Classification of Alzheimer’s disease in a mixed clinical cohort using biofluid Raman spectroscopy
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Introduction
There is a clinical unmet need for scalable, accessible and objective tests for dementia. Raman spectroscopy (RS) is a laser-based optical method that can rapidly provide chemically rich information (‘spectral biomarkers’) from biofluids but its utility for Alzheimer’s disease (AD) diagnosis has not been rigorously established.
Methods
We measured cerebrospinal fluid (CSF) samples from a mixed clinical cohort of patients (N=143) using RS. Machine-learning algorithms were trained, optimized and evaluated on Raman spectra to classify AD from non-AD.
Results
AD was classified with 93% accuracy and spectral biomarkers were identified and primarily assigned to protein-derived aromatic amino acids. These spectral biomarkers directly correlated with pathological CSF biomarker concentrations.
Conclusions
The feasibility of applying our simple, holistic and label-free spectral biomarker approach to dementia diagnosis was demonstrated. Compared to current and emerging methods, RS does not require sophisticated or specialized labs and is reagentless potentially offering unprecedented scalability and accessibility.
