Key result
A multiple instance learning convolutional neural network applied to raw ECG signals outperformed existing metrics in predicting 90-day cardiovascular death, achieving an AUC of 0.81 compared to 0.68 for morphological variability.
Why the study?
Patients with acute coronary syndrome face elevated risk of adverse cardiovascular events, but estimating risk directly from raw ECG signals is challenging due to class imbalance and long multi-beat signals.
Does a multiple instance learning framework applied to raw ECG signals improve prediction of cardiovascular death in patients after an acute coronary syndrome compared to existing risk metrics?
Observational (n=4,975)
Does a multiple instance learning framework applied to raw ECG signals improve prediction of cardiovascular death in patients after an acute coronary syndrome compared to existing risk metrics?
A novel multiple instance learning framework applied to raw ECG signals outperforms existing metrics in predicting cardiovascular death up to 1 year after an acute coronary syndrome.
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.
No takes yet. Share an insight, caveat, or question.
Shanmugam et al. (2018) conducted an observational in Acute coronary syndrome (n=4,975). Multiple Instance Learning Convolutional Neural Network (MIL-CNN) ECG risk score vs. Existing ECG-based risk metrics (e.g., Morphological Variability in Beat-space [MVB], TRS, LR-RNN) was evaluated on Prediction of cardiovascular death within 30, 60, 90, and 365 days (measured by AUC). A multiple instance learning convolutional neural network applied to raw ECG signals outperformed existing metrics in predicting 90-day cardiovascular death, achieving an AUC of 0.81 compared to 0.68 for morphological variability.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: