Assessment of the Concordance and Diagnostic Accuracy Between Elecsys and Lumipulse Fully Automated Platforms and Innotest

Abstract

Manual ELISA assays are the most commonly used methods for quantification of biomarkers; however, they often show inter- and intra-laboratory variability that limits their wide use. Here, we compared the Innotest ELISA method with two fully automated platforms (Lumipulse and Elecsys) to determine whether these new methods can provide effective substitutes for ELISA assays. We included 149 patients with AD (n = 34), MCI (n = 94) and non-AD dementias (n = 21). Aβ42, T-tau, and P-tau were quantified using the ELISA method (Innotest, Fujirebio Europe), CLEIA method on a Lumipulse G600II (Fujirebio Diagnostics), and ECLIA method on a Cobas e 601 (Roche Diagnostics) instrument. We found a high correlation between the three methods, although there were systematic differences between biomarker values measured by each method. Both Lumipulse and Elecsys methods were highly concordant with clinical diagnoses, and the combination of Lumipulse Aβ42 and P-tau had the highest discriminating power (AUC 0.915, 95% CI 0.822-1.000). We also assessed the agreement of AT(N) classification for each method with AD diagnosis. Although differences were not significant, the use of Aβ42/Aβ40 ratio instead of Aβ42 alone in AT(N) classification enhanced the diagnostic accuracy (AUC 0.798, 95% CI 0.649-0.947 vs. AUC 0.778, 95% CI 0.617-0.939). We determined the cut-offs for the Lumipulse and Elecsys assays based on the Aβ42/Aβ40 ratio ± status as a marker of amyloid pathology, and these cut-offs were consistent with those recommended by manufacturers, which had been determined based on visual amyloid PET imaging or diagnostic accuracy. Finally, the biomarker ratios (P-tau/Aβ42 and T-tau/Aβ42) were more consistent with the Aβ42/Aβ40 ratio for both Lumipulse and Elecsys methods, and Elecsys P-tau/Aβ42 had the highest consistency with amyloid pathology (AUC 0.994, 95% CI 0.986-1.000 and OPA 96.4%) at the ≥0.024 cut-off. The Lumipulse and Elecsys cerebrospinal fluid (CSF) AD assays showed high analytical and clinical performances. As both automated platforms were standardized for reference samples, their use is recommended for the measurement of CSF AD biomarkers compared with unstandardized manual methods, such as Innotest ELISA, that have demonstrated a high inter and intra-laboratory variability.

Keywords: Alzheimer’s disease; assay automation; biomarker; cerebrospinal fluid; cut-off.

FIGURE 1

The correlation and Bland-Altman plots for Aβ42, T-tau, and P-tau measurements obtained by Lumipulse and Innotest ELISA methods (n = 149). Each point is defined as the measurements of Lumipulse and ELISA assays on the same biological sample. In correlation plots, the solid lines represent the estimated regression line, and the dotted line represents the identity line (x = y). In the Bland-Altman plots, solid lines represent the slope observed.

FIGURE 2

The correlation and Bland-Altman plots for Aβ42, T-tau, and P-tau measurements obtained by Elecsys and Innotest methods (for P-tau and T-tau n = 145; for Aβ42 n = 135). Each point is defined as the measurement of Elecsys and Innotest assays on the same biological sample. In correlation plots, the solid lines represent the estimated regression line, and the dotted line represents the identity line (x = y). In the Bland-Altman plots, solid lines represent the slope observed.

FIGURE 3

The correlation and Bland-Altman plots for Aβ42, T-tau, and P-tau measurements obtained by Lumipulse and Elecsys methods (for P-tau and T-tau n = 145; for Aβ42 n = 137). Each point is defined as the measurement of Lumipulse and Elecsys assays on the same biological sample. In correlation plots, the solid lines represent the estimated regression line, and the dotted line represents the identity line (x = y). In the Bland-Altman plots, solid lines represent the slope observed.

FIGURE 4

CSF biomarkers that yielded the maximum Youden index versus Aβ42/Aβ40 ratio status in the receiver operating characteristics analysis.