Login / Signup

Rethinking the residual approach: Leveraging machine learning to operationalize cognitive resilience in Alzheimer's disease.

Colin BirkenbihlMadison CuppelsRory T BoyleHannah M KlingerOliver LangfordGillian T CoughlanMichael J ProperziJasmeer ChhatwalJulie T PriceAaron P SchultzDorene M RentzRebecca E AmariglioKeith A JohnsonRebecca F GottesmanShubhabrata MukherjeePaul MaruffYen Ying LimColin L MastersAlexa BeiserSusan M ResnickTimothy M HughesSamantha BurnhamIlke TunaliSusan LandauAnn D CohenSterling C JohnsonTobey J BetthauserSudha SeshadriSamuel N LockhartSid E O'BryantPrashanthi VemuriReisa A SperlingTimothy J HohmanMichael C DonohueRachel F Buckley
Published in: medRxiv : the preprint server for health sciences (2024)
Cognitive resilience 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. 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 construct to be measured and achieves better estimation accuracy on simulated ground-truth data.
Keyphrases
  • cognitive decline
  • climate change
  • mild cognitive impairment
  • social support
  • machine learning
  • big data
  • electronic health record
  • depressive symptoms
  • deep learning
  • data analysis