Wrist pulse signal classification for inflammation of appendix, pancreas, and duodenum

Wrist pulse signal is believed to contain critical information of the patients´ health condition. This project aims to analyze the time series wrist pulse signals in order to distinguish patients suffering from various symptoms with healthy people. In this paper, the four inflammation symptoms tackled in this project are Appendicitis (A), Acute Appendicitis (AA), Pancreatitis (P) and Duodenal Bulb Ulcer (DBU). Moreover, studying the characteristic of blood flow in arteries and cardiac cycle is crucial for the sake of selecting features from the wrist pulse signals. The defined Doppler parameters in the wrist pulse signal are defined as the disease sensitive features. Furthermore, the features extracted are considered as the parameters for training the Support Vector Machine (SVM) classifier. The classification accuracy can reach over 88% in distinguishing patients with healthy persons from Acute Appendicitis and up to 98% from Pancreatitis. These results indicate the methodology proposed in this project can provide an advanced idea for enhancing the research of wrist pulse signal analysis.