AI Personalizes Aging Interventions

Researchers are investigating how advanced AI tools, particularly Large Language Models (LLMs), can improve the evaluation of aging-related interventions and provide personalized recommendations. Their findings, published in Ageing Research Reviews, aim to refine how AI systems assess treatments for aging and longevity.

Researchers from the Yong Loo Lin School of Medicine at the National University of Singapore (NUS Medicine) and the Institute for Biostatistics and Informatics in Medicine and Ageing Research at Rostock University Medical Center, Germany, have tackled this challenge by exploring how AI can enhance the assessment of aging-related interventions.

This study established a comprehensive set of guidelines to ensure AI systems provide accurate, reliable, and comprehensible assessments by leveraging their ability to analyze intricate biological data more effectively.

The researchers identified eight key prerequisites for AI-driven evaluations:

• Accuracy of assessment outcomes, ensuring data quality and precision
• Practicality and comprehensiveness of evaluations
• Interpretability and clarity of results, making findings easy to understand
• Consideration of the intervention’s effects on causal mechanisms
• Holistic data analysis, including effectiveness, toxicity, and therapeutic window assessment
• Interdisciplinary approach to data evaluation
• Standardization, reproducibility, and harmonization of analyses and reporting
• Emphasis on longitudinal large-scale data and established aging mechanisms

Incorporating these principles into AI prompting significantly improved the quality of its recommendations.

We tested AI methods using real-world examples such as medicines and dietary supplements. We found that by following specific guidelines, AI can provide more accurate and detailed insights. For instance, when analyzing rapamycin, a drug often studied for its potential to promote healthy ageing, the AI not only evaluated its efficacy but also provided context-specific explanations and caveats, such as possible side effects.

Brian Kennedy, Professor, Department of Biochemistry & Physiology, and Healthy Longevity Translational Research Program, National University of Singapore

Professor Georg Fuellen, Director, Institute for Biostatistics and Informatics in Medicine and Ageing Research, Rostock University Medical Center, who co-led the study, added, “The study’s findings could have far-reaching effects. For healthcare, telling the AI about the critical requirements of a good response can enable it to find more effective treatments and make them safer to use. Generally, AI tools could design better clinical trials and help tailor health recommendations to each person. This research is a major step toward using AI to improve health outcomes for everyone, especially as they age.”

Looking ahead, the team is focusing on large-scale research to refine AI prompting strategies for longevity-related interventions. They aim to evaluate accuracy and reliability across well-designed benchmarks based on high-quality curated data. Validating these AI systems is especially crucial as longevity therapies become increasingly accessible to healthy individuals.

Future research will need to demonstrate that AI-driven evaluations can reliably predict positive outcomes in human trials, paving the way for safer and more effective healthcare interventions.

Collaboration among researchers, clinicians, and policymakers will be essential to establishing regulatory frameworks that ensure AI-driven assessments are both safe and effective. The team hopes their work will contribute to improving health and longevity by making interventions more precise, accessible, and beneficial for all.

Journal Reference:

Fuellen, G., et. al. (2025) Validation requirements for AI-based intervention-evaluation in aging and longevity research and practice. Ageing Research Reviews. doi.org/10.1016/j.arr.2024.102617