Generative Imputation with Uncertainty Calibration for Missing Clinical Time-Series Data
Article Sidebar
Main Article Content
Abstract
Missing observations are pervasive in clinical time-series data and can substantially affect the reliability of downstream machine learning models. This study develops an uncertainty-calibrated generative framework for reconstructing incomplete clinical trajectories while preserving uncertainty associated with missing measurements. The proposed method combines conditional generative modeling with temporal attention to estimate distributions of missing laboratory and physiological variables rather than producing deterministic point estimates. Multiple plausible trajectories are generated for each patient, and an uncertainty calibration module estimates the reliability of reconstructed values before they are used for downstream prediction. Experiments evaluate reconstruction performance under random, temporally clustered, and clinically informative missingness patterns with missing rates ranging from 10% to 50%. In addition to conventional imputation metrics, the evaluation measures the effect of reconstructed data on mortality and deterioration prediction. Results indicate that uncertainty-aware generative imputation maintains more stable downstream performance as missingness increases and avoids excessive confidence in highly uncertain reconstructed observations. The framework provides a practical approach for improving the reliability of AI models trained on incomplete real-world healthcare data.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Mind forge Academia also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.
References
H. Harutyunyan et al., “Multitask learning and benchmarking with clinical time series data,” Scientific Data, vol. 6, Art. no. 96, 2019.
H. Zheng, L. Zhu, W. Cui, R. Pan, X. Yan, and Y. Xing, “Selective knowledge injection via adapter modules in large-scale language models,” ICAIDE, pp. 373–377, 2025.
Z. C. Lipton, D. C. Kale, and R. Wetzel, “Modeling missing data in clinical time series with RNNs,” Machine Learning for Healthcare, 2016.
X. Yan, W. Wang, M. Xiao, Y. Li, and M. Gao, “Survival prediction across diverse cancer types using neural networks,” pp. 134–138, 2024.
X. Yan, Y. Jiang, W. Liu, D. Yi, and J. Wei, “Transforming Multidimensional Time Series into Interpretable Event Sequences for Advanced Data Mining,” ICHCI, pp. 126–130, 2024.
Y. Li, W. Zhao, B. Dang, X. Yan, M. Gao, W. Wang, and M. Xiao, “Research on adverse drug reaction prediction model combining knowledge graph embedding and deep learning,” MLISE, pp. 322–329, 2024.
Y. Luo, Y. Zhang, X. Cai, and X. Yuan, “E²GAN: End-to-end generative adversarial network for multivariate time series imputation,” IJCAI, pp. 3094–3100, 2019.
X. Yan, J. Du, X. Li, X. Wang, X. Sun, P. Li, and H. Zheng, “A Hierarchical Feature Fusion and Dynamic Collaboration Framework for Robust Small Target Detection,” IEEE Access, vol. 13, pp. 92953–92964, 2025.
J. Wei, Y. Liu, X. Huang, X. Zhang, W. Liu, and X. Yan, “Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networks,” ICMLCA, pp. 272–276, 2024.
H. Zheng, Y. Ma, Y. Wang, G. Liu, Z. Qi, and X. Yan, “Structuring low-rank adaptation with semantic guidance for model fine-tuning,” ICECAI, pp. 731–735, 2025.
A. Rajkomar et al., “Scalable and accurate deep learning with electronic health records,” npj Digital Medicine, vol. 1, Art. no. 18, 2018.
W. Wang, Y. Li, X. Yan, M. Xiao, and M. Gao, “Breast cancer image classification method based on deep transfer learning,” pp. 190–197, 2024.
Y. Li, X. Yan, M. Xiao, W. Wang, and F. Zhang, “Investigation of Creating Accessibility Linked Data Based on Publicly Available Accessibility Datasets,” pp. 77–81, 2024.
R. Miotto, L. Li, B. A. Kidd, and J. T. Dudley, “Deep Patient: An unsupervised representation to predict the future of patients from the electronic health records,” Scientific Reports, vol. 6, Art. no. 26094, 2016.
M. Xiao, Y. Li, X. Yan, M. Gao, and W. Wang, “Convolutional neural network classification of cancer cytopathology images: Taking breast cancer as an example,” pp. 145–149, 2024.
X. Yan, J. Du, L. Wang, Y. Liang, J. Hu, and B. Wang, “The Synergistic Role of Deep Learning and Neural Architecture Search in Advancing Artificial Intelligence,” ICEDCS, pp. 452–456, 2024.
B. Shickel et al., “Deep EHR: A survey of recent advances in deep learning techniques for electronic health record analysis,” IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 5, pp. 1589–1604, 2018.
J. N. Acosta et al., “Multimodal biomedical AI,” Nature Medicine, vol. 28, pp. 1773–1784, 2022.