Pancreatic Cancer Classification Using the Kernel-based Support Vector Machine (KSVM)

Abstract

Pancreatic cancer is a disease in which malignant (cancerous) tumor cells develop in pancreatic tissue; organ behind the lower abdomen and in front of the spine, which helps the body use and store energy from food by producing hormones to control blood sugar levels and digestive enzymes to break down food. Usually, pancreatic cancer is rarely detected at an early stage. One sign of a person with pancreatic cancer is diabetes, especially if it coincides with rapid weight loss, jaundice, or pain in the upper abdomen that spreads to the back. Among various types of cancer, pancreatic cancer has the lowest survival rate of only about 3%-6% of those diagnosed who can survive for five years. If patients are diagnosed on time for treatment, their chances of survival will increase. There is a tumor marker commonly used to follow the course of pancreatic cancer, namely CA 19-9 which can be measured in the blood. Healthy people can have small amounts of CA 19-9 in their blood. High levels of CA 19-9 are often a sign of pancreatic cancer. But sometimes, high levels can indicate other types of cancer or certain noncancerous disorders, including cirrhosis and gallstones. Because a high level of CA 19-9 is not specific for pancreatic cancer, CA 19-9 cannot be used by itself for screening or diagnosis. It can help monitor the progress of your cancer and the effectiveness of cancer treatment. In this study, the Kernel-based Support Vector Machine method is used to classify CA19-9 blood test results into two sections including data on patients diagnosed with pancreatic cancer or normal patients. This method will get an accuracy of around 95%.