Scholarlink

<p>Cognitive resilience&#xa0;(CR) describes the phenomenon of individuals evading cognitive decline despite prominent Alzheimer’s disease neuropathology. Operationalization and measurement of this latent construct is non-trivial as it cannot be directly observed. The residual approach has been widely applied to estimate CR, where the degree of resilience is estimated through a linear model’s residuals. We demonstrate that this approach makes specific, uncontrollable assumptions and likely leads to biased and erroneous resilience estimates. This is especially true when information about CR is contained in the data the linear model was fitted to, either through inclusion of CR-associated variables or due to correlation. We propose an alternative strategy which overcomes the standard approach’s limitations using machine learning principles. Our proposed approach makes fewer assumptions about the data and CR and achieves better estimation accuracy on simulated ground-truth data.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Rethinking the residual approach: leveraging statistical learning to operationalize cognitive resilience in Alzheimer’s disease

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年1月27日

查看全文
  • Colin Birkenbihl,
  • Madison Cuppels,
  • Rory T. Boyle,
  • Hannah M. Klinger,
  • Oliver Langford,
  • Gillian T. Coughlan,
  • Michael J. Properzi,
  • Jasmeer Chhatwal,
  • Julie C. Price,
  • Aaron P. Schultz,
  • Dorene M. Rentz,
  • Rebecca E. Amariglio,
  • Keith A. Johnson,
  • Rebecca F. Gottesman,
  • Shubhabrata Mukherjee,
  • Paul Maruff,
  • Yen Ying Lim,
  • Colin L. Masters,
  • Alexa Beiser,
  • Susan M. Resnick,
  • Timothy M. Hughes,
  • Samantha Burnham,
  • Ilke Tunali,
  • Susan Landau,
  • Ann D. Cohen,
  • Sterling C. Johnson,
  • Tobey J. Betthauser,
  • Sudha Seshadri,
  • Samuel N. Lockhart,
  • Sid E. O’Bryant,
  • Prashanthi Vemuri,
  • Reisa A. Sperling,
  • Timothy J. Hohman,
  • Michael C. Donohue,
  • Rachel F. Buckley

摘要

Cognitive resilience (CR) describes the phenomenon of individuals evading cognitive decline despite prominent Alzheimer’s disease neuropathology. Operationalization and measurement of this latent construct is non-trivial as it cannot be directly observed. The residual approach has been widely applied to estimate CR, where the degree of resilience is estimated through a linear model’s residuals. We demonstrate that this approach makes specific, uncontrollable assumptions and likely leads to biased and erroneous resilience estimates. This is especially true when information about CR is contained in the data the linear model was fitted to, either through inclusion of CR-associated variables or due to correlation. We propose an alternative strategy which overcomes the standard approach’s limitations using machine learning principles. Our proposed approach makes fewer assumptions about the data and CR and achieves better estimation accuracy on simulated ground-truth data.