Validation Requirements for AI-based Intervention-Evaluation in Aging and Longevity Research and Practice

TL;DR

This paper discusses the necessary validation standards for AI tools, especially Large Language Models, used in aging research to ensure accurate, comprehensive, and explainable evaluation of interventions, emphasizing the importance of benchmarks and informed use.

Contribution

It proposes specific validation requirements and workflows for AI-based evaluation in aging research, highlighting the integration of Knowledge Graphs and Retrieval-Augmented Generation.

Findings

AI validation standards improve response quality.

Benchmarking is essential for trustworthy AI in aging.

Informed AI use can prevent harm in longevity research.

Abstract

The field of aging and longevity research is overwhelmed by vast amounts of data, calling for the use of Artificial Intelligence (AI), including Large Language Models (LLMs), for the evaluation of geroprotective interventions. Such evaluations should be correct, useful, comprehensive, explainable, and they should consider causality, interdisciplinarity, adherence to standards, longitudinal data and known aging biology. In particular, comprehensive analyses should go beyond comparing data based on canonical biomedical databases, suggesting the use of AI to interpret changes in biomarkers and outcomes. Our requirements motivate the use of LLMs with Knowledge Graphs and dedicated workflows employing, e.g., Retrieval-Augmented Generation. While naive trust in the responses of AI tools can cause harm, adding our requirements to LLM queries can improve response quality, calling for benchmarking efforts and justifying the informed use of LLMs for advice on longevity interventions.