Machine Learning Driven Profiling of Cerebrospinal Fluid Core Biomarkers in Alzheimer’s Disease and Other Neurological Disorders

Abstract

Amyloid-beta (Aβ) 42/40 ratio, tau phosphorylated at threonine-181 (p-tau), and total-tau (t-tau) are considered core biomarkers for the diagnosis of Alzheimer’s disease (AD). The use of fully automated biomarker assays has been shown to reduce the intra- and inter-laboratory variability, which is a critical factor when defining cut-off values. The calculation of cut-off values is often influenced by the composition of AD and control groups. Indeed, the clinically defined AD group may include patients affected by other forms of dementia, while the control group is often very heterogeneous due to the inclusion of subjects diagnosed with other neurological diseases (OND). In this context, unsupervised machine learning approaches may overcome these issues providing unbiased cut-off values and data-driven patient stratification according to the sole distribution of biomarkers. In this work, we took advantage of the reproducibility of automated determination of the CSF core AD biomarkers to compare two large cohorts of patients diagnosed with different neurological disorders and enrolled in two centers with established expertise in AD biomarkers. We applied an unsupervised Gaussian mixture model clustering algorithm and found that our large series of patients could be classified in six clusters according to their CSF biomarker profile, some presenting a typical AD-like profile and some a non-AD profile. By considering the frequencies of clinically defined OND and AD subjects in clusters, we subsequently computed cluster-based cut-off values for Aβ42/Aβ40, p-tau, and t-tau. This approach promises to be useful for large-scale biomarker studies aimed at providing efficient biochemical phenotyping of neurological diseases.

Clinical usefulness of cerebrospinal fluid biomarkers in Alzheimer's disease

“…In the literature, found levels for this cut-off point were between 0.059 and 0.073. 24,27 In general, small differences in these biomarkers' levels were found in comparison with other studies. Actually, it could be explained by the use of different analytical methods and the differences in the cohorts (age, status, inclusion of other dementias or neurological diseases).…”

“…For the ratio Aβ42/Aβ40, the cut‐off was 0.0695 which was very close to the results from João‐Leitão (0.068). In the literature, found levels for this cut‐off point were between 0.059 and 0.073 24,27 . In general, small differences in these biomarkers' levels were found in comparison with other studies.…”

A Novel Automated Chemiluminescence Method for Detecting Cerebrospinal Fluid Amyloid-Beta 1-42 and 1-40, Total Tau and Phosphorylated-Tau: Implications for Improving Diagnostic Performance in Alzheimer’s Disease

“…Here, we did not consider clustering approach [ 25 ] allowing to include all samples (i.e., all demented patients) in the analysis because the cohort is quite small, particularly also the group of other dementias, to foresee relevant results.…”

Cerebrospinal fluid lipoproteins inhibit α-synuclein aggregation by interacting with oligomeric species in seed amplification assays

“…NC were cognitively unimpaired subjects referring to the Centre for Memory Disturbances of the University of Perugia (Perugia, Italy), who underwent lumbar puncture for subjective memory complaints not confirmed by the neuropsychological assessment, or as part of a diagnostic work-up for minor neurological symptoms (i.e., headache, peripheral neuropathy, psychiatric disorders), showing no cognitive impairment after at least a 2-year follow-up. All the selected NC samples tested negative for both classical AD CSF biomarkers (amyloid 1–40 and 1–42 peptides ratio, total tau, and T181-phosphorylated tau) [ 18 ] and for α-syn SAA [ 19 ].…”