Machine learning prediction of future amyloid beta positivity in amyloid-negative individuals.

Background: The pathophysiology of Alzheimer's disease (AD) involves -amyloid (A ) accumulation. Early identification of individuals with abnormal -amyloid levels is crucial, but A 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 A -positivity in A -negative individuals. We separately study A -positivity defined by PET and CSF.

Results: Cross-validated AUC for 4-year A conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based A 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).

Conclusion: Standard measures have potential in detecting future A -positivity and assessing conversion risk, even in cognitively normal individuals. The CSF-based definition led to better predictions than the PET-based definition.