Development of a prediction classifier for the early diagnosis of liver cancer

EasyChair Preprint 568

Abstract

Hepatocellular carcinoma (HCC) is the second cause of cancer-related death worldwide, and the incidence rate of liver cancer has continuously increased, with approximately 750,000 new diagnosed cases each year. Especially in China, both the incidence and mortality rate of HCC have been ranked second among all cancers. Importantly, HCC mortality rate is similar to its incidence rate, indicating that most patients with liver cancer die from HCC. In clinical practice, liver cancers are usually diagnosed by detecting alpha-fetoprotein (AFP) and abdominal ultrasound. However, abnormal AFP is usually detected at late stages of liver cancer, in which most patients are refractory to surgery, radiotherapy and chemotherapy. Moreover, AFP is not detectable in some liver cancer patients. In this study, we aimed to establish an alternative diagnostic method for liver cancer patients by analyzing hidden patterns and relationships among multiple specific markers of liver cancers. By building a predictive classification of liver cancer and the relationship between different markers, a support vector machine (SVM) classifier was developed. Our SVM classifier integrated 22 specific markers. Our results revealed that the input of these 22 markers into the classifier could accurately determine the exitence of HCC in a patient. Our established SVM classifier may achieve the early prediction of liver cancer, thereby improving the accuracy of diagnosis and treatment of live cancer patients.

Keyphrases: alpha-fetoprotein, hepatocellular carcinoma, specific markers, support vector machine classifier

@booklet{EasyChair:568,
  author    = {Di Wu and Jianhua Cao and Wei Li and Xin Wang},
  title     = {Development of a prediction classifier for the early diagnosis of liver cancer},
  doi       = {10.29007/3g25},
  howpublished = {EasyChair Preprint 568},
  year      = {EasyChair, 2018}}