The proposed Bayesian Network has been designed according to the latest ‘Research criteria for the diagnosis of Alzheimer’s disease: revising the NINCDS-ADRDA criteria’ and the model exports for every AD category the maximum probability value is given the biomarkers evidence. The proposed statistical model is multi-parametric, relating several heterogeneous data like plasma and CSF tests, behavioral or imaging tests as categorical variables through prior categorical distributions.
The probabilistic model is based on conditional probabilities, therefore it must be noted that the calculated error is the Monte Carlo error that measures the variability of each estimation due to the simulation. The AD Bayesian model uses the WinBUGS 1.4.3 software, which cannot be used online. Therefore users are able to fill AD results in the form of YES or NO and receive the exported statistics in their email account.
The preferred reference for citing this work and the WinBUGS as well, in scientific papers are:
 Alexiou A, Mantzavinos VD, Greig NH and Kamal MA (2017) A Bayesian Model for the Prediction and Early Diagnosis of Alzheimer’s Disease. Front. Aging Neurosci. 9:77. doi: 10.3389/fnagi.2017.00077
 Matzavinos V, Alexiou A, Greig NH, Kamal MA, Biomarkers for Alzheimer’s disease diagnosis (2017) Curr. Alzheimer Res. doi: 10.2174/1567205014666170203125942.
 Lunn DJ, Thomas A, Best N, Spiegelhalter D (2000) WinBUGS – a Bayesian modelling framework: concepts, structure, and extensibility. Statistics and Computing, 10:325-337.