Alzheimer´s disease (AD) is a progressive degenerative disease of the brain that mainly affect older people. It is the most common form of dementia and as the population grows older the prevalence is increasing. [1, 2]. There is increasing evidence that the typical neuropathological changes in AD start to develop decades prior to onset of symptoms [3–5], hence the recognition of AD as a continuum [6]. These changes are considered hallmarks of AD, namely neurofibrillary tangles and neuritic plaques. Biomarkers for AD reflect these hallmarks and were included into the diagnostic criteria in 2011, although only for research purposes [7, 8]. The recently published research framework recognizes the increasing position of biomarkers in AD and proposes a focus on biologically defining the etiology of AD through the use of biomarkers, rather than defining diagnosis by clinical symptoms [6]. Biomarkers of AD may be measured in cerebrospinal fluid (CSF) or evaluated with positron emission tomography (PET). PET utilizes radioactively labelled amyloid β (Aβ) tracers, or the more recently investigated tau-tracers, which bind to fibrillary forms of Aβ and tau in the brain, respectively. Evidence shows that decreased levels of Aβ consisting of 42 amino acids (Aβ₄₂) in CSF or a positive Aβ PET is closely related to Aβ deposition in neuritic plaques [9, 10] while increased levels of phosphorylated tau protein (P-tau) in CSF or a positive tau-PET is closely related to fibrillar tau accumulation in neurofibrillary tangles [11–13]. Elevated total tau (T-tau) in CSF, atrophy on magnetic resonance imaging (MRI) or hypometabolism on 2-deoxy-2-(¹⁸F)-fluoro-D-glucose (FDG) PET are biomarkers of neurodegeneration which may co-occur with the other hallmarks [6]. Evaluation of biomarkers with PET or CSF may be used to gain confidence in a clinical AD diagnosis [6–8]. ¹⁸F-Flutemetamol is an Aβ PET-tracer that binds to fibrillar Aβ and it has a similar structure to the widely investigated ¹¹C-Pittsburg compound B (PiB) as both are derivatives of Thioflavin-T, labelled with different radioisotopes. Previous studies have shown a good correlation between ¹⁸F-Flutemetamol binding and neuropathological evidence of Aβ neuritic plaques [14–17], as well as a good correlation between ¹⁸F-Flutemetamol PET and CSF measurements of Aβ₄₂ [18–20]. Consequently, Aβ PET has been used to suggest cut-off values for CSF biomarkers for AD [18, 20]. However, the cut-off values vary as different methods for CSF analysis and different Aβ PET-tracers are used.

The aim of this study was to correlate ¹⁸F-Flutemetamol PET with CSF biomarkers to assess the optimal cut-off values, to evaluate the effect of the newly implemented cut-off value for Aβ₄₂ and to investigate the prediction of ¹⁸F-Flutemetamol PET on a clinical AD diagnosis.

Patient characteristics, CSF biomarker levels, distribution of diagnoses and cognitive measures for the patient population are listed in Table 1.

In the present study we found a significant correlation between ¹⁸F-Flutemetamol PET classification and the three CSF biomarkers explored, with the highest correlation between Aβ₄₂ and ¹⁸F-Flutemetamol PET. The optimal cut-off value for Aβ₄₂ presented is in accordance with the newly implemented cut-off value and yielded an improvement in sensitivity, while maintaining a high specificity, for a positive ¹⁸F-Flutemetamol PET. ¹⁸F-Flutemetamol PET was found to be the best predictor of a clinical AD diagnosis.

The significant correlation between the three CSF biomarkers and ¹⁸F-Flutemetamol PET is in line with previous studies [18–20]. The laboratory analyzing CSF samples for AD biomarkers in Norway recently elevated the recommended cut-off value for Aβ₄₂ from 550 pg/mL to 700 pg/mL [23]. Our results support this change for use in Norwegian memory clinic settings. The change in cut-off value has recently been showed to also improve the sensitivity with only a small decrease in specificity for a clinical AD diagnosis and without increasing false positives [35]. A previous study compared different immunoassays with visual ¹⁸F-Flutemetamol PET and when using Innotest they found a cut-off value of 548 pg/mL (sensitivity 96% and specificity 82%) [36]. Other studies comparing ¹⁸F-Flutemetamol PET and Innotest for CSF analysis found a cut-off value of 647 pg/mL (sensitivity 95% and specificity 90%) [18], while two other studies found a cut-off value of 679 pg/mL (sensitivity 100% and specificity 89%) [37] and a cut-off value range of 645–762 pg/mL across different brain regions (sensitivities 87–93% and specificities 85–93%) [23]. For the other biomarkers we found that T-tau and P-tau had lower specificity for ¹⁸F-Flutemetamol PET than Aβ₄₂, not surprisingly, as these are biomarkers of pathological processes that are not directly evaluated with ¹⁸F-Flutemetamol PET. The ratios performed better, understandingly, as they include Aβ₄₂. Our cut-off values for T-tau, P-tau and the ratios were within the range found in other studies [19, 20, 36, 38, 39], although they are not directly comparable due to differences in patient populations, diagnostic criteria, CSF analysis methods as well as PET tracers and classification methods used. These factors represent a challenge when comparing studies exploring PET and CSF biomarkers and may partly also explain the differences in cut-offs for Aβ₄₂ shown across studies. We did not have available Aβ₄₀ in CSF. This would have been favorable to explore as the Aβ₄₂/Aβ₄₀ ratio is found to have better diagnostic accuracy as well as being a better predictor of abnormal Aβ PET than Aβ₄₂ alone [40, 41].

We found that ¹⁸F-Flutemetamol-PET is a better predictor of a clinical AD diagnosis than Aβ₄₂, however we suggest they can be used interchangeably for evaluating Aβ load in a memory clinic setting, due to the high correlation between ¹⁸F-Flutemetamol PET and Aβ₄₂. This high correlation may have influenced the significance level of Aβ₄₂ in the multivariate analysis, however ¹⁸F-Flutemetamol PET demonstrated a lower p-value as well as a higher explained variance than Aβ₄₂ in the univariate analyses. ¹⁸F-Flutemetamol was also the most significant variable in all the tested prediction models. Which biomarker examination is used in clinical practice will vary depending on availability, tradition, patient comfort as well as confidence in performing and contraindications (e.g anticoagulative medications) for a lumbar puncture. However, Aβ₄₂ level in CSF and Aβ PET does not provide identical information. The level of Aβ₄₂ provides information about the Aβ₄₂ epitopes that may be in either soluble or protofibrillar forms in CSF and reflects the balance between Aβ₄₂ production and clearance at the time of lumbar puncture. It is further an indirect measure which is associated with the accumulation of Aβ in the form of plaques [6]. ¹⁸F-Flutemetamol-PET, on the other hand, provides information of the amount of insoluble Aβ fibrils and consequently the Aβ burden in the brain which has accumulated over time [42]. Previous longitudinal studies have described a nonlinear correlation between Aβ PET imaging and CSF Aβ₄₂ which supports the hypothesis that the two methods show different aspects of Aβ pathology [43–45]. In the present study, there were eight patients (12.5%) with discordance between Aβ PET and CSF Aβ₄₂ (using cut-off of 706.5 pg/mL), in seven of these there was concordance between PET and clinical diagnosis which explains the better performance of ¹⁸F-Flutemetamol PET as a predictor of clinical AD diagnosis (see Fig 1).

There were 11 patients (15%) with discordance between Aβ PET and clinical diagnosis (see Fig 1). All except one had concordance between Aβ PET and CSF Aβ₄₂ (using cut-off of 706.5 pg/mL), in which eight had no evidence of Aβ pathology combined with a clinical AD diagnosis and two had evidence of Aβ pathology combined with a clinical non-AD diagnosis. One review reported a proportion of 2–32% of patients with a clinical AD diagnosis with a negative Aβ PET [46], while others have found this proportion to be as high as 61.3% [47]. The NIA-AA criteria applied here focuses on the clinical presentation where biomarkers are to be used only for support to refine confidence in the diagnosis. Although, the majority of patients without evidence of Aβ pathology (either PET or CSF) and clinical AD diagnosis (both dementia and MCI) in this study did have evidence of neurodegeneration. These cases may be categorized as “Suspected non-Alzheimer disease pathophysiology” (SNAP), which is a biomarker-based concept in which evidence of Aβ deposition is lacking, but evidence of neurodegeneration is present [48]. The sensitivity of the NIA-AA criteria has previously been reported with sensitivities ranging from 65.6% to 79.5% for probable and possible AD respectively, but with specificities considerably higher [49]. Whether biomarkers are to be included in the clinical criteria to further improve their sensitivity is still under investigation.

Another explanation for a negative Aβ PET with a clinical AD diagnosis is the possibility of a false-negative PET. This is thought to occur if non-fibrillar, smaller or less dense Aβ species are dominating, which may be challenging to detect by qualitative Aβ PET [50]. We did not apply quantification methods to evaluate ¹⁸F-Flutemetamol PET as this study reflects clinical practice in which qualitative classification is used, which is currently the only validated method [14, 21]. Although one autopsy study found that ¹⁸F-Flutemetamol can detect also diffuse Aβ plaques [16, 51], the ability of Aβ PET to detect the smallest and oligomeric toxic Aβ species is unlikely. Wolk et al included both qualitative and quantitative classification of images and found similar results using the two methods [52]. In preclinical stages of the AD continuum however, it is possible that quantitative PET will provide an even higher sensitivity for Aβ which may be of value, especially in drug trials. Cortical Aβ burden demonstrated with PET is nevertheless a sensitive biomarker, without being specific, for AD and its effect on diagnoses and outcomes is still under investigation. This stress the importance of an appropriate use of Aβ PET imaging [53].

The women included in this study had more evidence of Aβ pathology. There were no significant differences in age, MMSE, CDR, T-tau or P-tau between females and males. However, a larger proportion of women also had a clinical AD diagnosis. Whether this indicate more severe disease at the time of diagnostic workup in women remains unclear. Sex differences have been reported previously [54], the occurrence of AD and other forms of dementia has been shown to be higher in women [2, 55] and studies show that in cognitively normal individuals men are more likely to have SNAP than women [48]. In the presented population we found eight patients (12,5%) that may have SNAP and five of these were males.

The demonstrated excellent interrater agreement of ¹⁸F-Flutemetamol PET in this study have been reported to be similarly high in other studies [21, 52], which confirms that the qualitative method is a highly robust and effective way to classify Aβ PET in patients in a memory clinic setting. Despite one of the memory clinic physicians who made diagnoses were blind to the ¹⁸F-Flutemetamol PET result, the interrater agreement of diagnoses was excellent. However, both physicians had the Aβ₄₂ level in CSF available, suggesting that these methods for evaluating Aβ load may be used interchangeably to support a clinical diagnosis.

A limitation of this study is the rather low number of patients included, which is partly a consequence of excluding patients with more than 190 days between PET and lumbar puncture. All data was collected from clinical practice which may be regarded as both a strength and a limitation. The inclusion was performed through a memory clinic with a preselected population with typically younger patients with most likely more challenging diagnoses. We did not include information about the APOE genotype nor did we have a control group, both which would have strengthened the study. We did not perform semi-quantification of ¹⁸F-Flutemetamol PET, mainly due to lack of an appropriate MRI for such purposes. Semi-quantification could have provided an objective evaluation of amyloid burden as well as improved the correlations to CSF biomarkers further and is consequently a limitation of this study. All CSF analyses were performed according to the same routine, analyzed in the same laboratory and all PET images were acquired at the same PET scanner with the same standardized protocol, which are considered strengths of this study.

In the present study we found a high correlation between qualitative ¹⁸F-Flutemetamol PET and Aβ₄₂ in CSF in patients referred from a memory clinic and ¹⁸F-Flutemetamol PET was the best predictor of clinical AD diagnosis. Thus, ¹⁸F-Flutemetamol PET is a valuable tool to refine confidence that a patients’ cognitive impairment is caused by pathophysiological changes in the AD continuum.