Validation requirements for AI-based intervention-evaluation in aging and longevity research and practice

IF 12.5 1区医学 Q1 CELL BIOLOGY

Ageing Research Reviews Pub Date : 2025-02-01 DOI:10.1016/j.arr.2024.102617

Georg Fuellen , Anton Kulaga , Sebastian Lobentanzer , Maximilian Unfried , Roberto A. Avelar , Daniel Palmer , Brian K. Kennedy

{"title":"Validation requirements for AI-based intervention-evaluation in aging and longevity research and practice","authors":"Georg Fuellen , Anton Kulaga , Sebastian Lobentanzer , Maximilian Unfried , Roberto A. Avelar , Daniel Palmer , Brian K. Kennedy","doi":"10.1016/j.arr.2024.102617","DOIUrl":null,"url":null,"abstract":"<div><div>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.</div></div>","PeriodicalId":55545,"journal":{"name":"Ageing Research Reviews","volume":"104 ","pages":"Article 102617"},"PeriodicalIF":12.5000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ageing Research Reviews","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1568163724004355","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CELL BIOLOGY","Score":null,"Total":0}

引用次数: 0

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.

查看原文本刊更多论文

基于人工智能的老龄化与长寿研究与实践干预评估的验证要求

老龄化和长寿研究领域被大量数据淹没，需要使用人工智能（AI），包括大型语言模型（LLMs），来评估老年保护干预措施。这样的评估应该是正确的、有用的、全面的、可解释的，并且应该考虑因果关系、跨学科性、对标准的遵守、纵向数据和已知的衰老生物学。特别是，综合分析应超越基于规范生物医学数据库的数据比较，建议使用人工智能来解释生物标志物和结果的变化。我们的需求激发了法学硕士与知识图和专用工作流的使用，例如，检索增强生成。虽然对人工智能工具的响应的天真信任可能会造成伤害，但将我们的需求添加到法学硕士查询中可以提高响应质量，呼吁进行基准测试，并证明法学硕士在长寿干预方面的明智使用是合理的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Ageing Research Reviews 医学-老年医学

CiteScore

19.80

自引率

2.30%

发文量

216

审稿时长

55 days

期刊介绍： With the rise in average human life expectancy, the impact of ageing and age-related diseases on our society has become increasingly significant. Ageing research is now a focal point for numerous laboratories, encompassing leaders in genetics, molecular and cellular biology, biochemistry, and behavior. Ageing Research Reviews (ARR) serves as a cornerstone in this field, addressing emerging trends. ARR aims to fill a substantial gap by providing critical reviews and viewpoints on evolving discoveries concerning the mechanisms of ageing and age-related diseases. The rapid progress in understanding the mechanisms controlling cellular proliferation, differentiation, and survival is unveiling new insights into the regulation of ageing. From telomerase to stem cells, and from energy to oxyradical metabolism, we are witnessing an exciting era in the multidisciplinary field of ageing research. The journal explores the cellular and molecular foundations of interventions that extend lifespan, such as caloric restriction. It identifies the underpinnings of manipulations that extend lifespan, shedding light on novel approaches for preventing age-related diseases. ARR publishes articles on focused topics selected from the expansive field of ageing research, with a particular emphasis on the cellular and molecular mechanisms of the aging process. This includes age-related diseases like cancer, cardiovascular disease, diabetes, and neurodegenerative disorders. The journal also covers applications of basic ageing research to lifespan extension and disease prevention, offering a comprehensive platform for advancing our understanding of this critical field.