# Temporal-Clustering Invariance in Irregular Healthcare Time Series

arXiv: https://arxiv.org/abs/1904.12206 · HTML: https://mlsanity.com/paper/1904.12206/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis](https://mlsanity.com/paper/2411.00696/) (2024)
- [Subtyping patients with chronic disease using longitudinal BMI patterns](https://mlsanity.com/paper/2111.05385/) (2021)
- [DCSF: Deep Convolutional Set Functions for Classification of Asynchronous Time Series](https://mlsanity.com/paper/2208.11374/) (2022)
- [Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling](https://mlsanity.com/paper/2403.00869/) (2024)
- [Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network](https://mlsanity.com/paper/2102.01147/) (2021)
- [Recent Trends in Modelling the Continuous Time Series using Deep Learning: A Survey](https://mlsanity.com/paper/2409.09106/) (2024)
- [4TaStiC: Time and trend traveling time series clustering for classifying long-term type 2 diabetes patients](https://mlsanity.com/paper/2505.07702/) (2025)

## Abstract (arXiv)

Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g., whether a series of blood tests are completed at once or in rapid succession should not alter predictions based on this data. Motivated by this intuition, we propose models for analyzing sequences of multivariate clinical time series data that are invariant to this temporal clustering. We propose an efficient data augmentation technique that exploits the postulated temporal-clustering invariance to regularize deep neural networks optimized for several clinical prediction tasks. We introduce two techniques to temporally coarsen (downsample) irregular time series: (i) grouping the data points based on regularly-spaced timestamps; and (ii) clustering them, yielding irregularly-paced timestamps. Moreover, we propose a MultiResolution Ensemble (MRE) model, improving predictive accuracy by ensembling predictions based on inputs sequences transformed by different coarsening operators. Our experiments show that MRE improves the mAP on the benchmark mortality prediction task from 51.53% to 53.92%.