Orientation-Invariant ECG-Based Virtual Pathology Stethoscope Tracking for Standardized Patient Heart Auscultation

Date of Award

Fall 2012

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computational Modeling & Simulation Engineering

Program/Concentration

Modeling and Simulation

Committee Director

Frederic D. McKenzie

Committee Member

Roland R. Mielke

Committee Member

Michel Audette

Committee Member

Jiang Li

Call Number for Print

Special Collections LD4331.E58 K53 2012

Abstract

Cardiac auscultation (CA), the act of listening to the heart sounds, is a critical physician's skill that provides substantial information for diagnosing many cardiovascular disorders; therefore, competent training can be a key for accurate and reliable diagnosis. The teaching of CA has been an area of recognized importance since the inception of the stethoscope. However, recent changes in health-care, such as limited student access to patients and higher reliance on competing technologies have made it challenging to teach bedside CA techniques.

Over the past few decades, standardized patients (SPs), individuals trained to portray real patients, have been widely used for such training, thereby overcoming the problem of waiting for suitable real patients. However, SPs are typically healthy individuals and rarely exhibit the same abnormal CA findings as their attributed disorders. This limits the range and variety of symptoms that can be demonstrated to medical students.

This thesis seeks to improve the CA skills of medical students by virtual pathology simulation that utilizes modified stethoscopes (virtual pathology stethoscopes) in tandem with standardized patients. In this work, we describe a novel orientation-invariant stethoscope tracking method for placing virtual symptoms in correct auscultation areas based on recorded electrocardiogram (ECG) signals. This would extend the capabilities of SPs and allow trainees to perform realistic CA and hear abnormal heart or lung sounds in otherwise healthy patient actors.

Recorded ECG signals of two different SPs with a wide range of the stethoscope's chest piece orientations were processed from four CA regions. After processing the signals and extracting proper features, different classifiers were applied for assessment of the proposed tracking method- 95% and 87% accuracy was obtained for SPl and SP2, respectively. These findings suggest that the system is invariant to the stethoscope's chest piece orientation and can accurately distinguish the different auscultation areas. The proposed system provides an efficient and cost-effective method for tracking virtual pathology stethoscopes which can be used in training medical practitioners on proper heart auscultation.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/hw4f-tr55

This document is currently not available here.

Share

COinS