Xiangnong Wu
Research Mentor(s): Vishwaratn Asthana
Mentor Department:
Authors: Xiangnong Wu, Vishwaratn Asthana
Session: Session 1 (9:00am – 9:50am)
Presentation Type: Poster 76
Abstract
Modeling outcomes, such as onset of heart failure (HF) or mortality, in patients following ST elevation myocardial infarction (STEMI) is challenging but clinically very useful. The acute insult following a myocardial infarction and chronic degeneration seen in HF involve a similar process where a loss of cardiomyocytes and abnormal remodeling lead to pump failure. This process may alter the strength and direction of the heart’s net depolarization signal. We hypothesize that changes over time in unique parameters extracted using vectorcardiography (VCG) have the potential to predict outcomes in patients post-STEMI and could eventually be used as a noninvasive and cost-effective surveillance tool for characterizing the severity and progression of HF to guide evidence-based therapies. Thus far, we have developed an algorithm to process the XML files that the ECG signals are stored in. We have also identified key ECG signal parameters that likely have clinical significance and encoded these into a script to process ECGs in batch. Our next step is to develop a machine learning algorithm to identify additional signal features that are not immediately obvious to a human user. Once complete, we will run our ECG parameters and machine learning script on a large database of ECGs from Michigan Medicine and correlate them with clinical outcomes.
