Abstract:
Patients who have suffered an acute coronary syndrome (ACS) are at elevated risk of future adverse events, including fatal arrhythmias or myocardial infarction. Risk stratification--he identification of high-risk patients--s an important step in determining who is most likely to benefit from aggressive treatments. We propose a new automated risk stratification technique that uses the long-term electrocardiographic data routinely recorded in the days following an ACS. Data obtained from clinical drug trials indicates that our technique, called MV-DF (morphologic variability diagnostic frequencies), can significantly improve prognostication for ACS patients. Patients with MV-DF values in the highest quartile show a more than five-fold elevated risk of death in the 90 days following a non-ST-elevation ACS. We also propose techniques to construct models of the dynamics of cardiac behavior. Preliminary results suggest that such techniques may be useful for short-term prediction of fatal arrhythmias. Our results suggest that long-term ECG-based risk assessment techniques--n particular, methods incorporating information about morphologic variability--re an effective and practical way to select appropriate treatment options for cardiovascular disease patients.
Description:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.; This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.; Includes bibliographical references (p. 95-100).
