Development of a Human Immunodeficiency Virus Risk Prediction Model Using Electronic Health Record Data From an Academic Health System in the Southern United States

HIV Risk Score and Prediction Model in the United States: A Scoping Review

Human immunodeficiency virus (HIV) remains a public health issue in the U.S., affecting approximately 1.2 million individuals, many of whom are unaware of their infection status. This study reviews predictors and the performance of HIV risk prediction models. We analyzed 18 studies published since 2010, which featured logistic regression, survival analysis, and machine learning techniques. These studies focused on diverse populations, including men who have sex with men, emergency department visitors, and the general population. Key predictors of HIV risk included demographics (age, sex, race) and behavioral factors (sexual practices, drug use). Electronic health records (EHR) documenting diagnoses of sexually transmitted infection (STI) were significant in all models. Behaviors like condomless sex, multiple sexual partners, and drug use were also strongly linked to increased risk scores. However, we noted a lack of social determinants of health in risk models, and a gap in studies focusing on cis female and transgender populations.

Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms

Objective

Early assessment and intervention of Acquired Immune Deficiency Syndrome (AIDS) patients at high risk of mortality is critical. This study aims to develop an optimally performing mortality risk prediction model for AIDS patients with comorbid AIDS-related diseases or symptoms to facilitate early intervention.

Methods

The study included 478 first-time hospital-admitted AIDS patients with related diseases or symptoms. Eight predictors were screened using lasso regression, followed by building eight models and using SHAP values (Shapley's additive explanatory values) to identify key features in the best models. The accuracy and discriminatory power of model predictions were assessed using variable importance plots, receiver operating characteristic curves, calibration curves, and confusion matrices. Clinical benefits were evaluated through decision-curve analyses, and validation was performed with an external set of 48 patients.

Results

Lasso regression identified eight predictors, including hemoglobin, infection pathway, Sulfamethoxazole-Trimethoprim, expectoration, headache, persistent diarrhea, Pneumocystis jirovecii pneumonia, and bacterial pneumonia. The optimal model, XGBoost, yielded an Area Under Curve (AUC) of 0.832, a sensitivity of 0.703, and a specificity of 0.799 in the training set. In the test set, the AUC was 0.729, the sensitivity was 0.717, and the specificity was 0.636. In the external validation set, the AUC was 0.873, the sensitivity was 0.852, and the specificity was 0.762. Furthermore, the calibration curves showed a high degree of fit, and the DCA curves demonstrated the overall high clinical utility of the model.

Conclusion

In this study, an XGBoost-based mortality risk prediction model is proposed, which can effectively predict the mortality risk of patients with co-morbid AIDS-related diseases or symptomatic AIDS, providing a new reference for clinical decision-making.

Mapping Implementation Strategies to Address Barriers to Pre-Exposure Prophylaxis Use Among Women Through POWER Up (Pre-Exposure Prophylaxis Optimization Among Women to Enhance Retention and Uptake): Content Analysis

BACKGROUND

Black cisgender women (hereafter referred to as "women") experience one of the highest incidences of HIV among all populations in the United States. Pre-exposure prophylaxis (PrEP) is an effective biomedical HIV prevention option, but uptake among women is low. Despite tailored strategies for certain populations, including men who have sex with men and transgender women, Black women are frequently overlooked in HIV prevention efforts. Strategies to increase PrEP awareness and use among Black women are needed at multiple levels (ie, community, system or clinic, provider, and individual or patient).

OBJECTIVE

This study aimed to identify barriers and facilitators to PrEP uptake and persistence among Black cisgender women and to map implementation strategies to identified barriers using the CFIR (Consolidated Framework for Implementation Research)-ERIC (Expert Recommendations for Implementing Change) Implementation Strategy Matching Tool.

METHODS

We conducted a secondary analysis of previous qualitative studies completed by a multidisciplinary team of HIV physicians, implementation scientists, and epidemiologists. Studies involved focus groups and interviews with medical providers and women at a federally qualified health center in Chicago, Illinois. Implementation science frameworks such as the CFIR were used to investigate determinants of PrEP use among Black women. In this secondary analysis, data from 45 total transcripts were analyzed. We identified barriers and facilitators to PrEP uptake and persistence among cisgender women across each CFIR domain. The CFIR-ERIC Implementation Strategy Matching Tool was used to map appropriate implementation strategies to address barriers and increase PrEP uptake among Black women.

RESULTS

Barriers to PrEP uptake were identified across the CFIR domains. Barriers included being unaware that PrEP was available (characteristics of individuals), worrying about side effects and impacts on fertility and pregnancy (intervention characteristics), and being unsure about how to pay for PrEP (outer setting). Providers identified lack of training (characteristics of individuals), need for additional clinical support for PrEP protocols (inner setting), and need for practicing discussions about PrEP with women (intervention characteristics). ERIC mapping resulted in 5 distinct implementation strategies to address barriers and improve PrEP uptake: patient education, provider training, PrEP navigation, clinical champions, and electronic medical record optimization.

CONCLUSIONS

Evidence-based implementation strategies that address individual, provider, and clinic factors are needed to engage women in the PrEP care continuum. Tailoring implementation strategies to address identified barriers increases the probability of successfully improving PrEP uptake. Our results provide an overview of a comprehensive, multilevel implementation strategy (ie, "POWER Up") to improve PrEP uptake among women.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1371/journal.pone.0285858.

Artificial intelligence in assisting pathogenic microorganism diagnosis and treatment: a review of infectious skin diseases

The skin, the largest organ of the human body, covers the body surface and serves as a crucial barrier for maintaining internal environmental stability. Various microorganisms such as bacteria, fungi, and viruses reside on the skin surface, and densely arranged keratinocytes exhibit inhibitory effects on pathogenic microorganisms. The skin is an essential barrier against pathogenic microbial infections, many of which manifest as skin lesions. Therefore, the rapid diagnosis of related skin lesions is of utmost importance for early treatment and intervention of infectious diseases. With the continuous rapid development of artificial intelligence, significant progress has been made in healthcare, transforming healthcare services, disease diagnosis, and management, including a significant impact in the field of dermatology. In this review, we provide a detailed overview of the application of artificial intelligence in skin and sexually transmitted diseases caused by pathogenic microorganisms, including auxiliary diagnosis, treatment decisions, and analysis and prediction of epidemiological characteristics.

Development of a Machine Learning Modeling Tool for Predicting HIV Incidence Using Public Health Data From a County in the Southern United States

BACKGROUND

Advancements in machine learning (ML) have improved the accuracy of models that predict human immunodeficiency virus (HIV) incidence. These models have used electronic medical records and registries. We aim to broaden the application of these tools by using deidentified public health datasets for notifiable sexually transmitted infections (STIs) from a southern US county known for high HIV incidence. The goal is to assess the feasibility and accuracy of ML in predicting HIV incidence, which could inform and enhance public health interventions.

METHODS

We analyzed 2 deidentified public health datasets from January 2010 to December 2021, focusing on notifiable STIs. Our process involved data processing and feature extraction, including sociodemographic factors, STI cases, and social vulnerability index (SVI) metrics. Various ML models were trained and evaluated for predicting HIV incidence using metrics such as accuracy, precision, recall, and F1 score.

RESULTS

We included 85 224 individuals; 2027 (2.37%) were newly diagnosed with HIV during the study period. The ML models demonstrated high performance in predicting HIV incidence among males and females. Influential features for males included age at STI diagnosis, previous STI information, provider type, and SVI. For females, predictive features included age, ethnicity, previous STI information, overall SVI, and race.

CONCLUSIONS

The high accuracy of our ML models in predicting HIV incidence highlights the potential of using public health datasets for public health interventions such as tailored HIV testing and prevention. While these findings are promising, further research is needed to translate these models into practical public health applications.

Using Machine Learning to Identify Patients at Risk of Acquiring HIV in an Urban Health System

BACKGROUND

Effective measures exist to prevent the spread of HIV. However, the identification of patients who are candidates for these measures can be a challenge. A machine learning model to predict risk for HIV may enhance patient selection for proactive outreach.

SETTING

Using data from the electronic health record at Parkland Health, 1 of the largest public healthcare systems in the country, a machine learning model is created to predict incident HIV cases. The study cohort includes any patient aged 16 or older from 2015 to 2019 (n = 458,893).

METHODS

Implementing a 70:30 ratio random split of the data into training and validation sets with an incident rate <0.08% and stratified by incidence of HIV, the model is evaluated using a k-fold cross-validated (k = 5) area under the receiver operating characteristic curve leveraging Light Gradient Boosting Machine Algorithm, an ensemble classifier.

RESULTS

The light gradient boosting machine produces the strongest predictive power to identify good candidates for HIV PrEP. A gradient boosting classifier produced the best result with an AUC of 0.88 (95% confidence interval: 0.86 to 0.89) on the training set and 0.85 (95% confidence interval: 0.81 to 0.89) on the validation set for a sensitivity of 77.8% and specificity of 75.1%.

CONCLUSIONS

A gradient boosting model using electronic health record data can be used to identify patients at risk of acquiring HIV and implemented in the clinical setting to build outreach for preventative interventions.

Early diagnosis of HIV cases by means of text mining and machine learning models on clinical notes

Undiagnosed and untreated human immunodeficiency virus (HIV) infection increases morbidity in the HIV-positive person and allows onward transmission of the virus. Minimizing missed opportunities for HIV diagnosis when a patient visits a healthcare facility is essential in restraining the epidemic and working toward its eventual elimination. Most state-of-the-art proposals employ machine learning (ML) methods and structured data to enhance HIV diagnoses, however, there is a dearth of recent proposals utilizing unstructured textual data from Electronic Health Records (EHRs). In this work, we propose to use only the unstructured text of the clinical notes as evidence for the classification of patients as suspected or not suspected. For this purpose, we first compile a dataset of real clinical notes from a hospital with patients classified as suspects and non-suspects of having HIV. Then, we evaluate the effectiveness of two types of classification models to identify patients suspected of being infected with the virus: classical ML algorithms and two Large Language Models (LLMs) from the biomedical domain in Spanish. The results show that both LLMs outperform classical ML algorithms in the two settings we explore: one dataset version is balanced, containing an equal number of suspicious and non-suspicious patients, while the other reflects the real distribution of patients in the hospital, being unbalanced. We obtain F1 score figures of 94.7 with both LLMs in the unbalanced setting, while in the balance one, RoBERTaBio model outperforms the other one with a F1 score of 95.7. The findings indicate that leveraging unstructured text with LLMs in the biomedical domain yields promising outcomes in diminishing missed opportunities for HIV diagnosis. A tool based on our system could assist a doctor in deciding whether a patient in consultation should undergo a serological test.

Using Electronic Health Records to Improve HIV Preexposure Prophylaxis Care: A Randomized Trial

BACKGROUND

Preexposure prophylaxis (PrEP) use remains limited and inequitable, and strategies are needed to improve PrEP provision in primary care.

METHODS

We conducted a cluster randomized trial at Kaiser Permanente, San Francisco, to evaluate the effectiveness of a clinical decision support intervention guided by an electronic health record (EHR)-based HIV risk prediction model to improve PrEP provision. Primary care providers (PCPs) were randomized to usual care or intervention, with PCPs who provide care to people with HIV balanced between arms. PCPs in the intervention arm received an EHR-based staff message with prompts to discuss HIV prevention and PrEP before upcoming in-person or video visits with patients whose predicted 3-year HIV risk was above a prespecified threshold. The main study outcome was initiation of PrEP care within 90 days, defined as PrEP discussions, referrals, or prescription fills.

RESULTS

One hundred twenty-one PCPs had 5051 appointments with eligible patients (2580 usual care; 2471 intervention). There was a nonsignificant increase in initiation of PrEP care in the intervention arm (6.0% vs 4.5%, HR 1.32, 95% CI: 0.84 to 2.1). There was a significant interaction by HIV provider status, with an intervention HR of 2.59 (95% CI: 1.30 to 5.16) for HIV providers and 0.89 (95% CI: 0.59 to 1.35) for non-HIV providers (P-interaction <0.001).

CONCLUSION

An EHR-based intervention guided by an HIV risk prediction model substantially increased initiation of PrEP care among patients of PCPs who also care for people with HIV. Higher-intensity interventions may be needed to improve PrEP provision among PCPs less familiar with PrEP and HIV care.

How Would You Manage HIV Pre-exposure Prophylaxis in This Patient With Medical Comorbidities? : Grand Rounds Discussion From Beth Israel Deaconess Medical Center

Despite advances in treatment, HIV infection remains an important cause of morbidity and mortality, with more than 30 000 new cases diagnosed in the United States each year. There are several interventions traditionally used to prevent HIV transmission, but these vary in effectiveness and there are challenges to their implementation. In 2014, the Centers for Disease Control and Prevention published initial guidance on the use of antiretroviral pre-exposure prophylaxis (PrEP) to prevent transmission of HIV infection in persons at risk based on multiple studies that showed it to be highly efficacious in various populations. It was updated in 2021 to reflect new drug options. The U.S. Preventive Services Task Force also recently updated its recommendations for PrEP, which strongly support its use in persons at risk. Despite its well-established effectiveness, the implementation of PrEP in clinical practice has been variable, especially among populations underserved by the medical system and marginalized by society. Fewer than one third of persons in the United States who are eligible for PrEP currently receive it. Here, 2 physicians experienced in HIV PrEP debate how best to identify patients who might benefit from PrEP, how to decide what regimen to use, and how to monitor therapy.

Demographics, Trends, and Clinical Characteristics of HIV Pre-Exposure Prophylaxis Recipients and People Newly Diagnosed with HIV from Large Electronic Health Records in Florida

Florida is one of the HIV epicenters with high incidence and marked sociodemographic disparities. We analyzed a decade of statewide electronic health record/claims data-OneFlorida+-to identify and characterize pre-exposure prophylaxis (PrEP) recipients and newly diagnosed HIV cases in Florida. Refined computable phenotype algorithms were applied and a total of 2186 PrEP recipients and 7305 new HIV diagnoses were identified between January 2013 and April 2021. We examined patients' sociodemographic characteristics, stratified by self-reported sex, along with both frequency-driven and expert-selected descriptions of clinical conditions documented within 12 months before the first PrEP use or HIV diagnosis. PrEP utilization rate increased in both sexes; higher rates were observed among males with sex differences widening in recent years. HIV incidence peaked in 2016 and then decreased with minimal sex differences observed. Clinical characteristics were similar between the PrEP and new HIV diagnosis cohorts, characterized by a low prevalence of sexually transmitted infections (STIs) and a high prevalence of mental health and substance use conditions. Study limitations include the overrepresentation of Medicaid recipients, with over 96% of female PrEP users on Medicaid, and the inclusion of those engaged in regular health care. Although PrEP uptake increased in Florida, and HIV incidence decreased, sex disparity among PrEP recipients remained. Screening efforts beyond individuals with documented prior STI and high-risk behavior, especially for females, including integration of mental health care with HIV counseling and testing, are crucial to further equalize PrEP access and improve HIV prevention programs.

Development of a predictive model for identifying women vulnerable to HIV in Chicago

INTRODUCTION

Researchers in the United States have created several models to predict persons most at risk for HIV. Many of these predictive models use data from all persons newly diagnosed with HIV, the majority of whom are men, and specifically men who have sex with men (MSM). Consequently, risk factors identified by these models are biased toward features that apply only to men or capture sexual behaviours of MSM. We sought to create a predictive model for women using cohort data from two major hospitals in Chicago with large opt-out HIV screening programs.

METHODS

We matched 48 newly diagnosed women to 192 HIV-negative women based on number of previous encounters at University of Chicago or Rush University hospitals. We examined data for each woman for the two years prior to either their HIV diagnosis or their last encounter. We assessed risk factors including demographic characteristics and clinical diagnoses taken from patient electronic medical records (EMR) using odds ratios and 95% confidence intervals. We created a multivariable logistic regression model and measured predictive power with the area under the curve (AUC). In the multivariable model, age group, race, and ethnicity were included a priori due to increased risk for HIV among specific demographic groups.

RESULTS

The following clinical diagnoses were significant at the bivariate level and were included in the model: pregnancy (OR 1.96 (1.00, 3.84)), hepatitis C (OR 5.73 (1.24, 26.51)), substance use (OR 3.12 (1.12, 8.65)) and sexually transmitted infections (STIs) chlamydia, gonorrhoea, or syphilis. We also a priori included demographic factors that are associated with HIV. Our final model had an AUC of 0.74 and included healthcare site, age group, race, ethnicity, pregnancy, hepatitis C, substance use, and STI diagnosis.

CONCLUSIONS

Our predictive model showed acceptable discrimination between those who were and were not newly diagnosed with HIV. We identified risk factors such as recent pregnancy, recent hepatitis C diagnosis, and substance use in addition to the traditionally used recent STI diagnosis that can be incorporated by health systems to detect women who are vulnerable to HIV and would benefit from preexposure prophylaxis (PrEP).

Accelerating health system innovation: principles and practices from the Duke Institute for Health Innovation

The Duke Institute for Health Innovation (DIHI) was launched in 2013. Frontline staff members submit proposals for innovation projects that align with strategic priorities set by organizational leadership. Funded projects receive operational and technical support from institute staff members and a transdisciplinary network of collaborators to develop and implement solutions as part of routine clinical care, ranging from machine learning algorithms to mobile applications. DIHI's operations are shaped by four guiding principles: build to show value, build to integrate, build to scale, and build responsibly. Between 2013 and 2021, more than 600 project proposals have been submitted to DIHI. More than 85 innovation projects, both through the application process and other strategic partnerships, have been supported and implemented. DIHI's funding has incubated 12 companies, engaged more than 300 faculty members, staff members, and students, and contributed to more than 50 peer-reviewed publications. DIHI's practices can serve as a model for other health systems to systematically source, develop, implement, and scale innovations.