MRI and cognitive scores complement each other to accurately predict Alzheimer's dementia 2 to 7 years before clinical onset

Neuroimage Clin. 2020;25:102121. doi: 10.1016/j.nicl.2019.102121. Epub 2019 Dec 16.


Background: Predicting cognitive decline and the eventual onset of dementia in patients with Mild Cognitive Impairment (MCI) is of high value for patient management and potential cohort enrichment in pharmaceutical trials. We used cognitive scores and MRI biomarkers from a single baseline visit to predict the onset of dementia due to AD in an amnestic MCI (aMCI) population over a nine-year follow-up period.

Method: All aMCI subjects from ADNI1, ADNI2, and ADNI-GO with available baseline neurocognitive scores and T1w MRI were included in the study (n = 756). We built a Naïve Bayes classifier for every year over a 9-year follow-up period and tested each one with Leave one out cross validation.

Results: We reached 87% prediction accuracy at five years follow-up with an AUC > 0.85 from two to seven years (peaking at 0.92 at five years). Both neurocognitive scores and MRI biomarkers were needed to make the prognostic models highly sensitive and specific, especially for longer follow-ups. MRI features are more sensitive, while cognitive features bring specificity to the prediction.

Conclusion: Combining cognitive scores and MRI biomarkers yield accurate prediction years before onset of dementia. Such a tool may be helpful in selecting patients that would most benefit from lifestyle changes, and eventually early treatments that would slow cognitive decline and delay the onset of dementia.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Aged
  • Alzheimer Disease / diagnosis*
  • Bayes Theorem
  • Cognitive Dysfunction
  • Disease Progression
  • Early Diagnosis*
  • Female
  • Humans
  • Magnetic Resonance Imaging / methods
  • Male
  • Neuroimaging / methods*
  • Neuropsychological Tests*
  • Prognosis
  • Sensitivity and Specificity