Raman spectroscopy and machine learning for biomedical applications: Alzheimer's disease diagnosis based on the analysis of cerebrospinal fluid

Elena Ryzhikova; Nicole M Ralbovsky; Vitali Sikirzhytski; Oleksandr Kazakov; Lenka Halamkova; Joseph Quinn; Earl A Zimmerman; Igor K Lednev

doi:10.1016/j.saa.2020.119188

Raman spectroscopy and machine learning for biomedical applications: Alzheimer's disease diagnosis based on the analysis of cerebrospinal fluid

Spectrochim Acta A Mol Biomol Spectrosc. 2021 Mar 5:248:119188. doi: 10.1016/j.saa.2020.119188. Epub 2020 Nov 13.

Authors

Elena Ryzhikova¹, Nicole M Ralbovsky¹, Vitali Sikirzhytski¹, Oleksandr Kazakov², Lenka Halamkova¹, Joseph Quinn³, Earl A Zimmerman⁴, Igor K Lednev⁵

Affiliations

¹ Department of Chemistry, University at Albany, SUNY, 1400 Washington Avenue, Albany, NY 12222, USA.
² Department of Physics, University at Albany, SUNY, 1400 Washington Avenue, Albany, NY 12222, USA.
³ Layton Aging and Alzheimer's Center, Oregon Health & Science University, Portland, OR 97239, USA.
⁴ Alzheimer's Center, Department of Neurology of Albany Medical Center, Albany, NY 12222, USA.
⁵ Department of Chemistry, University at Albany, SUNY, 1400 Washington Avenue, Albany, NY 12222, USA. Electronic address: ilednev@albany.edu.

PMID: 33268033
DOI: 10.1016/j.saa.2020.119188

Abstract

Current Alzheimer's disease (AD) diagnostics is based on clinical assessments, imaging and neuropsychological tests that are efficient only at advanced stages of the disease. Early diagnosis of AD will provide decisive opportunities for preventive treatment and development of disease-modifying drugs. Cerebrospinal fluid (CSF) is in direct contact with the human brain, where the deadly pathological process of the disease occurs. As such, the CSF biochemical composition reflects specific changes associated with the disease and is therefore the most promising body fluid for AD diagnostic test development. Here, we describe a new method to diagnose AD based on CSF via near infrared (NIR) Raman spectroscopy in combination with machine learning analysis. Raman spectroscopy is capable of probing the entire biochemical composition of a biological fluid at once. It has great potential to detect small changes specific to AD, even at the earliest stages of pathogenesis. NIR Raman spectra were measured of CSF samples acquired from 21 patients diagnosed with AD and 16 healthy control (HC) subjects. Artificial neural networks (ANN) and support vector machine discriminant analysis (SVM-DA) statistical methods were used for differentiation purposes, with the most successful results allowing for the differentiation of AD and HC subjects with 84% sensitivity and specificity. Our classification models show high discriminative power, suggesting the method has a great potential for AD diagnostics. The reported Raman spectroscopic examination of CSF can complement current clinical tests, making early AD detection fast, accurate, and inexpensive. While this study shows promise using a small sample set, further method validation on a larger scale is required to indicate the true strength of the approach.

Keywords: Alzheimer’s disease; Cerebrospinal fluid; Early diagnosis; Machine learning; Raman spectroscopy.

MeSH terms

Alzheimer Disease* / diagnosis
Early Diagnosis
Humans
Machine Learning
Neural Networks, Computer
Spectrum Analysis, Raman