mlsanityData to 14 Oct 2026

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

arXiv 2210.08258 ↗First posted 15 Oct 2022cs.LGcited by 25

Not on the map. Why?

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.

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

24 of 146 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2014Conditional Generative Adversarial Netscited by 2,162
  5. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  6. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  7. 2020Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease predictioncited by 373
  8. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  9. 2019CollaGAN : Collaborative GAN for Missing Image Data Imputationcited by 33
  10. 2020Uncertainty-Aware Variational-Recurrent Imputation Network for Clinical Time Seriescited by 33
  11. 2020Longitudinal Variational Autoencodercited by 25
  12. 2021Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problemscited by 15
12 more
  1. 2019Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modelingcited by 14
  2. 2022Missing Value Estimation using Clustering and Deep Learning within Multiple Imputation Frameworkcited by 13
  3. 2020Neural ODEs for Informative Missingness in Multivariate Time Seriescited by 7
  4. 2020Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problemscited by 6
  5. 2020Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)cited by 6
  6. 2020Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Predictioncited by 4
  7. 2021Machine Learning Applications for Therapeutic Tasks with Genomics Datacited by 3
  8. 2022Compound Density Networks for Risk Prediction using Electronic Health Recordscited by 3
  9. 2020Multiple Imputation for Biomedical Data using Monte Carlo Dropout Autoencoderscited by 2
  10. 2022Comparison of Missing Data Imputation Methods using the Framingham Heart study datasetcited by 2
  11. 2020fMRI Multiple Missing Values Imputation Regularized by a Recurrent Denoisercited by 1
  12. 2022Coupling Deep Imputation with Multitask Learning for Downstream Tasks on Genomics Datacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 9; 2025: 10; 2026: 2.

25 papers.

Sort:

By area:

  1. 2024Generative AI for Synthetic Data Generation: Methods, Challenges and the Futurecited by 33
  2. 2024Not Another Imputation Method: A Transformer-based Model for Missing Values in Tabular Datasetscited by 10
  3. 2023PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representationscited by 9
  4. 2024Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputationcited by 6
  5. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  6. 2025Timely Clinical Diagnosis through Active Test Selectioncited by 4
  7. 2023Leveraging Anatomical Constraints with Uncertainty for Pneumothorax Segmentationcited by 3
  8. 2025A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoptioncited by 3
  9. 2025LLM-Aided Customizable Profiling of Code Data Based On Programming Language Conceptscited by 2
  10. 2024Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classificationcited by 1
  11. 2024Still More Shades of Null: An Evaluation Suite for Responsible Missing Value Imputationcited by 1
  12. 2024Enhancing Glucose Level Prediction of ICU Patients through Hierarchical Modeling of Irregular Time-Seriescited by 1
13 more
  1. 2025MissMecha: An All-in-One Python Package for Studying Missing Data Mechanismscited by 1
  2. 2023Machine Learning Based Missing Values Imputation in Categorical Datasetscited by 0
  3. 2023Enhancing Mortality Prediction in Heart Failure Patients: Exploring Preprocessing Methods for Imbalanced Clinical Datasetscited by 0
  4. 2024METRIK: Measurement-Efficient Randomized Controlled Trials using Transformers with Input Maskingcited by 0
  5. 2024Modular Deep Learning for Multivariate Time-Series: Decoupling Imputation and Downstream Taskscited by 0
  6. 2025Evaluation of the impact of expert knowledge: How decision support scores impact the effectiveness of automatic knowledge-driven feature engineering (aKDFE)cited by 0
  7. 2025IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)cited by 0
  8. 2025Data-driven Insights for Informed Decision-Making: Applying LSTM Networks for Robust Electricity Forecasting in Libyacited by 0
  9. 2025TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Datacited by 0
  10. 2025A Systematic Review on the Generative AI Applications in Human Medical Genomicscited by 0
  11. 2025An Interdisciplinary and Cross-Task Review on Missing Data Imputationcited by 0
  12. 2026Temporal Fusion Nexus: A task-agnostic multi-modal embedding model for clinical narratives and irregular time series in post-kidney transplant carecited by 0
  13. 2026Imputation of Unknown Missingness in Sparse Electronic Health Recordscited by 0