# Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputation

arXiv: https://arxiv.org/abs/2405.17508 · HTML: https://mlsanity.com/paper/2405.17508/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 26 May 2024.

## Builds on (most cited first, 9 of 9)

- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [GP-VAE: Deep Probabilistic Time Series Imputation](https://mlsanity.com/paper/1907.04155/) (2019)
- [SAITS: Self-Attention-based Imputation for Time Series](https://mlsanity.com/paper/2202.08516/) (2022)
- [Deep Learning for Multivariate Time Series Imputation: A Survey](https://mlsanity.com/paper/2402.04059/) (2024)
- [Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques](https://mlsanity.com/paper/2210.08258/) (2022)
- [PyPOTS: A Python Toolkit for Machine Learning on Partially-Observed Time Series](https://mlsanity.com/paper/2305.18811/) (2023)

## Built on by (most cited first, 6 of 6)

- [TSI-Bench: Benchmarking Time Series Imputation](https://mlsanity.com/paper/2406.12747/) (2024)
- [Intelligent Cross-Organizational Process Mining: A Survey and New Perspectives](https://mlsanity.com/paper/2407.11280/) (2024)
- [SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data](https://mlsanity.com/paper/2505.19193/) (2025)
- [Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction](https://mlsanity.com/paper/2510.06029/) (2025)
- [Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation](https://mlsanity.com/paper/2605.02742/) (2026)
- [Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness](https://mlsanity.com/paper/2608.21207/) (2026)

## Abstract (arXiv)

This study investigates the impact of masking strategies on time series imputation models in healthcare settings. While current approaches predominantly rely on random masking for model evaluation, this practice fails to capture the structured nature of missing patterns in clinical data. Using the PhysioNet Challenge 2012 dataset, we analyse how different masking implementations affect both imputation accuracy and downstream clinical predictions across eleven imputation methods. Our results demonstrate that masking choices significantly influence model performance, while recurrent architectures show more consistent performance across strategies. Analysis of downstream mortality prediction reveals that imputation accuracy doesn't necessarily translate to optimal clinical prediction capabilities. Our findings emphasise the need for clinically-informed masking strategies that better reflect real-world missing patterns in healthcare data, suggesting current evaluation frameworks may need reconsideration for reliable clinical deployment.