Identification of individual red blood cells by single-cell Raman spectroscopy combined with machine learning

Abstract

Raman spectroscopy, a "fingerprint" spectrum of substances, can be used to characterize various biological and chemical samples. To allow for blood classification using single-cell Raman spectroscopy, several machine learning algorithms were implemented and compared. A single-cell laser optical tweezer Raman spectroscopy system was established to obtain the Raman spectra of red blood cells. The Boruta algorithm extracted the spectral feature frequency shift, reduced the spectral dimension, and determined the essential features that affect classification. Next, seven machine learning classification models and deep learning model without dimensionality reduction are analyzed and compared based on the classification accuracy, precision, and recall indicators. The results show that support vector machines and convolutional neural network are the two most appropriate machine learning algorithms for single-cell Raman spectrum blood classification, and the findings provide essential guidance for future research studies.