Development and Validation of a Risk Prediction Tool to Identify People with HIV Infection Likely Not to Achieve Viral Suppression

Development and Validation of a Risk Prediction Tool to Identify People at Greater Risk of Having Hepatitis C among Drug Users

BACKGROUND

People who use drugs (PWUD) are among those with the highest risk for hepatitis C virus (HCV) infection. Highly effective direct-acting antiviral agents offer an opportunity to eliminate HCV. A simple tool for the prediction of HCV infection risk in PWUD is urgently needed. This study aimed to develop and validate a risk prediction tool to identify people at greater risk of having hepatitis C among PWUD that is applicable in resource-limited settings.

METHODS

We extracted data from national HIV/AIDS sentinel surveillance in PWUD (Zhejiang Province, 2016-2021) and developed and validated a risk score to improve HCV testing in PWUD. This risk score consists of seven risk factors identified using multivariable logistic regression modeling (2016-2020, exploratory group). We validated this score using surveillance data for 2021 (validation group). The accuracy of the model was determined using C-statistics.

RESULTS

We identified seven risk factors, including sex, age, marital status, educational attainment, and the use of heroin, morphine, and methamphetamine. In the exploratory group, the positive rates of detecting the HCV antibody in the low-risk (0-9 points), intermediate-risk (10-16 points), and high-risk (≥17 points) groups were 6.72%, 17.24%, and 38.02%, respectively (P_trend < 0.001). In the validation group, the positive rates in the low-, medium-, and high-risk groups were 4.46%, 12.23%, and 38.99%, respectively (P_trend < 0.001).

CONCLUSIONS

We developed and validated a drug-specific risk prediction tool for identifying PWUD at increased risk of HCV infection. This tool can complement and integrate the screening strategy for the purpose of early diagnosis and treatment.

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 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.