The next frontier: AI, multi-omics, and predictive models for weight gain in HIV

Area of Science:

• Biomedical research
• Data science
• Genomics

Background:

• People with HIV (PWH) face increasing rates of excess weight gain and obesity following antiretroviral therapy initiation.
• Individual weight gain varies significantly and is poorly predicted by clinical factors alone.
• Obesity in PWH has a complex pathophysiology influenced by biological and environmental interactions.

Purpose of the Study:

• To review emerging machine learning and multi-omics methods for understanding and predicting weight gain in PWH.
• To explore the challenges and future directions in this research area.

Main Methods:

• Review of recent studies utilizing machine learning and multi-omics approaches.
• Analysis of data to identify biological and environmental factors contributing to weight gain.

Main Results:

• Few studies have applied omics or machine learning to model weight gain trajectories in PWH.
• Existing studies demonstrate the potential and difficulties of using multi-omics and machine learning for weight gain prediction.
• These advanced methods are crucial for understanding complex disease pathways.

Conclusions:

• Machine learning and multi-omics are accelerating the understanding of human health and disease.
• These tools can define the biology and predictors of weight gain in PWH.
• Improved prediction and targeted interventions can enhance health outcomes for PWH.