ABSTRACT
INTRODUCTION The pathophysiology of Alzheimer’s disease (AD) involves β-amyloid (Aβ) accumulation. Early identification of individuals with abnormal β-amyloid levels is crucial, but Aβ quantification with positron emission tomography (PET) and cerebrospinal fluid (CSF) is invasive and expensive.
METHODS We propose a machine learning framework using standard non-invasive (MRI, demographics, APOE, neuropsychology) measures to predict future Aβ-positivity in Aβ-negative individuals. We separately study Aβ-positivity defined by PET and CSF. RESULTS: Cross-validated AUC for 4-year Aβ conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based Aβ definitions. Although not trained for the clinical status-change prediction, the CSF-based model excelled in predicting future mild cognitive impairment (MCI)/dementia conversion in cognitively normal/MCI individuals (AUCs, respectively, 0.76 and 0.89 with a separate dataset).
DISCUSSION Standard measures have potential in detecting future Aβ-positivity and assessing conversion risk, even in cognitively normal individuals. The CSF-based definition led to better predictions than the PET-based definition.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
↵** Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf
