUND

Drug overdose persists as a leading cause of death in the United States, but resources to address it remain limited. As a result, health authorities must consider where to allocate scarce resources within their jurisdictions. Machine learning offers a strategy to identify areas with increased future overdose risk to proactively allocate overdose prevention resources. This modeling study is embedded in a randomized trial to measure the effect of proactive resource allocation on statewide overdose rates in Rhode Island (RI).

METHODS

We used statewide data from RI from 2016 to 2020 to develop an ensemble machine learning model predicting neighborhood-level fatal overdose risk. Our ensemble model integrated gradient boosting machine and super learner base models in a moving window framework to make predictions in 6-month intervals. Our performance target, developed a priori with the RI Department of Health, was to identify the 20% of RI neighborhoods containing at least 40% of statewide overdose deaths, including at least one neighborhood per municipality. The model was validated after trial launch.

RESULTS

Our model selected priority neighborhoods capturing 40.2% of statewide overdose deaths during the test periods and 44.1% of statewide overdose deaths during validation periods. Our ensemble outperformed the base models during the test periods and performed comparably to the best-performing base model during the validation periods.

CONCLUSIONS

We demonstrated the capacity for machine learning models to predict neighborhood-level fatal overdose risk to a degree of accuracy suitable for practitioners. Jurisdictions may consider predictive modeling as a tool to guide allocation of scarce resources.

Addressing Unmet PrEP Needs in Women: Impact of a Laboratory-Driven Protocol at an Urban, Essential Hospital

Background

HIV pre-exposure prophylaxis (PrEP) uptake in women remains low. We developed a laboratory result-driven protocol to link women with a positive bacterial sexually transmitted infection (STI) to HIV PrEP at an urban safety-net hospital.

Methods

Electronic health records of women with positive chlamydia, gonorrhea, and/or syphilis tests were reviewed, and those eligible for PrEP were referred for direct or primary care provider-driven outreach. We assessed the proportion of women with STIs who received PrEP offers, acceptance, and prescriptions before (July 1, 2018-December 31, 2018) and after (January 1, 2019-June 30, 2020) implementation to evaluate changes in the delivery of key elements of the PrEP care cascade (ie, PrEP offers, acceptance, and prescribing) for women with STIs after protocol implementation.

Results

The proportion of women who received PrEP offers increased from 7.6% to 17.6% (P < .001). After multivariable adjustment, only the postintervention period was associated with PrEP offers (odds ratio [OR], 2.49; 95% CI, 1.68-3.68). In subgroup analyses, PrEP offers increased significantly among non-Hispanic Black (OR, 2.75; 95% CI, 1.65-4.58) and Hispanic (OR, 5.34; 95% CI, 1.77-16.11) women but not among non-Hispanic White women (OR, 1.49; 95% CI, 0.54-4.05). Significant changes in PrEP acceptance and prescriptions were not observed in the sample overall.

Conclusions

A laboratory result-driven protocol was associated with a significant increase in PrEP offers to Black and Hispanic women with STI. These results provide concrete suggestions for health systems seeking to increase PrEP access and equity among women.

Generalizable pipeline for constructing HIV risk prediction models across electronic health record systems

OBJECTIVE

The HIV epidemic remains a significant public health issue in the United States. HIV risk prediction models could be beneficial for reducing HIV transmission by helping clinicians identify patients at high risk for infection and refer them for testing. This would facilitate initiation on treatment for those unaware of their status and pre-exposure prophylaxis for those uninfected but at high risk. Existing HIV risk prediction algorithms rely on manual construction of features and are limited in their application across diverse electronic health record systems. Furthermore, the accuracy of these models in predicting HIV in females has thus far been limited.

MATERIALS AND METHODS

We devised a pipeline for automatic construction of prediction models based on automatic feature engineering to predict HIV risk and tested our pipeline on a local electronic health records system and a national claims data. We also compared the performance of general models to female-specific models.

RESULTS

Our models obtain similarly good performance on both health record datasets despite difference in represented populations and data availability (AUC = 0.87). Furthermore, our general models obtain good performance on females but are also improved by constructing female-specific models (AUC between 0.81 and 0.86 across datasets).

DISCUSSION AND CONCLUSIONS

We demonstrated that flexible construction of prediction models performs well on HIV risk prediction across diverse health records systems and perform as well in predicting HIV risk in females, making deployment of such models into existing health care systems tangible.

Testing the Feasibility and Acceptability of Using an Artificial Intelligence Chatbot to Promote HIV Testing and Pre-Exposure Prophylaxis in Malaysia: Mixed Methods Study

BACKGROUND

The HIV epidemic continues to grow fastest among men who have sex with men (MSM) in Malaysia in the presence of stigma and discrimination. Engaging MSM on the internet using chatbots supported through artificial intelligence (AI) can potentially help HIV prevention efforts. We previously identified the benefits, limitations, and preferred features of HIV prevention AI chatbots and developed an AI chatbot prototype that is now tested for feasibility and acceptability.

OBJECTIVE

This study aims to test the feasibility and acceptability of an AI chatbot in promoting the uptake of HIV testing and pre-exposure prophylaxis (PrEP) in MSM.

METHODS

We conducted beta testing with 14 MSM from February to April 2022 using Zoom (Zoom Video Communications, Inc). Beta testing involved 3 steps: a 45-minute human-chatbot interaction using the think-aloud method, a 35-minute semistructured interview, and a 10-minute web-based survey. The first 2 steps were recorded, transcribed verbatim, and analyzed using the Unified Theory of Acceptance and Use of Technology. Emerging themes from the qualitative data were mapped on the 4 domains of the Unified Theory of Acceptance and Use of Technology: performance expectancy, effort expectancy, facilitating conditions, and social influence.

RESULTS

Most participants (13/14, 93%) perceived the chatbot to be useful because it provided comprehensive information on HIV testing and PrEP (performance expectancy). All participants indicated that the chatbot was easy to use because of its simple, straightforward design and quick, friendly responses (effort expectancy). Moreover, 93% (13/14) of the participants rated the overall chatbot quality as high, and all participants perceived the chatbot as a helpful tool and would refer it to others. Approximately 79% (11/14) of the participants agreed they would continue using the chatbot. They suggested adding a local language (ie, Bahasa Malaysia) to customize the chatbot to the Malaysian context (facilitating condition) and suggested that the chatbot should also incorporate more information on mental health, HIV risk assessment, and consequences of HIV. In terms of social influence, all participants perceived the chatbot as helpful in avoiding stigma-inducing interactions and thus could increase the frequency of HIV testing and PrEP uptake among MSM.

CONCLUSIONS

The current AI chatbot is feasible and acceptable to promote the uptake of HIV testing and PrEP. To ensure the successful implementation and dissemination of AI chatbots in Malaysia, they should be customized to communicate in Bahasa Malaysia and upgraded to provide other HIV-related information to improve usability, such as mental health support, risk assessment for sexually transmitted infections, AIDS treatment, and the consequences of contracting HIV.

A conceptual analysis of SBIRT implementation alongside the continuum of PrEP awareness: domains of fit and feasibility

Screening, Brief Intervention, and Referral to Treatment (SBIRT) is a supplementary intervention that can be incorporated into the Pre-Exposure Prophylaxis (PrEP) Care Continuum, complementing initiatives and endeavors focused on Human Immunodeficiency Virus (HIV) prevention in clinical care and community-based work. Referencing the Transtheoretical Model of Change and the PrEP Awareness Continuum, this conceptual analysis highlights how SBIRT amplifies ongoing HIV prevention initiatives and presents a distinct chance to address identified gaps. SBIRT's mechanisms show promise of fit and feasibility through (a) implementing universal Screening (S), (b) administering a Brief Intervention (BI) grounded in motivational interviewing aimed at assisting individuals in recognizing the significance of PrEP in their lives, (c) providing an affirming and supportive Referral to Treatment (RT) to access clinical PrEP care, and (d) employing client-centered and destigmatized approaches. SBIRT is uniquely positioned to help address the complex challenges facing PrEP awareness and initiation efforts. Adapting the SBIRT model to integrate and amplify HIV prevention efforts merits further examination.

Machine Learning Approach for Analyzing 3-Year Outcomes of Patients with Brain Arteriovenous Malformation (AVM) after Stereotactic Radiosurgery (SRS)

A cerebral arteriovenous malformation (AVM) is a tangle of abnormal blood vessels that irregularly connects arteries and veins. Stereotactic radiosurgery (SRS) has been shown to be an effective treatment for AVM patients, but the factors associated with AVM obliteration remains a matter of debate. In this study, we aimed to develop a model that can predict whether patients with AVM will be cured 36 months after intervention by means of SRS and identify the most important predictors that explain the probability of being cured. A machine learning (ML) approach was applied using decision tree (DT) and logistic regression (LR) techniques on historical data (sociodemographic, clinical, treatment, angioarchitecture, and radiosurgery procedure) of 202 patients with AVM who underwent SRS at the Instituto de Radiocirugía del Perú (IRP) between 2005 and 2018. The LR model obtained the best results for predicting AVM cure with an accuracy of 0.92, sensitivity of 0.93, specificity of 0.89, and an area under the curve (AUC) of 0.98, which shows that ML models are suitable for predicting the prognosis of medical conditions such as AVM and can be a support tool for medical decision-making. In addition, several factors were identified that could explain whether patients with AVM would be cured at 36 months with the highest likelihood: the location of the AVM, the occupation of the patient, and the presence of hemorrhage.

The Role and Impact of Artificial Intelligence in Addressing Sexually Transmitted Infections, Nonvenereal Genital Diseases, Sexual Health, and Wellness

The potential of artificial intelligence (AI) in diagnosing and managing sexually transmitted infections (STIs), nonvenereal genital diseases, and overall sexual health is immense. AI shows promise in STI screening and diagnosis through image recognition and patient data analysis, potentially increasing diagnostic accuracy while ensuring inclusivity. AI can fuel the transformation of e-health and direct-to-consumer services, enhancing targeted screening and personalized interventions while improving the user-friendliness of services. There is a significant role for AI in sexual education, particularly its use in interactive, empathetic chatbots. AI's integration into health care as a decision support tool for primary health-care providers can boost real-time diagnostic accuracy. Furthermore, AI's use in big data can enhance real-time epidemiology, predictive analysis, and directed interventions at population levels. However, challenges such as real-world diagnostic accuracy, liability, privacy concerns, and ethical dilemmas persist. Future directions include an emphasis on inclusivity, language accommodation, and swift research-to-practice transitions. Collaboration among policymakers, researchers, and health-care providers is needed to leverage AI's transformative potential in sexual health.

"But can chatbots understand sex?" Attitudes towards artificial intelligence chatbots amongst sexual and reproductive health professionals: An exploratory mixed-methods study

BACKGROUND

Artificial Intelligence (AI)-enabled chatbots can offer anonymous education about sexual and reproductive health (SRH). Understanding chatbot acceptability and feasibility allows the identification of barriers to the design and implementation.

METHODS

In 2020, we conducted an online survey and qualitative interviews with SRH professionals recruited online to explore the views on AI, automation and chatbots. Qualitative data were analysed thematically.

RESULTS

Amongst 150 respondents (48% specialist doctor/consultant), only 22% perceived chatbots as effective and 24% saw them as ineffective for SRH advice [Mean = 2.91, SD = 0.98, range: 1-5]. Overall, there were mixed attitudes towards SRH chatbots [Mean = 4.03, SD = 0.87, range: 1-7]. Chatbots were most acceptable for appointment booking, general sexual health advice and signposting, but not acceptable for safeguarding, virtual diagnosis, and emotional support. Three themes were identified: "Moving towards a 'digital' age'", "AI improving access and service efficacy", and "Hesitancy towards AI".

CONCLUSIONS

Half of SRH professionals were hesitant about the use of chatbots in SRH services, attributed to concerns about patient safety, and lack of familiarity with this technology. Future studies should explore the role of AI chatbots as supplementary tools for SRH promotion. Chatbot designers need to address the concerns of health professionals to increase acceptability and engagement with AI-enabled services.

A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

Background

Artificial intelligence (AI) is a broad outlet of computer science aimed at constructing machines capable of simulating and performing tasks usually done by human beings. The aim of this scoping review is to map existing evidence on the use of AI in the delivery of medical care.

Methods

We searched PubMed and Scopus in March 2022, screened identified records for eligibility, assessed full texts of potentially eligible publications, and extracted data from included studies in duplicate, resolving differences through discussion, arbitration, and consensus. We then conducted a narrative synthesis of extracted data.

Results

Several AI methods have been used to detect, diagnose, classify, manage, treat, and monitor the prognosis of various health issues. These AI models have been used in various health conditions, including communicable diseases, non-communicable diseases, and mental health.

Conclusions

Presently available evidence shows that AI models, predominantly deep learning, and machine learning, can significantly advance medical care delivery regarding the detection, diagnosis, management, and monitoring the prognosis of different illnesses.

Development and validation of a prediction tool to support engagement in HIV care among young people ages 10-24 years in Kenya

INTRODUCTION

Loss to follow-up (LTFU) among adolescents and young adults living with HIV (AYALWH) is a barrier to optimal health and HIV services. We developed and validated a clinical prediction tool to identify AYALWH at risk of LTFU.

METHODS

We used electronic medical records (EMR) of AYALWH ages 10 to 24 in HIV care at 6 facilities in Kenya and surveys from a subset of participants. Early LTFU was defined as >30 days late for a scheduled visit in the last 6 months, which accounts for clients with multi-month refills. We developed a tool combining surveys with EMR ('survey-plus-EMR tool'), and an 'EMR-alone' tool to predict high, medium, and low risk of LTFU. The survey-plus-EMR tool included candidate sociodemographics, partnership status, mental health, peer support, any unmet clinic needs, WHO stage, and time in care variables for tool development, while the EMR-alone included clinical and time in care variables only. Tools were developed in a 50% random sample of the data and internally validated using 10-fold cross-validation of the full sample. Tool performance was evaluated using Hazard Ratios (HR), 95% Confidence Intervals (CI), and area under the curve (AUC) ≥ 0.7 for good performance and ≥0.60 for modest performance.

RESULTS

Data from 865 AYALWH were included in the survey-plus-EMR tool and early LTFU was (19.2%, 166/865). The survey-plus-EMR tool ranged from 0 to 4, including PHQ-9 ≥5, lack of peer support group attendance, and any unmet clinical need. High (3 or 4) and medium (2) prediction scores were associated with greater risk of LTFU (high, 29.0%, HR 2.16, 95%CI: 1.25-3.73; medium, 21.4%, HR 1.52, 95%CI: 0.93-2.49, global p-value = 0.02) in the validation dataset. The 10-fold cross validation AUC was 0.66 (95%CI: 0.63-0.72). Data from 2,696 AYALWH were included in the EMR-alone tool and early LTFU was 28.6% (770/2,696). In the validation dataset, high (score = 2, LTFU = 38.5%, HR 2.40, 95%CI: 1.17-4.96) and medium scores (1, 29.6%, HR 1.65, 95%CI: 1.00-2.72) predicted significantly higher LTFU than low-risk scores (0, 22.0%, global p-value = 0.03). Ten-fold cross-validation AUC was 0.61 (95%CI: 0.59-0.64).

CONCLUSIONS

Clinical prediction of LTFU was modest using the surveys-plus-EMR tool and the EMR-alone tool, suggesting limited use in routine care. However, findings may inform future prediction tools and intervention targets to reduce LTFU among AYALWH.

A Transgender Chatbot (Amanda Selfie) to Create Pre-exposure Prophylaxis Demand Among Adolescents in Brazil: Assessment of Acceptability, Functionality, Usability, and Results

BACKGROUND

HIV incidence rates have increased in adolescent men who have sex with men (AMSM) and adolescent transgender women (ATGW). Thus, it is essential to promote access to HIV prevention, including pre-exposure prophylaxis (PrEP), among these groups. Moreover, using artificial intelligence and online social platforms to create demand and access to health care services are essential tools for adolescents and youth.

OBJECTIVE

This study aims to describe the participative process of developing a chatbot using artificial intelligence to create demand for PrEP use among AMSM and ATGW in Brazil. Furthermore, it analyzes the chatbot's acceptability, functionality, and usability and its results on the demand creation for PrEP.

METHODS

The chatbot Amanda Selfie integrates the demand creation strategies based on social networks (DCSSNs) of the PrEP1519 study. She was conceived as a Black transgender woman and to function as a virtual peer educator. The development process occurred in 3 phases (conception, trial, and final version) and lasted 21 months. A mixed methodology was used for the evaluations. Qualitative approaches, such as in-depth adolescent interviews, were used to analyze acceptability and usability, while quantitative methods were used to analyze the functionality and result of the demand creation for PrEP based on interactions with Amanda and information from health care services about using PrEP. To evaluate Amanda's result on the demand creation for PrEP, we analyzed sociodemographic profiles of adolescents who interacted at least once with her and developed a cascade model containing the number of people at various stages between the first interaction and initiation of PrEP (PrEP uptake). These indicators were compared with other DCSs developed in the PrEP1519 study using chi-square tests and residual analysis (P=.05).

RESULTS

Amanda Selfie was well accepted as a peer educator, clearly and objectively communicating on topics such as gender identity, sexual experiences, HIV, and PrEP. The chatbot proved appropriate for answering questions in an agile and confidential manner, using the language used by AMSM and ATGW and with a greater sense of security and less judgment. The interactions with Amanda Selfie combined with a health professional were well evaluated and improved the appointment scheduling. The chatbot interacted with most people (757/1239, 61.1%) reached by the DCSSNs. However, when compared with the other DCSSNs, Amanda was not efficient in identifying AMSM/ATGW (359/482, 74.5% vs 130/757, 17.2% of total interactions, respectively) and in PrEP uptake (90/359, 25.1% vs 19/130, 14.6%). The following profiles were associated (P<.001) with Amanda Selfie's demand creation, when compared with other DCS: ATGW and adolescents with higher levels of schooling and White skin color.

CONCLUSIONS

Using a chatbot to create PrEP demand among AMSM and ATGW was well accepted, especially for ATGW with higher levels of schooling. A complimentary dialog with a health professional increased PrEP uptake, although it remained lower than the results of the other DCSSNs.

Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms

Inadequate knowledge is one of the principal obstacles for preventing HIV/AIDS spread. Worldwide, it is reported that adolescents and young people have a higher vulnerability of being infected. Thus, the need to understand youths' knowledge towards HIV/AIDS becomes crucial. This study aimed to identify the determinants and develop a predictive model to estimate HIV/AIDS knowledge among this target population in Peru. Data from the 2019 DHS Survey were used. The software RStudio and RapidMiner were used for quasi-binomial logistic regression and computational model building, respectively. Five classification algorithms were considered for model development and their performance was assessed using accuracy, sensitivity, specificity, FPR, FNR, Cohen's kappa, F1 score and AUC. The results revealed an association between 14 socio-demographic, economic and health factors and HIV/AIDS knowledge. The accuracy levels were estimated between 59.47 and 64.30%, with the random forest model showing the best performance (64.30%). Additionally, the best classifier showed that the gender of the respondent, area of residence, wealth index, region of residence, interviewee's age, highest educational level, ethnic self-perception, having heard about HIV/AIDS in the past, the performance of an HIV/AIDS screening test and mass media access have a major influence on HIV/AIDS knowledge prediction. The results suggest the usefulness of the associations found and the random forest model as a predictor of knowledge of HIV/AIDS and may aid policy makers to guide and reinforce the planning and implementation of healthcare strategies.

Potential application of conversational agents in HIV testing uptake among high-risk populations

Human Immunodeficiency Virus (HIV) continues to be a significant public health problem, with ~1.2 million Americans living with HIV and ~14% unaware of their infection. The Centers for Disease Control and Prevention recommends that patients 13 to 64 years of age get screened for HIV at least once, and those with higher risk profiles screen at least annually. Unfortunately, screening rates are below recommendations for high-risk populations, leading to problems of delayed diagnosis. Novel technologies have been applied in HIV research to increase prevention, testing and treatment. Conversational agents, with potential for integrating artificial intelligence and natural language processing, may offer an opportunity to improve outreach to these high-risk populations. The feasibility, accessibility and acceptance of using conversational agents for HIV testing outreach is important to evaluate, especially amidst a global coronavirus disease 2019 pandemic when clinical services have been drastically affected. This viewpoint explores the application of a conversational agent in increasing HIV testing among high-risk populations.

Addressing Health Inequities in Digital Clinical Trials: A Review of Challenges and Solutions From the Field of HIV Research

Clinical trials are considered the gold standard for establishing efficacy of health interventions, thus determining which interventions are brought to scale in health care and public health programs. Digital clinical trials, broadly defined as trials that have partial to full integration of technology across implementation, interventions, and/or data collection, are valued for increased efficiencies as well as testing of digitally delivered interventions. Although recent reviews have described the advantages and disadvantages of and provided recommendations for improving scientific rigor in the conduct of digital clinical trials, few to none have investigated how digital clinical trials address the digital divide, whether they are equitably accessible, and if trial outcomes are potentially beneficial only to those with optimal and consistent access to technology. Human immunodeficiency virus (HIV), among other health conditions, disproportionately affects socially and economically marginalized populations, raising questions of whether interventions found to be efficacious in digital clinical trials and subsequently brought to scale will sufficiently and consistently reach and provide benefit to these populations. We reviewed examples from HIV research from across geographic settings to describe how digital clinical trials can either reproduce or mitigate health inequities via the design and implementation of the digital clinical trials and, ultimately, the programs that result. We discuss how digital clinical trials can be intentionally designed to prevent inequities, monitor ongoing access and utilization, and assess for differential impacts among subgroups with diverse technology access and use. These findings can be generalized to many other health fields and are practical considerations for donors, investigators, reviewers, and ethics committees engaged in digital clinical trials.

Characterizing the Impact of the COVID-19 Pandemic on HIV PrEP care: A Review and Synthesis of the Literature

The global COVID-19 pandemic and associated lockdown measures have caused disruptions to sexual health services and created additional barriers to the continuity of HIV pre-exposure prophylaxis (PrEP) among key populations. This review provides an examination of the influences of the pandemic on engagement in the PrEP care continuum. Using the PRISMA guideline, 46 studies were included in this review and the synthesis. Most of the studies were conducted in high-income settings through quantitative analysis. A majority of studies examining the changes in PrEP use suggested a decline or discontinuation in PrEP uptake during the pandemic. The most common reasons for stopping using PrEP were perceived barriers to PrEP-related care, having reduced sexual behaviors and fewer sexual partners, and reduced perceived risk of HIV infection. Limited studies documenting an increase in PrEP uptake were all in specific PrEP optimizing programs. During the pandemic, there is also an emerging trend of switching to on-demand PrEP from daily oral PrEP. Future studies should understand the mechanism of strategies that facilitated the improvements during the pandemic. PrEP implementation programs should consider alternative PrEP modalities and provide consistent and comprehensive knowledge about correct information.

Application of machine learning algorithms for localized syringe services program policy implementation - Florida, 2017

BACKGROUND

People who inject drugs (PWID) are at an amplified vulnerability for experiencing a multitude of harms related to their substance use, including viral (e.g. HIV, Hepatitis C) and bacterial infections (e.g. endocarditis). Implementation of evidence-based interventions, such as syringe services programs (SSPs), remains imperative, particularly in locations at an increased risk of HIV outbreaks. This study aims to identify communities in Florida that are high-priority locations for SSP implementation by examining state-level data related to the substance use and overdose crises.

METHODS

State-level surveillance data were aggregated at the ZIP Code Tabulation Area (ZCTA) (n = 983) for 2017. We used confirmed cases of acute HCV infection as a proxy of injection drug use. Least Absolute Selection and Shrinkage Operator (LASSO) regression was used to develop a machine learning model to identify significant indicators of acute HCV infection and high-priority areas for SSP implementation due to their increased vulnerability to an HIV outbreak.

RESULTS

The final model retained three variables of importance: (1) the number of drug-associated skin and soft tissue infection hospitalizations, (2) the number of chronic HCV infections in people aged 18-39, and 3) the number of drug-associated endocarditis hospitalizations. High-priority SSP implementation locations were identified in both urban and rural communities outside of current Ending the HIV Epidemic counties.

CONCLUSION

SSPs are long researched, safe, and effective evidence-based programs that offer a variety of services that reduce disease transmission and assist with combating the overdose crisis. Opportunities to increase services in needed regions across the state now exist in Florida as supported by the expansion of the Infectious Disease Elimination Act of 2019. This study provides details where potential areas of concern may be and highlights regions where future evidence-based harm reduction programs, such as SSPs, would be useful to reduce opioid overdoses and disease transmission among PWID.Key messagesThe rate of acute HCV in Florida in 2017 was 1.9 per 100,000, nearly twice the national average.Serious injection related infections among PWID are significant indicators of acute HCV infection.High-priority SSP implementation locations in Florida were identified in both urban and rural communities, including those outside of current Ending the HIV Epidemic counties.

Artificial intelligence and health inequities in primary care: a systematic scoping review and framework

OBJECTIVE

Artificial intelligence (AI) will have a significant impact on healthcare over the coming decade. At the same time, health inequity remains one of the biggest challenges. Primary care is both a driver and a mitigator of health inequities and with AI gaining traction in primary care, there is a need for a holistic understanding of how AI affect health inequities, through the act of providing care and through potential system effects. This paper presents a systematic scoping review of the ways AI implementation in primary care may impact health inequity.

DESIGN

Following a systematic scoping review approach, we searched for literature related to AI, health inequity, and implementation challenges of AI in primary care. In addition, articles from primary exploratory searches were added, and through reference screening.The results were thematically summarised and used to produce both a narrative and conceptual model for the mechanisms by which social determinants of health and AI in primary care could interact to either improve or worsen health inequities.Two public advisors were involved in the review process.

ELIGIBILITY CRITERIA

Peer-reviewed publications and grey literature in English and Scandinavian languages.

INFORMATION SOURCES

PubMed, SCOPUS and JSTOR.

RESULTS

A total of 1529 publications were identified, of which 86 met the inclusion criteria. The findings were summarised under six different domains, covering both positive and negative effects: (1) access, (2) trust, (3) dehumanisation, (4) agency for self-care, (5) algorithmic bias and (6) external effects. The five first domains cover aspects of the interface between the patient and the primary care system, while the last domain covers care system-wide and societal effects of AI in primary care. A graphical model has been produced to illustrate this. Community involvement throughout the whole process of designing and implementing of AI in primary care was a common suggestion to mitigate the potential negative effects of AI.

CONCLUSION

AI has the potential to affect health inequities through a multitude of ways, both directly in the patient consultation and through transformative system effects. This review summarises these effects from a system tive and provides a base for future research into responsible implementation.

Machine learning with routine electronic medical record data to identify people at high risk of disengagement from HIV care in Tanzania

Machine learning methods for health care delivery optimization have the potential to improve retention in HIV care, a critical target of global efforts to end the epidemic. However, these methods have not been widely applied to medical record data in low- and middle-income countries. We used an ensemble decision tree approach to predict risk of disengagement from HIV care (missing an appointment by ≥28 days) in Tanzania. Our approach used routine electronic medical records (EMR) from the time of antiretroviral therapy (ART) initiation through 24 months of follow-up for 178 adults (63% female). We compared prediction accuracy when using EMR-based predictors alone and in combination with sociodemographic survey data collected by a research study. Models that included only EMR-based indicators and incorporated changes across past clinical visits achieved a mean accuracy of 75.2% for predicting risk of disengagement in the next 6 months, with a mean sensitivity of 54.7% for targeting the 30% highest-risk individuals. Additionally including survey-based predictors only modestly improved model performance. The most important variables for prediction were time-varying EMR indicators including changes in treatment status, body weight, and WHO clinical stage. Machine learning methods applied to existing EMR data in resource-constrained settings can predict individuals' future risk of disengagement from HIV care, potentially enabling better targeting and efficiency of interventions to promote retention in care.

Public Health Implications of Adapting HIV Pre-exposure Prophylaxis Programs for Virtual Service Delivery in the Context of the COVID-19 Pandemic: Systematic Review

BACKGROUND

The novel coronavirus disease COVID-19 caused by SARS-CoV-2 threatens to disrupt global progress toward HIV epidemic control. Opportunities exist to leverage ongoing public health responses to mitigate the impacts of COVID-19 on HIV services, and novel approaches to care provision might help address both epidemics.

OBJECTIVE

As the COVID-19 pandemic continues, novel approaches to maintain comprehensive HIV prevention service delivery are needed. The aim of this study was to summarize the related literature to highlight adaptations that could address potential COVID-19-related service interruptions.

METHODS

We performed a systematic review and searched six databases, OVID/Medline, Scopus, Cochrane Library, CINAHL, PsycINFO, and Embase, for studies published between January 1, 2010, and October 26, 2021, related to recent technology-based interventions for virtual service delivery. Search terms included "telemedicine," "telehealth," "mobile health," "eHealth," "mHealth," "telecommunication," "social media," "mobile device," and "internet," among others. Of the 6685 abstracts identified, 1259 focused on HIV virtual service delivery, 120 of which were relevant for HIV prevention efforts; 48 pertained to pre-exposure prophylaxis (PrEP) and 19 of these focused on evaluations of interventions for the virtual service delivery of PrEP. Of the 16 systematic reviews identified, three were specific to PrEP. All 35 papers were reviewed for outcomes of efficacy, feasibility, and/or acceptability. Limitations included heterogeneity of the studies' methodological approaches and outcomes; thus, a meta-analysis was not performed. We considered the evidence-based interventions found in our review and developed a virtual service delivery model for HIV prevention interventions. We also considered how this platform could be leveraged for COVID-19 prevention and care.

RESULTS

We summarize 19 studies of virtual service delivery of PrEP and 16 relevant reviews. Examples of technology-based interventions that were effective, feasible, and/or acceptable for PrEP service delivery include: use of SMS, internet, and smartphone apps such as iText (50% [95% CI 16%-71%] reduction in discontinuation of PrEP) and PrEPmate (OR 2.62, 95% CI 1.24-5.5.4); telehealth and eHealth platforms for virtual visits such as PrEPTECH and IowaTelePrEP; and platforms for training of health care workers such as Extension for Community Healthcare Outcomes (ECHO). We suggest a virtual service delivery model for PrEP that can be leveraged for COVID-19 using the internet and social media for demand creation, community-based self-testing, telehealth platforms for risk assessment and follow-up, applications for support groups and adherence/appointment reminders, and applications for monitoring.

CONCLUSIONS

Innovations in the virtual service provision of PrEP occurred before COVID-19 but have new relevance during the COVID-19 pandemic. The innovations we describe might strengthen HIV prevention service delivery during the COVID-19 pandemic and in the long run by engaging traditionally hard-to-reach populations, reducing stigma, and creating a more accessible health care platform. These virtual service delivery platforms can mitigate the impacts of the COVID-19 pandemic on HIV services, which can be leveraged to facilitate COVID-19 pandemic control now and for future responses.

Current Artificial Intelligence (AI) Techniques, Challenges, and Approaches in Controlling and Fighting COVID-19: A Review

SARS-CoV-2 (COVID-19) has been one of the worst global health crises in the 21st century. The currently available rollout vaccines are not 100% effective for COVID-19 due to the evolving nature of the virus. There is a real need for a concerted effort to fight the virus, and research from diverse fields must contribute. Artificial intelligence-based approaches have proven to be significantly effective in every branch of our daily lives, including healthcare and medical domains. During the early days of this pandemic, artificial intelligence (AI) was utilized in the fight against this virus outbreak and it has played a major role in containing the spread of the virus. It provided innovative opportunities to speed up the development of disease interventions. Several methods, models, AI-based devices, robotics, and technologies have been proposed and utilized for diverse tasks such as surveillance, spread prediction, peak time prediction, classification, hospitalization, healthcare management, heath system capacity, etc. This paper attempts to provide a quick, concise, and precise survey of the state-of-the-art AI-based techniques, technologies, and datasets used in fighting COVID-19. Several domains, including forecasting, surveillance, dynamic times series forecasting, spread prediction, genomics, compute vision, peak time prediction, the classification of medical imaging-including CT and X-ray and how they can be processed-and biological data (genome and protein sequences) have been investigated. An overview of the open-access computational resources and platforms is given and their useful tools are pointed out. The paper presents the potential research areas in AI and will thus encourage researchers to contribute to fighting against the virus and aid global health by slowing down the spread of the virus. This will be a significant contribution to help minimize the high death rate across the globe.

Effectiveness of an electronic health record model for HIV pre-exposure prophylaxis

Pre-exposure prophylaxis (PrEP) to prevent human immunodeficiency virus (HIV) is extremely effective when taken correctly, though grossly under-prescribed for at-risk patients. We initiated a best practice advisory (BPA) in the Epic electronic medical record (EMR) to identify patients who met criteria for PrEP use. We evaluated this model to determine its effectiveness in identifying patients and its use by providers for increasing prescription of PrEP. The BPA fired 145 times with five total new PrEP prescriptions. Over half of the patients identified were cisgender women, a group that is both under prescribed PrEP and missed by prior EMR PrEP algorithms. Half of the patients were African American, a group at high risk of HIV infection. Though the model was effective at identifying patients, provider initiation of PrEP or acknowledgment of the BPA was low. Further education of providers regarding PrEP usage and expansion of BPA messages are needed to increase rates of PrEP initiation.

A Machine-Learning-Based Risk-Prediction Tool for HIV and Sexually Transmitted Infections Acquisition over the Next 12 Months

Background: More than one million people acquire sexually transmitted infections (STIs) every day globally. It is possible that predicting an individual’s future risk of HIV/STIs could contribute to behaviour change or improve testing. We developed a series of machine learning models and a subsequent risk-prediction tool for predicting the risk of HIV/STIs over the next 12 months. Methods: Our data included individuals who were re-tested at the clinic for HIV (65,043 consultations), syphilis (56,889 consultations), gonorrhoea (60,598 consultations), and chlamydia (63,529 consultations) after initial consultations at the largest public sexual health centre in Melbourne from 2 March 2015 to 31 December 2019. We used the receiver operating characteristic (AUC) curve to evaluate the model’s performance. The HIV/STI risk-prediction tool was delivered via a web application. Results: Our risk-prediction tool had an acceptable performance on the testing datasets for predicting HIV (AUC = 0.72), syphilis (AUC = 0.75), gonorrhoea (AUC = 0.73), and chlamydia (AUC = 0.67) acquisition. Conclusions: Using machine learning techniques, our risk-prediction tool has acceptable reliability in predicting HIV/STI acquisition over the next 12 months. This tool may be used on clinic websites or digital health platforms to form part of an intervention tool to increase testing or reduce future HIV/STI risk.

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

Introduction

Several HIV risk scores have been developed to identify individuals for prioritized HIV prevention in sub‐Saharan Africa. We systematically reviewed HIV risk scores to: (1) identify factors that consistently predicted incident HIV infection, (2) review inclusion of community‐level HIV risk in predictive models and (3) examine predictive performance.

Methods

We searched nine databases from inception until 15 February 2021 for studies developing and/or validating HIV risk scores among the heterosexual adult population in sub‐Saharan Africa. 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‐effects meta‐analysis to summarize 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 contraceptives enrolled in randomized‐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 was only considered in 3 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, limiting their programmatic utility. Further evidence on the relative value of specific risk factors, studies populations not restricted to “at‐risk” individuals and data outside South Africa will improve the evidence base for risk differentiation in HIV prevention programmes.

PROSPERO Number

CRD42021236367

A Primary Care Intervention to Increase HIV Pre-Exposure Prophylaxis (PrEP) Uptake in Patients with Syphilis

Identifying candidates for HIV pre-exposure prophylaxis (PrEP) is a barrier to improving PrEP uptake in priority populations. Syphilis infection is an indication for PrEP in all individuals and can be easily assessed by primary care providers (PCP) and health systems. This retrospective study evaluated the impact of a multidisciplinary provider outreach intervention on PrEP uptake in patients with a positive syphilis test result in a safety-net hospital-based primary care practice. The PCPs of PrEP-eligible patients with a positive syphilis result were notified via the electronic medical record (EMR) about potential PrEP eligibility and institutional HIV PrEP resources. Rates of PrEP offers and prescriptions were compared in the pre (8/1/2018-12/31/2018, n = 60) and post (1/1/2019-5/31/2019, n = 86) intervention periods. Secondary analyzes evaluated receipt of appropriate syphilis treatment and contemporaneous screening for HIV, gonorrhea, and chlamydia. No significant differences in the overall proportion of patients offered (15% vs 19%) and prescribed (7% vs 5%) PrEP were observed between the pre- and post-periods. Overall, 7% of positive tests represented infectious syphilis. The rate of appropriate syphilis treatment was equivalent (57% vs 56%) and contemporaneous screening for other sexually transmitted infections was suboptimal across the entire study period. Although any positive syphilis test may be an easily abstracted metric from the EMR, this approach was inclusive of many patients without current HIV risk and did not increase PrEP uptake significantly. Future research into population health approaches to increase HIV prevention should focus on patients with infectious syphilis and other current risk factors for incident HIV infection.

Application of artificial intelligence and machine learning for HIV prevention interventions

In 2019, the US Government announced its goal to end the HIV epidemic within 10 years, mirroring the initiatives set forth by UNAIDS. Public health prevention interventions are a crucial part of this ambitious goal. However, numerous challenges to this goal exist, including improving HIV awareness, increasing early HIV infection detection, ensuring rapid treatment, optimising resource distribution, and providing efficient prevention services for vulnerable populations. Artificial intelligence has had a pivotal role in revolutionising health care and has shown great potential in developing effective HIV prevention intervention strategies. Although artificial intelligence has been used in a few HIV prevention intervention areas, there are challenges to address and opportunities to explore.

Machine Learning-Based HIV Risk Estimation Using Incidence Rate Ratios

HIV/AIDS is an ongoing global pandemic, with an estimated 39 million infected worldwide. Early detection is anticipated to help improve outcomes and prevent further infections. Point-of-care diagnostics make HIV/AIDS diagnoses available both earlier and to a broader population. Wide-spread and automated HIV risk estimation can offer objective guidance. This supports providers in making an informed decision when considering patients with high HIV risk for HIV testing or pre-exposure prophylaxis (PrEP). We propose a novel machine learning method that allows providers to use the data from a patient's previous stays at the clinic to estimate their HIV risk. All features available in the clinical data are considered, making the set of features objective and independent of expert opinions. The proposed method builds on association rules that are derived from the data. The incidence rate ratio (IRR) is determined for each rule. Given a new patient, the mean IRR of all applicable rules is used to estimate their HIV risk. The method was tested and validated on the publicly available clinical database MIMIC-IV, which consists of around 525,000 hospital stays that included a stay at the intensive care unit or emergency department. We evaluated the method using the area under the receiver operating characteristic curve (AUC). The best performance with an AUC of 0.88 was achieved with a model consisting of 53 rules. A threshold value of 0.66 leads to a sensitivity of 98% and a specificity of 53%. The rules were grouped into drug abuse, psychological illnesses (e.g., PTSD), previously known associations (e.g., pulmonary diseases), and new associations (e.g., certain diagnostic procedures). In conclusion, we propose a novel HIV risk estimation method that builds on existing clinical data. It incorporates a wide range of features, leading to a model that is independent of expert opinions. It supports providers in making informed decisions in the point-of-care diagnostics process by estimating a patient's HIV risk.

Barriers and facilitators to engagement with artificial intelligence (AI)-based chatbots for sexual and reproductive health advice: a qualitative analysis

Background The emergence of artificial intelligence (AI) provides opportunities for demand management of sexual and reproductive health services. Conversational agents/chatbots are increasingly common, although little is known about how this technology could aid services. This study aimed to identify barriers and facilitators for engagement with sexual health chatbots to advise service developers and related health professionals. Methods In January-June 2020, we conducted face-to-face, semi-structured and online interviews to explore views on sexual health chatbots. Participants were asked to interact with a chatbot, offering advice on sexually transmitted infections (STIs) and relevant services. Participants were UK-based and recruited via social media. Data were recorded, transcribed verbatim and analysed thematically. Results Forty participants (aged 18-50 years; 64% women, 77% heterosexual, 58% white) took part. Many thought chatbots could aid sex education, providing useful information about STIs and sign-posting to sexual health services in a convenient, anonymous and non-judgemental way. Some compared chatbots to health professionals or Internet search engines and perceived this technology as inferior, offering constrained content and interactivity, limiting disclosure of personal information, trust and perceived accuracy of chatbot responses. Conclusions Despite mixed attitudes towards chatbots, this technology was seen as useful for anonymous sex education but less suitable for matters requiring empathy. Chatbots may increase access to clinical services but their effectiveness and safety need to be established. Future research should identify which chatbots designs and functions lead to optimal engagement with this innovation.

Invited Commentary: Machine Learning in Causal Inference-How Do I Love Thee? Let Me Count the Ways

In this issue of the Journal, Mooney et al. (Am J Epidemiol. 2021;190(8):1476-1482) discuss machine learning as a tool for causal research in the style of Internet headlines. Here we comment by adapting famous literary quotations, including the one in our title (from "Sonnet 43" by Elizabeth Barrett Browning (Sonnets From the Portuguese, Adelaide Hanscom Leeson, 1850)). We emphasize that any use of machine learning to answer causal questions must be founded on a formal framework for both causal and statistical inference. We illustrate the pitfalls that can occur without such a foundation. We conclude with some practical recommendations for integrating machine learning into causal analyses in a principled way and highlight important areas of ongoing work.

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

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.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01346-2.

Addressing Unhealthy Alcohol Use and the HIV Pre-exposure Prophylaxis Care Continuum in Primary Care: A Scoping Review

Individuals with unhealthy alcohol use are at increased risk for HIV acquisition and may benefit from receiving HIV pre-exposure prophylaxis (PrEP) in primary care settings. To date, literature synthesizing what is known about the impact of unhealthy alcohol use on the PrEP care continuum with a focus on considerations for primary care is lacking. We searched OVID Medline and Web of Science from inception through March 19, 2020, to examine the extent, range, and nature of research on PrEP delivery among individuals with unhealthy alcohol use in primary care settings. We identified barriers and opportunities at each step along the PrEP care continuum, including for specific populations: adolescents, people who inject drugs, sex workers, and transgender persons. Future research should focus on identification of candidate patients, opportunities for patient engagement in novel settings, PrEP implementation strategies, and stigma reduction.

Using a machine learning approach to explore predictors of healthcare visits as missed opportunities for HIV diagnosis

OBJECTIVES

A significant number of individuals with a new HIV diagnosis are still late presenters despite numerous healthcare encounters prior to HIV diagnosis. We employed a machine learning approach to identify the predictors for the missed opportunities for earlier HIV diagnosis.

METHODS

The cohort comprised of individuals who were diagnosed with HIV in South Carolina from January 2008 to December 2016. Late presenters (LPs) (initial CD4 ≤200 cells/mm3 within one month of HIV diagnosis) with any healthcare visit during three years prior to HIV diagnosis were defined as patients with a missed opportunity. Using least absolute shrinkage and selection operator (LASSO) regression, two prediction models were developed to capture the impact of facility type (model 1) and physician specialty (model 2) of healthcare visits on missed opportunities.

RESULTS

Among 4,725 eligible participants, 72.2% had at least one healthcare visit prior to their HIV diagnosis, with most of the healthcare visits (78.5%) happening in the emergency departments (ED). A total of 1,148 individuals were LPs, resulting in an overall prevalence of 24.3% for the missed opportunities for earlier HIV diagnosis. Common predictors in both models included ED visit, older age, male gender, and alcohol use.

CONCLUSIONS

The findings underscored the need to reinforce the universal HIV testing strategy ED remains an important venue for HIV screening, especially for medically underserved or elder population. An improved and timely HIV screening strategy in clinical settings can be a key for early HIV diagnosis and play an increasingly important role in ending HIV epidemic.

Machine Learning and Clinical Informatics for Improving HIV Care Continuum Outcomes

PURPOSE OF REVIEW

This manuscript reviews the use of electronic medical record (EMR) data for HIV care and research along the HIV care continuum with a specific focus on machine learning methods and clinical informatics interventions.

RECENT FINDINGS

EMR-based clinical decision support tools and electronic alerts have been effectively utilized to improve HIV care continuum outcomes. Accurate EMR-based machine learning models have been developed to predict HIV diagnosis, retention in care, and viral suppression. Natural language processing (NLP) of clinical notes and data sharing between healthcare systems and public health agencies can enhance models for identifying people living with HIV who are undiagnosed or in need of relinkage to care. Challenges related to using these technologies include inconsistent EMR documentation, alert fatigue, and the potential for bias. Clinical informatics and machine learning models are promising tools for improving HIV care continuum outcomes. Future research should focus on methods for combining EMR data with additional data sources (e.g., social media, geospatial data) and studying how to effectively implement predictive models for HIV care into clinical practice.

Evaluation of an Electronic Algorithm for Identifying Cisgender Female Pre-Exposure Prophylaxis Candidates

We previously developed an electronic medical record-based algorithm for identifying patients at risk for HIV in the emergency department (ED). The aim of this study was to evaluate the performance of the HIV risk algorithm for identifying cisgender women with a pre-exposure prophylaxis (PrEP) indication. To retrospectively evaluate the HIV risk algorithm, we identified cisgender women with HIV diagnosed in the ED and retrospectively calculated the HIV risk algorithm output. To prospectively validate the algorithm, we surveyed cisgender women seeking care in the ED regarding behavioral risks for HIV. We prospectively determined whether the algorithm identified them as PrEP candidates. In the retrospective evaluation, 9.4% (2/21) of women with incident HIV infection were identified as at risk for HIV by the algorithm. In the prospective evaluation, 24% (59/245) of women who completed the survey had a PrEP indication based on self-report of behavioral risk factors for HIV. The sensitivity of the algorithm for identifying cisgender female PrEP candidates was 10%, and the specificity was 96%. PrEP indications missed by the electronic algorithm included condomless sex in a high HIV prevalence area, multiple sex partners, male partners who have sex with men, and recent bacterial sexually transmitted infections diagnosed at outside clinics. An electronic algorithm to identify PrEP candidates in the ED has low sensitivity for identifying cisgender women with PrEP indications. More research is needed to identify electronic data that can improve the algorithm sensitivity among cisgender women.