Introduction: The overlapping burden of HIV and COVID-19 poses significant challenges for healthcare systems, demanding innovative strategies for effective disease detection and management. Artificial intelligence (AI), particularly through machine learning (ML) and deep learning technologies, has revolutionized HIV detection and tracking by providing heightened sensitivity and specificity compared to conventional diagnostic methods. AI-enabled mobile applications and image analysis tools have shown remarkable accuracy in interpreting rapid HIV self-tests, proving especially valuable in resource-constrained settings and during periods of healthcare disruption.
Amid the COVID-19 pandemic, AI models have played a pivotal role in evaluating viral load suppression, CD4 cell counts, and virological failure in people living with HIV (PLWH), facilitating more personalized and responsive care approaches. Additionally, AI-based risk assessment platforms have supported the identification of individuals at elevated risk for HIV and other sexually transmitted infections, contributing to more precise prevention efforts. Emerging advancements have also enabled dual diagnosis and monitoring of HIV and COVID-19 co-infections.
ML algorithms trained on biochemical and hematological datasets can effectively differentiate between diagnoses such as COVID-19, HIV/AIDS, tuberculosis, and their co-infections, while simultaneously identifying key biomarkers and predicting adverse clinical outcomes. Moreover, AI-driven genomic analyses now provide tools for tracking pathogen evolution and understanding the dynamics of co-infections. Despite these breakthroughs, challenges persist. Issues related to data quality, model generalizability, and ethical concerns—such as patient privacy and algorithmic bias—remain barriers to equitable application.
Addressing these concerns is crucial to ensure the fair and effective implementation of AI in diverse healthcare environments. In conclusion, AI holds transformative promise in improving the detection and management of HIV, particularly in the context of COVID-19 co-infections. By enhancing diagnostic accuracy, enabling real-time monitoring, and shaping informed public health strategies, AI can drive meaningful progress. Continued research, coupled with ethical consideration, is vital to unlock the full potential of AI-driven healthcare solutions in managing intersecting infectious disease epidemics.
Methods: This review explores the role of AI-enabled mobile applications, image analysis tools, and ML algorithms in HIV detection, monitoring, and management, especially in the context of COVID-19 co-infections. Relevant studies on AI-driven diagnostic tools, risk assessment platforms, and genomic analyses were examined to assess their effectiveness, accuracy, and potential in resource-constrained settings.
Results: AI technologies demonstrated remarkable accuracy in interpreting rapid HIV self-tests, monitoring viral load suppression, CD4 cell counts, and identifying virological failure in people living with HIV (PLWH). AI-based risk assessment platforms supported the identification of high-risk individuals for HIV and other sexually transmitted infections. ML algorithms effectively differentiated between COVID-19, HIV/AIDS, tuberculosis, and co-infections while predicting adverse clinical outcomes. Genomic AI tools enabled tracking pathogen evolution and understanding co-infection dynamics.
Conclusion: AI holds transformative promise for improving HIV detection and management, particularly in COVID-19 co-infections. By enhancing diagnostic accuracy, enabling real-time monitoring, and shaping public health strategies, AI can drive significant progress. Addressing challenges such as data quality, model generalizability, and ethical concerns is crucial for the equitable implementation of AI in healthcare.