AI Poised to Predict HIV treatment Adherence Among Adolescents in uganda

A groundbreaking machine learning model is showing promise in predicting which adolescents living with HIV in Uganda are less likely to adhere to their antiretroviral therapy (ART). This innovation could pave teh way for targeted interventions and improved health outcomes in a region heavily burdened by the virus.

The Challenge of Adherence

Sub-Saharan Africa is home to nearly 85% of the 1.7 million adolescents living with HIV globally. In Uganda, despite the availability of free ART, adherence among those aged 10-16 remains a significant challenge, threatening to undermine treatment efforts and fuel further transmission.

The AI solution

Claire Najjuuko,a doctoral student at Washington University in St. Louis, is spearheading an effort to leverage artificial intelligence to address this critical issue. “I have great interest in machine learning and want to apply it to problems that speak directly to me,” she explains. By developing a predictive model, Najjuuko aims to provide healthcare practitioners with the insights needed to proactively support adolescents at risk of non-adherence.

How the Model Works

The machine learning model was trained using data from a six-year study involving 647 adolescents across 39 clinics in southern Uganda. the data, known as the Suubi+Adherence dataset, encompassed a wide range of factors, including social, interpersonal, family, educational, structural, and economic variables.

Najjuuko explains the current standard of care: “The current way the practice is, adolescents go to the clinic every month or two months for medication refills, and a health care practitioner checks how many pills the patient has left compared with what is expected, and also asking the adolescent questions regarding missed doses to establish if the patient is adhering to the therapy,” She suggests that this new model can have a “real impact” if implemented correctly.

Key Predictive Factors

The model identified 12 key variables strongly associated with poor adherence.These include:

• Economic factors (e.g.,child poverty)
• Poor adherence history
• Biological relationship to primary caregiver
• Self-concept
• Confidence in saving money
• Discussing sensitive topics with caregivers
• Household size
• School enrollment

The Role of Economic Stability

notably,economic factors emerged as highly influential predictors of non-adherence. Fred M. ssewamala, william E. Gordon Distinguished Professor, highlights the importance of financial resources. “The theory is when people own resources, especially when they have a nest egg, they think and behave differently,” he said. “The future holds promise, so they will take care of themselves so they can live longer. When people are hopeless, they have nothing to lose.”

Ssewamala further elaborated on the challenges: “Adhering to the treatment is difficult…as the medication must be taken with food or causes nausea. If a person with HIV doesn’t have access to food or transportation to get the medication,they are less likely to adhere to the treatment.”

Addressing Adolescent Non-Adherence

Ssewamala points out that, “Adolescents are the most nonadherent group across the globe,” and that “They are moving into independence and don’t want to be told what to do. As they move into the dating period, there is a lot of stigma, and they don’t want to be associated with HIV.”

Looking Ahead

Chenyang Lu, the Fullgraf Professor, envisions a future where the model is deployed in real-world settings to personalize intervention strategies.”This is an excellent example of interdisciplinary research…combining AI and global health,” Lu stated. “By leveraging the data that fred’s team gathered from the field and their insights on complex health issues, we apply AI expertise to analyze these data and build tools to enhance health outcomes.”

Call to Action

This innovative research offers a beacon of hope for improving HIV treatment adherence among adolescents in resource-limited settings. By understanding the key factors that influence adherence,healthcare providers and policymakers can develop targeted interventions to support this vulnerable population. Further research and implementation efforts are crucial to translating this promising model into tangible improvements in health outcomes. support global health initiatives and advocate for policies that address the social and economic determinants of health to ensure a brighter future for adolescents living with HIV.