Prediction of amyloid β accumulation from multiple biomarkers using a hierarchical Bayesian model

Accumulation of amyloid-beta (A{beta}) in the brain is associated with neurodegeneration in Alzheimers disease and can be an indicator of early disease progression. Thus, the non-invasively and inexpensively observable features related to A{beta} accumulation are promising biomarkers. However, in the experimental discovery of biomarkers in preclinical models, A{beta} and biomarker candidates are usually not observed in identical sample populations. This study established a hierarchical Bayesian model that predicts A{beta} accumulation level solely from biomarker candidates by integrating incomplete information. The model was applied to 5xFAD mouse behavioral experimental data. The predicted A{beta} accumulation level obeyed the observed amount of A{beta} when multiple features were used for learning and prediction. Based on the evaluation of predictability, the results suggest that the proposed model can contribute to discovering novel biomarkers, that is, multivariate biomarkers relevant to the accumulation state of abnormal proteins.