# Data-Driven Discovery of Feature Groups in Clinical Time Series

arXiv: https://arxiv.org/abs/2511.08260 · HTML: https://mlsanity.com/paper/2511.08260/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Efficient Content-Based Sparse Attention with Routing Transformers](https://mlsanity.com/paper/2003.05997/) (2020)
- [Fast Computation of Wasserstein Barycenters](https://mlsanity.com/paper/1310.4375/) (2013)
- [On Embeddings for Numerical Features in Tabular Deep Learning](https://mlsanity.com/paper/2203.05556/) (2022)
- [Fast Transformers with Clustered Attention](https://mlsanity.com/paper/2007.04825/) (2020)
- [Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions](https://mlsanity.com/paper/1410.7827/) (2014)
- [ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context](https://mlsanity.com/paper/1911.12216/) (2019)
- [GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer](https://mlsanity.com/paper/2108.12630/) (2021)
- [HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data](https://mlsanity.com/paper/2111.08536/) (2021)
- [Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML](https://mlsanity.com/paper/2306.05109/) (2023)
- [Temporal Label Smoothing for Early Event Prediction](https://mlsanity.com/paper/2208.13764/) (2022)
- [Composite Feature Selection using Deep Ensembles](https://mlsanity.com/paper/2211.00631/) (2022)
- [Intrinsic User-Centric Interpretability through Global Mixture of Experts](https://mlsanity.com/paper/2402.02933/) (2024)
- [A Novel Cluster Detection of COVID-19 Patients and Medical Disease Conditions Using Improved Evolutionary Clustering Algorithm Star](https://mlsanity.com/paper/2109.09492/) (2021)
- [On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series](https://mlsanity.com/paper/2311.08902/) (2023)
- [Dynamic Survival Analysis for Early Event Prediction](https://mlsanity.com/paper/2403.12818/) (2024)
- [Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions](https://mlsanity.com/paper/2209.00322/) (2022)
- [Towards Foundation Models for Critical Care Time Series](https://mlsanity.com/paper/2411.16346/) (2024)
- [Failure Modes of Time Series Interpretability Algorithms for Critical Care Applications and Potential Solutions](https://mlsanity.com/paper/2506.19035/) (2025)

## Built on by (most cited first, 1 of 1)

- [Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data](https://mlsanity.com/paper/2607.01838/) (2026)

## Abstract (arXiv)

Clinical time series data are critical for patient monitoring and predictive modeling. These time series are typically multivariate and often comprise hundreds of heterogeneous features from different data sources. The grouping of features based on similarity and relevance to the prediction task has been shown to enhance the performance of deep learning architectures. However, defining these groups a priori using only semantic knowledge is challenging, even for domain experts. To address this, we propose a novel method that learns feature groups by clustering weights of feature-wise embedding layers. This approach seamlessly integrates into standard supervised training and discovers the groups that directly improve downstream performance on clinically relevant tasks. We demonstrate that our method outperforms static clustering approaches on synthetic data and achieves performance comparable to expert-defined groups on real-world medical data. Moreover, the learned feature groups are clinically interpretable, enabling data-driven discovery of task-relevant relationships between variables.