Support vector machine for simultaneous determination of ultra trace concentrations of copper and cadmium in serum of patients with chronic hepatitis by adsorptive stripping voltammetry

Abstract

The purpose of this study is to establish a simple model and use the clinical data to predict the interferon efficacy. This model is a combination of Feature Subset Selection and the Classifier using a Support Vector Machine (SVM). The study indicates that when five features have been selected, the identification by the SVM is as follows: the identification rate for the effective group is 85%, and the ineffective group 83%.Serum trace elements concentrations and their ratios are frequently reported to be a good marker for diagnosing various diseases; one of these diseases is chronic liver diseases.  This study undertaken to simultaneous determine of Cu²⁺, and Cd²⁺ concentrations in sera from viral hepatitis (B and C) patients by adsorptive stripping voltammetry using 3-aminophthalhydrazide (luminol) as a complex agent and classification with support vector machine SVM. Donor's hepatitis patients and healthy persons were selected from different environmental areas, including Arar, Al-auiqilh and Rafha as unpolluted areas, and Al-Jouf , Tarif and Al- Qurayyat as a polluted areas. Hepatitis patients from polluted areas exhibited higher Cu²⁺ and Cd²⁺concentrations in their serum than those from the other areas. Patients with hepatitis B show higher levels of Cu²⁺, and Cd²⁺ in their serum than those with hepatitis C. Copper and cadmium presented at higher level in patient serum than in healthy ones. In this study the optimum reaction parameters and conditions studies are investigated. The calibration graphs were linear in the concentration range of 0.3– 142.5 and 0.065–60.0 ng/mL for copper and cadmium, respectively. The limit of detection of the method was 0.038ng/mL for Cu²⁺ and 0.013 ng/mL for Cd²⁺. The interference of some common ions was studied and it was concluded that application of this method for the determination of Cu²⁺ and Cd²⁺in the healthy control and hepatitis patient's serum led to satisfactory results.

Keywords: Support Vector Machine; adsorptive stripping voltammetry; chronic hepatitis; heavy metal.