TY - JOUR AU - Lan, Xiang AU - Ng, Dianwen AU - Hong, Shenda AU - Feng, Mengling PY - 2022/06/28 Y2 - 2024/03/29 TI - Intra-Inter Subject Self-Supervised Learning for Multivariate Cardiac Signals JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 4 SE - AAAI Technical Track on Domain(s) Of Application DO - 10.1609/aaai.v36i4.20376 UR - https://ojs.aaai.org/index.php/AAAI/article/view/20376 SP - 4532-4540 AB - Learning information-rich and generalizable representations effectively from unlabeled multivariate cardiac signals to identify abnormal heart rhythms (cardiac arrhythmias) is valuable in real-world clinical settings but often challenging due to its complex temporal dynamics. Cardiac arrhythmias can vary significantly in temporal patterns even for the same patient (i.e., intra subject difference). Meanwhile, the same type of cardiac arrhythmia can show different temporal patterns among different patients due to different cardiac structures (i.e., inter subject difference). In this paper, we address the challenges by proposing an Intra-Inter Subject Self-Supervised Learning (ISL) model that is customized for multivariate cardiac signals. Our proposed ISL model integrates medical knowledge into self-supervision to effectively learn from intra-inter subject differences. In intra subject self-supervision, ISL model first extracts heartbeat-level features from each subject using a channel-wise attentional CNN-RNN encoder. Then a stationarity test module is employed to capture the temporal dependencies between heartbeats. In inter subject self-supervision, we design a set of data augmentations according to the clinical characteristics of cardiac signals and perform contrastive learning among subjects to learn distinctive representations for various types of patients. Extensive experiments on three real-world datasets were conducted. In a semi-supervised transfer learning scenario, our pre-trained ISL model leads about 10% improvement over supervised training when only 1% labeled data is available, suggesting strong generalizability and robustness of the model. ER -