Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
Machine Learning for Dementia Research in People with HIV: A Rapid Review and Future Directions
26 Pages Posted: 1 May 2025
More...Abstract
Background: Over half of people living with HIV (PLWH) in the United States are over age 50 and face an approximately 60% higher risk of developing dementia compared to the general population. In recent years, the application of artificial intelligence (AI), particularly machine learning (ML), combined with the growing availability of large datasets, has opened new avenues for developing prediction models to improve dementia detection, monitoring, and management. This systematic review aimed to synthesize the existing literature that has applied ML in dementia research for PLWH and to highlight directions for future research.
Methods: A comprehensive search was conducted in PubMed, CINAHL, and Embase in September 2024, limited to studies published in the past ten years. Eligible articles included original research on PLWH that applied at least one ML technique and reported dementia-related outcomes.
Findings: The search yielded 721 articles, with 26 meeting inclusion criteria. Most studies were retrospective and focused on neurocognitive impairment, particularly HIV-associated neurocognitive disorders (HAND). Supervised ML techniques were most commonly used and showed strong predictive performance. The lack of longitudinal studies and external validation remain significant gaps.
Interpretation: ML research in dementia among PLWH largely focused on HAND, with limited attention to age-related dementias such as Alzheimer’s disease (AD) and related disorders. This review highlights the need for studies addressing all-cause dementia rather than focusing solely on HIV-associated conditions, while applying advanced ML methods and leveraging large, longitudinal, multimodal datasets. Strengthening methodological rigor and enhancing real-world clinical applications will improve early detection and management of dementia in aging PLWH.
Keywords: machine learning, artificial intelligence, HIV, dementia, neurocognitive impairment, aging
Suggested Citation: Suggested Citation