Multiple Instance Learning for ECG Risk Stratification

Divya Shanmugam, Davis Blalock, John Guttag
Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:124-139, 2019.

Abstract

Patients who suffer an acute coronary syndrome are at elevated risk for adverse cardiovascular events such as myocardial infarction and cardiovascular death. Accurate assessment of this risk is crucial to their course of care. We focus on estimating a patient’s risk of cardiovascular death after an acute coronary syndrome based on a patient’s raw electrocardiogram (ECG) signal. Learning from this signal is challenging for two reasons: 1) positive examples signifying a downstream cardiovascular event are scarce, causing drastic class imbalance, and 2) each patient’s ECG signal consists of thousands of heartbeats, accompanied by a single label for the downstream outcome. Machine learning has been previously applied to this task, but most approaches rely on hand-crafted features and domain knowledge. We propose a method that learns a representation from the raw ECG signal by using a multiple instance learning framework. We present a learned risk score for cardiovascular death that outperforms existing risk metrics in predicting cardiovascular death within 30, 60, 90, and 365 days on a dataset of 5000 patients.

Cite this Paper

BibTeX
@InProceedings{pmlr-v106-shanmugam19a, title = {Multiple Instance Learning for ECG Risk Stratification}, author = {Shanmugam, Divya and Blalock, Davis and Guttag, John}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {124--139}, year = {2019}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {106}, series = {Proceedings of Machine Learning Research}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/shanmugam19a/shanmugam19a.pdf}, url = {https://proceedings.mlr.press/v106/shanmugam19a.html}, abstract = {Patients who suffer an acute coronary syndrome are at elevated risk for adverse cardiovascular events such as myocardial infarction and cardiovascular death. Accurate assessment of this risk is crucial to their course of care. We focus on estimating a patient’s risk of cardiovascular death after an acute coronary syndrome based on a patient’s raw electrocardiogram (ECG) signal. Learning from this signal is challenging for two reasons: 1) positive examples signifying a downstream cardiovascular event are scarce, causing drastic class imbalance, and 2) each patient’s ECG signal consists of thousands of heartbeats, accompanied by a single label for the downstream outcome. Machine learning has been previously applied to this task, but most approaches rely on hand-crafted features and domain knowledge. We propose a method that learns a representation from the raw ECG signal by using a multiple instance learning framework. We present a learned risk score for cardiovascular death that outperforms existing risk metrics in predicting cardiovascular death within 30, 60, 90, and 365 days on a dataset of 5000 patients.} }
Endnote
%0 Conference Paper %T Multiple Instance Learning for ECG Risk Stratification %A Divya Shanmugam %A Davis Blalock %A John Guttag %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-shanmugam19a %I PMLR %P 124--139 %U https://proceedings.mlr.press/v106/shanmugam19a.html %V 106 %X Patients who suffer an acute coronary syndrome are at elevated risk for adverse cardiovascular events such as myocardial infarction and cardiovascular death. Accurate assessment of this risk is crucial to their course of care. We focus on estimating a patient’s risk of cardiovascular death after an acute coronary syndrome based on a patient’s raw electrocardiogram (ECG) signal. Learning from this signal is challenging for two reasons: 1) positive examples signifying a downstream cardiovascular event are scarce, causing drastic class imbalance, and 2) each patient’s ECG signal consists of thousands of heartbeats, accompanied by a single label for the downstream outcome. Machine learning has been previously applied to this task, but most approaches rely on hand-crafted features and domain knowledge. We propose a method that learns a representation from the raw ECG signal by using a multiple instance learning framework. We present a learned risk score for cardiovascular death that outperforms existing risk metrics in predicting cardiovascular death within 30, 60, 90, and 365 days on a dataset of 5000 patients.
APA
Shanmugam, D., Blalock, D. & Guttag, J.. (2019). Multiple Instance Learning for ECG Risk Stratification. Proceedings of the 4th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 106:124-139 Available from https://proceedings.mlr.press/v106/shanmugam19a.html.

Related Material