Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning
This work addresses the challenge of improving clinical decision-making for medical professionals by enhancing the analysis of irregular and incomplete medical time series data, representing an incremental advancement over existing single-perspective methods.
The paper tackled the problem of analyzing irregular medical time series with significant missingness by proposing a joint learning framework that integrates sequence and image representations using self-supervised learning. The results showed that this approach outperformed seven state-of-the-art models on three real-world clinical datasets and demonstrated greater robustness in handling simulated missingness scenarios.
Medical time series are often irregular and face significant missingness, posing challenges for data analysis and clinical decision-making. Existing methods typically adopt a single modeling perspective, either treating series data as sequences or transforming them into image representations for further classification. In this paper, we propose a joint learning framework that incorporates both sequence and image representations. We also design three self-supervised learning strategies to facilitate the fusion of sequence and image representations, capturing a more generalizable joint representation. The results indicate that our approach outperforms seven other state-of-the-art models in three representative real-world clinical datasets. We further validate our approach by simulating two major types of real-world missingness through leave-sensors-out and leave-samples-out techniques. The results demonstrate that our approach is more robust and significantly surpasses other baselines in terms of classification performance.