Raman spectroscopy combined with multiple algorithms for analysis and rapid screening of chronic renal failure.

Abstract

Chronic renal failure (CRF) is a symptom of kidney damage in the terminal stages. If a patient is not treated, then CRF will progress to uremia, which greatly reduces the lifespan of the patient. However, current screening strategies, including routine urine tests and medical imaging investigations, have poor sensitivity. Therefore, exploring new and efficient screening methods for CRF such as serum spectroscopy is of great significance. In this study, we first used Raman spectroscopy to classify sera from CRF patients and control subjects. A total of 47 samples from CRF patients and 54 samples from control subjects were acquired. The spectra revealed differences in the phospholipids and proteins between the CRF patients and control subjects. The differences between the CRF patients and control subjects were evaluated by building machine learning models. Subsequent principal component analysis (PCA) was first used for feature extraction. Then, back propagation (BP) neural network, extreme learning machine (ELM), genetic algorithms based on support vector machine (GA-SVM), particle swarm optimization-support vector machine (PSO-SVM), grid search-support vector machine (GS-SVM) and simulated annealing particle swarm optimization based on support vector machine (SAPSO-SVM) algorithms were employed to establish diagnostic models; the diagnostic accuracy of the six classifiers was 70.4 %, 71 %, 83.5 %, 86.9 %, 89.7 % and 82.8 %, respectively, for control subjects and CRF patients. The results show the potential of Raman spectroscopy in differentiating between the control subjects and CRF patients. Based on the limitations of current routine diagnostic methods, serum Raman spectroscopy may be an adjunct/replaceable method for the clinical diagnosis of CRF with the prospective validation of more samples.