![[2602.20442] Imputation of Unknown Missingness in Sparse Electronic Health Records](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.20442] Imputation of Unknown Missingness in Sparse Electronic Health Records
Summary
The paper presents a novel algorithm for imputing unknown missing values in sparse electronic health records (EHRs) using a transformer-based denoising neural network, improving accuracy in medical coding and downstream tasks.
Why It Matters
As electronic health records are crucial for healthcare analytics, addressing the challenge of unknown missingness can enhance data quality and improve patient outcomes. This research contributes to the development of more reliable machine learning models in healthcare by tackling a significant gap in existing imputation techniques.
Key Takeaways
- Introduces a transformer-based algorithm for denoising EHR data.
- Addresses the issue of unknown missingness in medical records.
- Demonstrates improved accuracy over existing imputation methods.
- Enhances predictive performance for hospital readmission tasks.
- Contributes to better data quality in healthcare analytics.
Computer Science > Machine Learning arXiv:2602.20442 (cs) [Submitted on 24 Feb 2026] Title:Imputation of Unknown Missingness in Sparse Electronic Health Records Authors:Jun Han, Josue Nassar, Sanjit Singh Batra, Aldo Cordova-Palomera, Vijay Nori, Robert E. Tillman View a PDF of the paper titled Imputation of Unknown Missingness in Sparse Electronic Health Records, by Jun Han and 5 other authors View PDF HTML (experimental) Abstract:Machine learning holds great promise for advancing the field of medicine, with electronic health records (EHRs) serving as a primary data source. However, EHRs are often sparse and contain missing data due to various challenges and limitations in data collection and sharing between healthcare providers. Existing techniques for imputing missing values predominantly focus on known unknowns, such as missing or unavailable values of lab test results; most do not explicitly address situations where it is difficult to distinguish what is missing. For instance, a missing diagnosis code in an EHR could signify either that the patient has not been diagnosed with the condition or that a diagnosis was made, but not shared by a provider. Such situations fall into the paradigm of unknown unknowns. To address this challenge, we develop a general purpose algorithm for denoising data to recover unknown missing values in binary EHRs. We design a transformer-based denoising neural network where the output is thresholded adaptively to recover values in cases where...
