Amyloid-β PET-Correlation with cerebrospinal fluid biomarkers and prediction of Alzheimer's disease diagnosis in a memory clinic

Background Alzheimer's disease (AD) remains a clinical diagnosis but biomarkers from cerebrospinal fluid (CSF) and more lately amyloid imaging with positron emission tomography (PET), are important to support a diagnosis of AD. Objective To compare amyloid-beta (A beta) PET imaging with biomarkers in CSF and evaluate the prediction of A beta PET on diagnosis in a memory clinic setting. Methods We included 64 patients who had lumbar puncture and A beta PET with F-18-Flutemetamol performed within 190 days. PET was binary classified (Flut+ or Flut-) and logistic regression analyses for correlation to each CSF biomarker; A beta(42) (A beta(42)), total tau (T-tau) and phosphorylated tau (P-tau), were performed. Cut-off values were assessed by receiver operating characteristic (ROC) curves. Logistic regression was performed for prediction of clinical AD diagnosis. We assessed the interrater agreement of PET classification as well as for diagnoses, which were made both with and without knowledge of PET results. Results Thirty-two of the 34 patients (94%) in the Flut+ group and nine of the 30 patients (30%) in the Flut-group had a clinical AD diagnosis. There were significant differences in all CSF biomarkers in the Flut+ and Flut-groups. A beta(42) showed the highest correlation with F-18-Flutemetamol PET with a cut-off value of 706.5 pg/mL, corresponding to sensitivity of 88% and specificity of 87%. F-18-Flutemetamol PET was the best predictor of a clinical AD diagnosis. We found a very high interrater agreement for both PET classification and diagnosis. Conclusions The present study showed an excellent correlation of A beta(42) in CSF and F-18-Flutemetamol PET and the presented cut-off value for A beta(42) yields high sensitivity and specificity for F-18-Flutemetamol PET. F-18-Flutemetamol PET was the best predictor of clinical AD diagnosis.