The biomarker-based new diagnostic criteria have been proposed for Alzheimer's disease (AD) spectrum. However, any biomarker alone has not been known to have satisfactory AD predictability. We explored the best combination model with baseline demography, neuropsychology, 18F-fluorodeoxyglucose positron emission tomography (FDG-PET), cerebrospinal fluid (CSF) biomarkers, and apolipoprotein E (APOE) genotype evaluation to predict progression to AD in mild cognitive impairment (MCI) patients. A longitudinal clinical follow-up (mean, 44 months; range, 1.6-161.7 months) of MCI patients was done. Among 83 MCI patients, 26 progressed to AD (MCI-AD) and 51 did not deteriorate (MCI-Stable). We applied that univariate and multivariate logistic regression analyses, and multistep model selection for AD predictors including biomarkers. In univariate logistic analysis, we selected age, Rey Auditory Verbal Retention Test, parietal glucose metabolic rate, CSF total tau, and presence or not of at least one APOE ε4 allele as predictors. Through multivariate stepwise logistic analysis and model selection, we found the combination of parietal glucose metabolic rate and total tau representing the best model for AD prediction. In conclusion, our findings highlight that the combination of regional glucose metabolic assessment by PET and CSF biomarkers evaluation can significantly improve AD predictive diagnostic accuracy of each respective method.