Automated Diagnosis of Coronary Artery Disease using Pattern Recognition Approach

Desai, Usha and Nayak, Gurudas C and Seshikala, G and Martis, Roshan J (2017) Automated Diagnosis of Coronary Artery Disease using Pattern Recognition Approach. In: 39th Annual International Conference of the IEEE, 2017, Seogwipo, South Korea.

[img] PDF
3032.pdf - Published Version
Restricted to Registered users only

Download (905kB) | Request a copy


Coronary Artery Disease (CAD) is the mostleading Cardiovascular Disease (CVD), which results due to buildup of plaque inside the coronary arteries. The CAD and Normal Sinus Rhythm (NSR) heartbeats can be discriminated and diagnosed noninvasively using the standard tool Electrocardiogram (ECG). However,manual diagnosis of ECG is tiresome and timeconsuming task, due to complex nature and unseennonlinearities of ECG. Hence an automated system playsa substantial role. In this study, CAD and NSRheartbeats are discriminated and diagnosed using Higher-Order Statistics (HOS) cumulants features. Further, the cumulants coefficients dimensionality reduced using Principal Components Analysis (PCA) and the medically significant features (p-value<0.05) Principal Components (PCs) are subjected forclassification using Random Forest (RAF) and RotationForest (ROF) ensemble classifiers. Proposed system isrobust which helps in screening CAD risk factors andtelemonitoring applications.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: ECG Signal Preprocessing; Dimensionality Reduction; Student’s t-test; Decision Tree; Binary Confusion Matrix.
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 18 Nov 2017 05:05
Last Modified: 18 Nov 2017 05:05

Actions (login required)

View Item View Item