# Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques

arXiv: https://arxiv.org/abs/2210.08258 · HTML: https://mlsanity.com/paper/2210.08258/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 146 references that are in the map.
- First posted on arXiv 15 Oct 2022.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks](https://mlsanity.com/paper/1711.08742/) (2017)
- [CollaGAN : Collaborative GAN for Missing Image Data Imputation](https://mlsanity.com/paper/1901.09764/) (2019)
- [Uncertainty-Aware Variational-Recurrent Imputation Network for Clinical Time Series](https://mlsanity.com/paper/2003.00662/) (2020)
- [Longitudinal Variational Autoencoder](https://mlsanity.com/paper/2006.09763/) (2020)
- [Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems](https://mlsanity.com/paper/2112.11507/) (2021)
- [Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling](https://mlsanity.com/paper/1903.07173/) (2019)
- [Missing Value Estimation using Clustering and Deep Learning within Multiple Imputation Framework](https://mlsanity.com/paper/2202.13734/) (2022)
- [Neural ODEs for Informative Missingness in Multivariate Time Series](https://mlsanity.com/paper/2005.10693/) (2020)
- [Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems](https://mlsanity.com/paper/2004.02584/) (2020)
- [Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)](https://mlsanity.com/paper/2005.06935/) (2020)
- [Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction](https://mlsanity.com/paper/2003.00655/) (2020)
- [Machine Learning Applications for Therapeutic Tasks with Genomics Data](https://mlsanity.com/paper/2105.01171/) (2021)
- [Compound Density Networks for Risk Prediction using Electronic Health Records](https://mlsanity.com/paper/2208.01320/) (2022)
- [Multiple Imputation for Biomedical Data using Monte Carlo Dropout Autoencoders](https://mlsanity.com/paper/2005.06173/) (2020)
- [Comparison of Missing Data Imputation Methods using the Framingham Heart study dataset](https://mlsanity.com/paper/2210.03154/) (2022)
- [fMRI Multiple Missing Values Imputation Regularized by a Recurrent Denoiser](https://mlsanity.com/paper/2009.12602/) (2020)
- [Coupling Deep Imputation with Multitask Learning for Downstream Tasks on Genomics Data](https://mlsanity.com/paper/2204.13705/) (2022)

## Built on by (most cited first, 25 of 25)

- [Generative AI for Synthetic Data Generation: Methods, Challenges and the Future](https://mlsanity.com/paper/2403.04190/) (2024)
- [Not Another Imputation Method: A Transformer-based Model for Missing Values in Tabular Datasets](https://mlsanity.com/paper/2407.11540/) (2024)
- [PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representations](https://mlsanity.com/paper/2309.04160/) (2023)
- [Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputation](https://mlsanity.com/paper/2405.17508/) (2024)
- [How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation](https://mlsanity.com/paper/2407.08442/) (2024)
- [Timely Clinical Diagnosis through Active Test Selection](https://mlsanity.com/paper/2510.18988/) (2025)
- [Leveraging Anatomical Constraints with Uncertainty for Pneumothorax Segmentation](https://mlsanity.com/paper/2311.15213/) (2023)
- [A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoption](https://mlsanity.com/paper/2504.19179/) (2025)
- [LLM-Aided Customizable Profiling of Code Data Based On Programming Language Concepts](https://mlsanity.com/paper/2503.15571/) (2025)
- [Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification](https://mlsanity.com/paper/2403.18871/) (2024)
- [Still More Shades of Null: An Evaluation Suite for Responsible Missing Value Imputation](https://mlsanity.com/paper/2409.07510/) (2024)
- [Enhancing Glucose Level Prediction of ICU Patients through Hierarchical Modeling of Irregular Time-Series](https://mlsanity.com/paper/2411.01418/) (2024)
- [MissMecha: An All-in-One Python Package for Studying Missing Data Mechanisms](https://mlsanity.com/paper/2508.04740/) (2025)
- [Machine Learning Based Missing Values Imputation in Categorical Datasets](https://mlsanity.com/paper/2306.06338/) (2023)
- [Enhancing Mortality Prediction in Heart Failure Patients: Exploring Preprocessing Methods for Imbalanced Clinical Datasets](https://mlsanity.com/paper/2310.00457/) (2023)
- [METRIK: Measurement-Efficient Randomized Controlled Trials using Transformers with Input Masking](https://mlsanity.com/paper/2406.16351/) (2024)
- [Modular Deep Learning for Multivariate Time-Series: Decoupling Imputation and Downstream Tasks](https://mlsanity.com/paper/2411.03941/) (2024)
- [Evaluation of the impact of expert knowledge: How decision support scores impact the effectiveness of automatic knowledge-driven feature engineering (aKDFE)](https://mlsanity.com/paper/2504.05928/) (2025)
- [IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)](https://mlsanity.com/paper/2506.08844/) (2025)
- [Data-driven Insights for Informed Decision-Making: Applying LSTM Networks for Robust Electricity Forecasting in Libya](https://mlsanity.com/paper/2507.01034/) (2025)
- [TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Data](https://mlsanity.com/paper/2508.01615/) (2025)
- [A Systematic Review on the Generative AI Applications in Human Medical Genomics](https://mlsanity.com/paper/2508.20275/) (2025)
- [An Interdisciplinary and Cross-Task Review on Missing Data Imputation](https://mlsanity.com/paper/2511.01196/) (2025)
- [Temporal Fusion Nexus: A task-agnostic multi-modal embedding model for clinical narratives and irregular time series in post-kidney transplant care](https://mlsanity.com/paper/2601.08503/) (2026)
- [Imputation of Unknown Missingness in Sparse Electronic Health Records](https://mlsanity.com/paper/2602.20442/) (2026)

## Abstract (arXiv)

Objective: The proper handling of missing values is critical to delivering reliable estimates and decisions, especially in high-stakes fields such as clinical research. The increasing diversity and complexity of data have led many researchers to develop deep learning (DL)-based imputation techniques. We conducted a systematic review to evaluate the use of these techniques, with a particular focus on data types, aiming to assist healthcare researchers from various disciplines in dealing with missing values. Methods: We searched five databases (MEDLINE, Web of Science, Embase, CINAHL, and Scopus) for articles published prior to August 2021 that applied DL-based models to imputation. We assessed selected publications from four perspectives: health data types, model backbone (i.e., main architecture), imputation strategies, and comparison with non-DL-based methods. Based on data types, we created an evidence map to illustrate the adoption of DL models. Results: We included 64 articles, of which tabular static (26.6%, 17/64) and temporal data (37.5%, 24/64) were the most frequently investigated. We found that model backbone(s) differed among data types as well as the imputation strategy. The "integrated" strategy, that is, the imputation task being solved concurrently with downstream tasks, was popular for tabular temporal (50%, 12/24) and multi-modal data (71.4%, 5/7), but limited for other data types. Moreover, DL-based imputation methods yielded better imputation accuracy in most studies, compared with non-DL-based methods. Conclusion: DL-based imputation models can be customized based on data type, addressing the corresponding missing patterns, and its associated "integrated" strategy can enhance the efficacy of imputation, especially in scenarios where data is complex. Future research may focus on the portability and fairness of DL-based models for healthcare data imputation.