Rapid screening of hepatitis B using Raman spectroscopy and long short-term memory neural network

  • PDF / 1,190,447 Bytes
  • 9 Pages / 595.276 x 790.866 pts Page_size
  • 32 Downloads / 210 Views

DOWNLOAD

REPORT


ORIGINAL ARTICLE

Rapid screening of hepatitis B using Raman spectroscopy and long short-term memory neural network Xin Wang 1 & Shengwei Tian 1 & Long Yu 2 & Xiaoyi Lv 1 & Zhaoxia Zhang 3 Received: 29 September 2019 / Accepted: 25 March 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020

Abstract This study presents a rapid method to screen hepatitis B patients using serum Raman spectroscopy combined with long shortterm memory neural network (LSTM). The serum samples taken from 435 hepatitis B patients and 699 non-hepatitis B people were measured in this experiment. Specific biomolecular changes in three groups of serum samples could be seen in the tentative assignment of Raman peaks. First, principal component analysis (PCA) was used for extracting key features of spectral data, which reduces the dimension of the multidimensional spectrum. Then, LSTM is used to train the spectral data. Finally, the full connection layer completes the classification of HBV. The diagnostic accuracy of the first LSTM model is 97.32%, and the value of AUC is 0.995. The results from the study demonstrate that the combination of serum Raman spectroscopy technique and LSTM provides an effective technical approach to the screening of hepatitis B. Keywords Serum . Raman spectroscopy . Hepatitis B . LSTM

Introduction Hepatitis B is a life-threatening viral infection with high risk, high prevalence and long periodicity. It has become one of the world’s major public problems, affecting an estimated 350 million to 400 million people [1, 2]. According to statistics, the number of hepatitis B in China has exceeded 93 million and has been increasing each year. If mishandled, it may develop chronic hepatitis and even cirrhosis and liver cancer [3]. This not only brings high diagnosis and treatment costs to patients but also consumes medical and social resources seriously. Therefore, the correct detection and treatment of hepatitis B are particularly important.

* Long Yu [email protected] * Xiaoyi Lv [email protected] 1

College of Software Engineering, Xin Jiang University, Urumuqi 830000, China

2

College of Network Center, Xin Jiang University, Urumuqi 830046, China

3

Department of Laboratory Medicine, The First Affiliated Hospital of Xinjiang Medical University, Urumuqi 830000, China

Hepatitis B surface antigen (HBsAg), hepatitis B surface antibody (HBsAb), e antigen (HBsAb), e antibody (HBeAb) and core antibody (HBcAb) were tested to confirm the infection of hepatitis B virus [4]. Studies have shown that infection of hepatitis B has two phases, acute hepatitis and chronic hepatitis [5]. Polymerase chain reaction (PCR) is used for the detection of these antigens and antibodies in the bloodstream to distinguish between acute and chronic infections. Due to the limitations of technology and cost, this test is not used as standard diagnostics. Enzyme-linked immunosorbent assay (ELISA) is widely used for the detection of HBV markers. However, the stability and accuracy of the test results are easily disturbed, which can easily caus