# Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction

arXiv: https://arxiv.org/abs/2401.16796 · HTML: https://mlsanity.com/paper/2401.16796/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://mlsanity.com/paper/2010.15980/) (2020)
- [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)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [What's a good imputation to predict with missing values?](https://mlsanity.com/paper/2106.00311/) (2021)
- [NAOMI: Non-Autoregressive Multiresolution Sequence Imputation](https://mlsanity.com/paper/1901.10946/) (2019)
- [ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context](https://mlsanity.com/paper/1911.12216/) (2019)
- [Missing Value Imputation on Multidimensional Time Series](https://mlsanity.com/paper/2103.01600/) (2021)
- [Longitudinal Variational Autoencoder](https://mlsanity.com/paper/2006.09763/) (2020)
- [NRTSI: Non-Recurrent Time Series Imputation](https://mlsanity.com/paper/2102.03340/) (2021)
- [PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning](https://mlsanity.com/paper/2211.01761/) (2022)
- [A Comprehensive Benchmark for COVID-19 Predictive Modeling Using Electronic Health Records in Intensive Care](https://mlsanity.com/paper/2209.07805/) (2022)

## Built on by (most cited first, 4 of 4)

- [Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation](https://mlsanity.com/paper/2508.08730/) (2025)
- [HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating](https://mlsanity.com/paper/2602.13665/) (2026)
- [Ocular-Induced Abnormal Head Posture: Diagnosis and Missing Data Imputation](https://mlsanity.com/paper/2510.05649/) (2025)
- [Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge](https://mlsanity.com/paper/2609.01839/) (2026)

## Abstract (arXiv)

Analyzing the health status of patients based on Electronic Health Records (EHR) is a fundamental research problem in medical informatics. The presence of extensive missing values in EHR makes it challenging for deep neural networks (DNNs) to directly model the patient's health status. Existing DNNs training protocols, including Impute-then-Regress Procedure and Jointly Optimizing of Impute-n-Regress Procedure, require the additional imputation models to reconstruction missing values. However, Impute-then-Regress Procedure introduces the risk of injecting imputed, non-real data into downstream clinical prediction tasks, resulting in power loss, biased estimation, and poorly performing models, while Jointly Optimizing of Impute-n-Regress Procedure is also difficult to generalize due to the complex optimization space and demanding data requirements. Inspired by the recent advanced literature of learnable prompt in the fields of NLP and CV, in this work, we rethought the necessity of the imputation model in downstream clinical tasks, and proposed Learnable Prompt as Pseudo-Imputation (PAI) as a new training protocol to assist EHR analysis. PAI no longer introduces any imputed data but constructs a learnable prompt to model the implicit preferences of the downstream model for missing values, resulting in a significant performance improvement for all state-of-the-arts EHR analysis models on four real-world datasets across two clinical prediction tasks. Further experimental analysis indicates that PAI exhibits higher robustness in situations of data insufficiency and high missing rates. More importantly, as a plug-and-play protocol, PAI can be easily integrated into any existing or even imperceptible future EHR analysis models.