# Improving Clinical Predictions through Unsupervised Time Series Representation Learning

arXiv: https://arxiv.org/abs/1812.00490 · HTML: https://mlsanity.com/paper/1812.00490/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2018.

## Built on by (most cited first, 24 of 24)

- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://mlsanity.com/paper/2202.04770/) (2022)
- [Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review](https://mlsanity.com/paper/2107.02975/) (2021)
- [Neighborhood Contrastive Learning Applied to Online Patient Monitoring](https://mlsanity.com/paper/2106.05142/) (2021)
- [MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series](https://mlsanity.com/paper/2212.01141/) (2022)
- [Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Models](https://mlsanity.com/paper/2310.15290/) (2023)
- [Generative modeling for time series via Schr"odinger bridge](https://mlsanity.com/paper/2304.05093/) (2023)
- [Unsupervised Representation Learning for Time Series: A Review](https://mlsanity.com/paper/2308.01578/) (2023)
- [On the Importance of Clinical Notes in Multi-modal Learning for EHR Data](https://mlsanity.com/paper/2212.03044/) (2022)
- [Deep Learning for Time Series Forecasting: A Survey](https://mlsanity.com/paper/2503.10198/) (2025)
- [Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder](https://mlsanity.com/paper/2306.06579/) (2023)
- [Conditional Loss and Deep Euler Scheme for Time Series Generation](https://mlsanity.com/paper/2102.05313/) (2021)
- [A Self-Supervised Framework for Function Learning and Extrapolation](https://mlsanity.com/paper/2106.07369/) (2021)
- [Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax](https://mlsanity.com/paper/2209.00655/) (2022)
- [Convolution-enhanced Evolving Attention Networks](https://mlsanity.com/paper/2212.08330/) (2022)
- [Improving Prediction of Low-Prior Clinical Events with Simultaneous General Patient-State Representation Learning](https://mlsanity.com/paper/2106.14838/) (2021)
- [Deep Normed Embeddings for Patient Representation](https://mlsanity.com/paper/2204.05477/) (2022)
- [Fully Embedded Time-Series Generative Adversarial Networks](https://mlsanity.com/paper/2308.15730/) (2023)
- [Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning](https://mlsanity.com/paper/2508.11210/) (2025)
- [Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction](https://mlsanity.com/paper/2407.19359/) (2024)
- [Two-Stage Representation Learning for Analyzing Movement Behavior Dynamics in People Living with Dementia](https://mlsanity.com/paper/2502.09173/) (2025)
- [Analyzing Patient Daily Movement Behavior Dynamics Using Two-Stage Encoding Model](https://mlsanity.com/paper/2502.09947/) (2025)
- [MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2509.16078/) (2025)
- [SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework](https://mlsanity.com/paper/2609.02203/) (2026)

## Abstract (arXiv)

In this work, we investigate unsupervised representation learning on medical time series, which bears the promise of leveraging copious amounts of existing unlabeled data in order to eventually assist clinical decision making. By evaluating on the prediction of clinically relevant outcomes, we show that in a practical setting, unsupervised representation learning can offer clear performance benefits over end-to-end supervised architectures. We experiment with using sequence-to-sequence (Seq2Seq) models in two different ways, as an autoencoder and as a forecaster, and show that the best performance is achieved by a forecasting Seq2Seq model with an integrated attention mechanism, proposed here for the first time in the setting of unsupervised learning for medical time series.