Background: Ongoing efforts within the Alzheimer’s disease (AD) field have focused on improving the intra- and inter-laboratory variability for cerebrospinal fluid (CSF) biomarkers. Fully automated assays offer the possibility to eliminate sample manipulation steps and are expected to contribute to this improvement. Recently, fully automated chemiluminescence enzyme immunoassays for the quantification of all four AD biomarkers in CSF became available. The aims of this study were to (i) evaluate the analytical performance of the Lumipulse G β-Amyloid 1-42 (restandardized to Certified Reference Materials), β-Amyloid 1-40, total Tau, and pTau 181 assays on the fully automated LUMIPULSE G600II; (ii) compare CSF biomarker results of the Lumipulse G assays with the established manual ELISA assays (INNOTEST®) from the same company (Fujirebio); and (iii) establish cut-off values and the clinical performance of the Lumipulse G assays for AD diagnosis. Methods: Intra- and inter-assay variation was assessed in CSF samples with low, medium, and high concentrations of each parameter. Method comparison and clinical evaluation were performed on 40 neurological controls (NC) and 80 patients with a diagnosis of probable AD supported by a follow-up ≥ 3 years and/or positive amyloid PET imaging. A small validation cohort of 10 NC and 20 AD patients was also included to validate the cut-off values obtained on the training cohort. Results: The maximal observed intra-assay and inter-assay coefficients of variation (CVs) were 3.25% and 5.50%, respectively. Method comparisons revealed correlation coefficients ranging from 0.89 (for Aβ40) to 0.98 (for t-Tau), with those for Aβ42 (0.93) and p-Tau (0.94) in-between. ROC curve analysis showed area under the curve values consistently above 0.85 for individual biomarkers other than Aβ40, and with the Aβ42/40, Aβ42/t-Tau, and Aβ42/p-Tau ratios outperforming Aβ42. Validation of the cut-off values in the independent cohort showed a sensitivity ranging from 75 to 95% and a specificity of 100%. The overall percentage of agreement between Lumipulse and INNOTEST was very high (> 87.5%). Conclusions: The Lumipulse G assays show a very good analytical performance that makes them well-suited for CSF clinical routine measurements. The good clinical concordance between the Lumipulse G and INNOTEST assays facilitates the implementation of the new method in routine practice.

Dementia remains an extremely prevalent syndrome among older people and represents a major cause of disability and dependency. Alzheimer’s disease (AD) accounts for the majority of dementia cases and stands as the most common neurodegenerative disease. Since age is the major risk factor for AD, the increase in lifespan not only represents a rise in the prevalence but also adds complexity to the diagnosis. Moreover, the lack of disease-modifying therapies highlights another constraint. A shift from a curative to a preventive approach is imminent and we are moving towards the application of personalized medicine where we can shape the best clinical intervention for an individual patient at a given point. This new step in medicine requires the most recent tools and analysis of enormous amounts of data where the application of artificial intelligence (AI) plays a critical role on the depiction of disease–patient dynamics, crucial in reaching early/optimal diagnosis, monitoring and intervention. Predictive models and algorithms are the key elements in this innovative field. In this review, we present an overview of relevant topics regarding the application of AI in AD, detailing the algorithms and their applications in the fields of drug discovery, and biomarkers.

Background and purpose: Blood‐based biomarkers are promising tools for the diagnosis of Alzheimer disease (AD) at prodromal stages (mild cognitive impairment [MCI]) and are hoped to be implemented as screening tools for patients with cognitive complaints. In this work, we evaluated the potential of peripheral neurological biomarkers to predict progression to AD dementia and the relation between blood and cerebrospinal fluid (CSF) AD markers in MCI patients referred from a general neurological department.Methods: A group of 106 MCI patients followed at the Neurology Department of Coimbra University Hospital was included. Data regarding baseline neuropsychological evaluation, CSF levels of amyloid β 42 (Aβ42), Aβ40, total tau (t‐Tau), and phosphorylated tau 181 (p‐Tau181) were available for all the patients. Aβ42, Aβ40, t‐Tau, p‐Tau181, glial fibrillary acidic protein (GFAP), and neurofilament light chain (NfL) levels were determined in baseline stored serum and plasma samples by commercial SiMoA (Single Molecule Array) assays. Progression from MCI to AD dementia was assessed at follow‐up (mean = 5.8 ± 3.4 years).Results: At baseline, blood markers NfL, GFAP, and p‐Tau181 were significantly increased in patients who progressed to AD at follow‐up (p < 0.001). In contrast, plasma Aβ42/40 ratio and t‐Tau showed no significant differences between groups. NfL, GFAP, and p‐Tau181 demonstrated good diagnostic accuracy to identify progression to AD dementia (area under the curve [AUC] = 0.81, 0.80, and 0.76, respectively), which improved when combined (AUC = 0.89). GFAP and p‐Tau181 were correlated with CSF Aβ42. Association of p‐Tau181 with NfL was mediated by GFAP, with a significant indirect association of 88% of the total effect.Conclusions: Our findings highlight the potential of combining blood‐based GFAP, NfL, and p‐Tau181 to be applied as a prognostic tool in MCI.

Background: Mild cognitive impairment (MCI) exhibits considerable heterogeneity, requiring accurate characterization through classification and prognostic models. In clinical research, data-driven models offer valuable insights for classification, stratification, and predicting progression to dementia. Objective: We implemented computational techniques to characterize MCI patients and develop multistate progression models for Alzheimer's disease (AD). Methods: Datasets comprising 544 MCI patients from Coimbra University Hospital and 497 from the ADNI, were processed using machine learning techniques, including dimensionality reduction and partition clustering algorithms. For longitudinal measures (n = 351), multistate non-Markov was applied to generate transition probability estimates. Results: Our analyses gave 4 possible subgroups of MCI patients: 1) increased cognitive reserve, 2) suspected AD pathology, 3) psychological manifestations, and 4) cardiovascular risk factors. Progression within these subgroups showed variations. The likelihood of progressing to AD dementia was estimated over a range of 5 months for those with suspected AD pathology and 66 months for those with psychological manifestations. Conclusions: Our findings support the significance of computational methods to improve the characterization and prognosis of MCI patients. We suggest that these four MCI subgroups should be considered for clinical monitoring.

Background and ObjectivesVariants of Alzheimer disease (AD) particularly affect early-onset patients. Yet, most of these patients lack a family history of similar or other presentations, suggesting...

Introduction: Blood-based neurofilament light chain (NfL), a neuronal cytoskeleton protein, has proven to be a dynamic and robust biomarker for neurodegeneration. The influence of age on NfL levels has been extensively documented in cerebrospinal fluid studies, with blood quantification showing similar trends. To aid the clinical interpretation of NfL values, it is crucial to establish normal reference intervals through population-specific studies that account for NfL’s dynamic range. Methods: In this study, we determined reliable age-stratified reference values for serum NfL (sNfL) using the single-molecule array (SiMoA) immunoassay in individuals with no evidence of cognitive impairment according to age- and education-adjusted normative data for the Mini-Mental State Examination (MMSE), recruited from the central region of Portugal, across a broad age range. Results: Our sample comprised 335 individuals (median age of 53 years, 57% female) aged 20 to 99 years. We found a strong correlation between age and sNfL levels (rho=0.72, p<0.001). Age-stratified reference limits (upper 95th percentile in each decade) were established as follows: 20-30 years= 9.77 pg/mL; 31-40 years= 13.3 pg/mL; 41-50 years= 16.5 pg/mL; 51-60 years= 21.2 pg/mL; 61-70 years= 41.3 pg/mL; 71-80 years= 48.1 pg/mL; 80+ years= 62.5 pg/mL. Conclusion: These findings provide a unique national normative baseline for the Portuguese population.